process of case study method

The Ultimate Guide to Qualitative Research - Part 1: The Basics

• Introduction and overview
• What is qualitative research?
• What is qualitative data?
• Examples of qualitative data
• Qualitative vs. quantitative research
• Mixed methods
• Qualitative research preparation
• Theoretical perspective
• Theoretical framework
• Literature reviews

Research question

• Conceptual framework
• Conceptual vs. theoretical framework

Data collection

• Qualitative research methods
• Focus groups
• Observational research

What is a case study?

Applications for case study research, what is a good case study, process of case study design, benefits and limitations of case studies.

• Ethnographical research
• Ethical considerations
• Confidentiality and privacy
• Power dynamics
• Reflexivity

Case studies

Case studies are essential to qualitative research , offering a lens through which researchers can investigate complex phenomena within their real-life contexts. This chapter explores the concept, purpose, applications, examples, and types of case studies and provides guidance on how to conduct case study research effectively.

Whereas quantitative methods look at phenomena at scale, case study research looks at a concept or phenomenon in considerable detail. While analyzing a single case can help understand one perspective regarding the object of research inquiry, analyzing multiple cases can help obtain a more holistic sense of the topic or issue. Let's provide a basic definition of a case study, then explore its characteristics and role in the qualitative research process.

Definition of a case study

A case study in qualitative research is a strategy of inquiry that involves an in-depth investigation of a phenomenon within its real-world context. It provides researchers with the opportunity to acquire an in-depth understanding of intricate details that might not be as apparent or accessible through other methods of research. The specific case or cases being studied can be a single person, group, or organization – demarcating what constitutes a relevant case worth studying depends on the researcher and their research question .

Among qualitative research methods , a case study relies on multiple sources of evidence, such as documents, artifacts, interviews , or observations , to present a complete and nuanced understanding of the phenomenon under investigation. The objective is to illuminate the readers' understanding of the phenomenon beyond its abstract statistical or theoretical explanations.

Characteristics of case studies

Case studies typically possess a number of distinct characteristics that set them apart from other research methods. These characteristics include a focus on holistic description and explanation, flexibility in the design and data collection methods, reliance on multiple sources of evidence, and emphasis on the context in which the phenomenon occurs.

Furthermore, case studies can often involve a longitudinal examination of the case, meaning they study the case over a period of time. These characteristics allow case studies to yield comprehensive, in-depth, and richly contextualized insights about the phenomenon of interest.

The role of case studies in research

Case studies hold a unique position in the broader landscape of research methods aimed at theory development. They are instrumental when the primary research interest is to gain an intensive, detailed understanding of a phenomenon in its real-life context.

In addition, case studies can serve different purposes within research - they can be used for exploratory, descriptive, or explanatory purposes, depending on the research question and objectives. This flexibility and depth make case studies a valuable tool in the toolkit of qualitative researchers.

Remember, a well-conducted case study can offer a rich, insightful contribution to both academic and practical knowledge through theory development or theory verification, thus enhancing our understanding of complex phenomena in their real-world contexts.

What is the purpose of a case study?

Case study research aims for a more comprehensive understanding of phenomena, requiring various research methods to gather information for qualitative analysis . Ultimately, a case study can allow the researcher to gain insight into a particular object of inquiry and develop a theoretical framework relevant to the research inquiry.

Why use case studies in qualitative research?

Using case studies as a research strategy depends mainly on the nature of the research question and the researcher's access to the data.

Conducting case study research provides a level of detail and contextual richness that other research methods might not offer. They are beneficial when there's a need to understand complex social phenomena within their natural contexts.

The explanatory, exploratory, and descriptive roles of case studies

Case studies can take on various roles depending on the research objectives. They can be exploratory when the research aims to discover new phenomena or define new research questions; they are descriptive when the objective is to depict a phenomenon within its context in a detailed manner; and they can be explanatory if the goal is to understand specific relationships within the studied context. Thus, the versatility of case studies allows researchers to approach their topic from different angles, offering multiple ways to uncover and interpret the data .

The impact of case studies on knowledge development

Case studies play a significant role in knowledge development across various disciplines. Analysis of cases provides an avenue for researchers to explore phenomena within their context based on the collected data.

This can result in the production of rich, practical insights that can be instrumental in both theory-building and practice. Case studies allow researchers to delve into the intricacies and complexities of real-life situations, uncovering insights that might otherwise remain hidden.

Types of case studies

In qualitative research , a case study is not a one-size-fits-all approach. Depending on the nature of the research question and the specific objectives of the study, researchers might choose to use different types of case studies. These types differ in their focus, methodology, and the level of detail they provide about the phenomenon under investigation.

Understanding these types is crucial for selecting the most appropriate approach for your research project and effectively achieving your research goals. Let's briefly look at the main types of case studies.

Exploratory case studies

Exploratory case studies are typically conducted to develop a theory or framework around an understudied phenomenon. They can also serve as a precursor to a larger-scale research project. Exploratory case studies are useful when a researcher wants to identify the key issues or questions which can spur more extensive study or be used to develop propositions for further research. These case studies are characterized by flexibility, allowing researchers to explore various aspects of a phenomenon as they emerge, which can also form the foundation for subsequent studies.

Descriptive case studies

Descriptive case studies aim to provide a complete and accurate representation of a phenomenon or event within its context. These case studies are often based on an established theoretical framework, which guides how data is collected and analyzed. The researcher is concerned with describing the phenomenon in detail, as it occurs naturally, without trying to influence or manipulate it.

Explanatory case studies

Explanatory case studies are focused on explanation - they seek to clarify how or why certain phenomena occur. Often used in complex, real-life situations, they can be particularly valuable in clarifying causal relationships among concepts and understanding the interplay between different factors within a specific context.

Intrinsic, instrumental, and collective case studies

These three categories of case studies focus on the nature and purpose of the study. An intrinsic case study is conducted when a researcher has an inherent interest in the case itself. Instrumental case studies are employed when the case is used to provide insight into a particular issue or phenomenon. A collective case study, on the other hand, involves studying multiple cases simultaneously to investigate some general phenomena.

Each type of case study serves a different purpose and has its own strengths and challenges. The selection of the type should be guided by the research question and objectives, as well as the context and constraints of the research.

The flexibility, depth, and contextual richness offered by case studies make this approach an excellent research method for various fields of study. They enable researchers to investigate real-world phenomena within their specific contexts, capturing nuances that other research methods might miss. Across numerous fields, case studies provide valuable insights into complex issues.

Critical information systems research

Case studies provide a detailed understanding of the role and impact of information systems in different contexts. They offer a platform to explore how information systems are designed, implemented, and used and how they interact with various social, economic, and political factors. Case studies in this field often focus on examining the intricate relationship between technology, organizational processes, and user behavior, helping to uncover insights that can inform better system design and implementation.

Health research

Health research is another field where case studies are highly valuable. They offer a way to explore patient experiences, healthcare delivery processes, and the impact of various interventions in a real-world context.

Case studies can provide a deep understanding of a patient's journey, giving insights into the intricacies of disease progression, treatment effects, and the psychosocial aspects of health and illness.

Asthma research studies

Specifically within medical research, studies on asthma often employ case studies to explore the individual and environmental factors that influence asthma development, management, and outcomes. A case study can provide rich, detailed data about individual patients' experiences, from the triggers and symptoms they experience to the effectiveness of various management strategies. This can be crucial for developing patient-centered asthma care approaches.

Other fields

Apart from the fields mentioned, case studies are also extensively used in business and management research, education research, and political sciences, among many others. They provide an opportunity to delve into the intricacies of real-world situations, allowing for a comprehensive understanding of various phenomena.

Case studies, with their depth and contextual focus, offer unique insights across these varied fields. They allow researchers to illuminate the complexities of real-life situations, contributing to both theory and practice.

Whatever field you're in, ATLAS.ti puts your data to work for you

Download a free trial of ATLAS.ti to turn your data into insights.

Understanding the key elements of case study design is crucial for conducting rigorous and impactful case study research. A well-structured design guides the researcher through the process, ensuring that the study is methodologically sound and its findings are reliable and valid. The main elements of case study design include the research question , propositions, units of analysis, and the logic linking the data to the propositions.

The research question is the foundation of any research study. A good research question guides the direction of the study and informs the selection of the case, the methods of collecting data, and the analysis techniques. A well-formulated research question in case study research is typically clear, focused, and complex enough to merit further detailed examination of the relevant case(s).

Propositions

Propositions, though not necessary in every case study, provide a direction by stating what we might expect to find in the data collected. They guide how data is collected and analyzed by helping researchers focus on specific aspects of the case. They are particularly important in explanatory case studies, which seek to understand the relationships among concepts within the studied phenomenon.

Units of analysis

The unit of analysis refers to the case, or the main entity or entities that are being analyzed in the study. In case study research, the unit of analysis can be an individual, a group, an organization, a decision, an event, or even a time period. It's crucial to clearly define the unit of analysis, as it shapes the qualitative data analysis process by allowing the researcher to analyze a particular case and synthesize analysis across multiple case studies to draw conclusions.

Argumentation

This refers to the inferential model that allows researchers to draw conclusions from the data. The researcher needs to ensure that there is a clear link between the data, the propositions (if any), and the conclusions drawn. This argumentation is what enables the researcher to make valid and credible inferences about the phenomenon under study.

Understanding and carefully considering these elements in the design phase of a case study can significantly enhance the quality of the research. It can help ensure that the study is methodologically sound and its findings contribute meaningful insights about the case.

Ready to jumpstart your research with ATLAS.ti?

Conceptualize your research project with our intuitive data analysis interface. Download a free trial today.

Conducting a case study involves several steps, from defining the research question and selecting the case to collecting and analyzing data . This section outlines these key stages, providing a practical guide on how to conduct case study research.

Defining the research question

The first step in case study research is defining a clear, focused research question. This question should guide the entire research process, from case selection to analysis. It's crucial to ensure that the research question is suitable for a case study approach. Typically, such questions are exploratory or descriptive in nature and focus on understanding a phenomenon within its real-life context.

Selecting and defining the case

The selection of the case should be based on the research question and the objectives of the study. It involves choosing a unique example or a set of examples that provide rich, in-depth data about the phenomenon under investigation. After selecting the case, it's crucial to define it clearly, setting the boundaries of the case, including the time period and the specific context.

Previous research can help guide the case study design. When considering a case study, an example of a case could be taken from previous case study research and used to define cases in a new research inquiry. Considering recently published examples can help understand how to select and define cases effectively.

Developing a detailed case study protocol

A case study protocol outlines the procedures and general rules to be followed during the case study. This includes the data collection methods to be used, the sources of data, and the procedures for analysis. Having a detailed case study protocol ensures consistency and reliability in the study.

The protocol should also consider how to work with the people involved in the research context to grant the research team access to collecting data. As mentioned in previous sections of this guide, establishing rapport is an essential component of qualitative research as it shapes the overall potential for collecting and analyzing data.

Collecting data

Gathering data in case study research often involves multiple sources of evidence, including documents, archival records, interviews, observations, and physical artifacts. This allows for a comprehensive understanding of the case. The process for gathering data should be systematic and carefully documented to ensure the reliability and validity of the study.

Analyzing and interpreting data

The next step is analyzing the data. This involves organizing the data , categorizing it into themes or patterns , and interpreting these patterns to answer the research question. The analysis might also involve comparing the findings with prior research or theoretical propositions.

Writing the case study report

The final step is writing the case study report . This should provide a detailed description of the case, the data, the analysis process, and the findings. The report should be clear, organized, and carefully written to ensure that the reader can understand the case and the conclusions drawn from it.

Each of these steps is crucial in ensuring that the case study research is rigorous, reliable, and provides valuable insights about the case.

The type, depth, and quality of data in your study can significantly influence the validity and utility of the study. In case study research, data is usually collected from multiple sources to provide a comprehensive and nuanced understanding of the case. This section will outline the various methods of collecting data used in case study research and discuss considerations for ensuring the quality of the data.

Interviews are a common method of gathering data in case study research. They can provide rich, in-depth data about the perspectives, experiences, and interpretations of the individuals involved in the case. Interviews can be structured , semi-structured , or unstructured , depending on the research question and the degree of flexibility needed.

Observations

Observations involve the researcher observing the case in its natural setting, providing first-hand information about the case and its context. Observations can provide data that might not be revealed in interviews or documents, such as non-verbal cues or contextual information.

Documents and artifacts

Documents and archival records provide a valuable source of data in case study research. They can include reports, letters, memos, meeting minutes, email correspondence, and various public and private documents related to the case.

These records can provide historical context, corroborate evidence from other sources, and offer insights into the case that might not be apparent from interviews or observations.

Physical artifacts refer to any physical evidence related to the case, such as tools, products, or physical environments. These artifacts can provide tangible insights into the case, complementing the data gathered from other sources.

Ensuring the quality of data collection

Determining the quality of data in case study research requires careful planning and execution. It's crucial to ensure that the data is reliable, accurate, and relevant to the research question. This involves selecting appropriate methods of collecting data, properly training interviewers or observers, and systematically recording and storing the data. It also includes considering ethical issues related to collecting and handling data, such as obtaining informed consent and ensuring the privacy and confidentiality of the participants.

Data analysis

Analyzing case study research involves making sense of the rich, detailed data to answer the research question. This process can be challenging due to the volume and complexity of case study data. However, a systematic and rigorous approach to analysis can ensure that the findings are credible and meaningful. This section outlines the main steps and considerations in analyzing data in case study research.

Organizing the data

The first step in the analysis is organizing the data. This involves sorting the data into manageable sections, often according to the data source or the theme. This step can also involve transcribing interviews, digitizing physical artifacts, or organizing observational data.

Categorizing and coding the data

Once the data is organized, the next step is to categorize or code the data. This involves identifying common themes, patterns, or concepts in the data and assigning codes to relevant data segments. Coding can be done manually or with the help of software tools, and in either case, qualitative analysis software can greatly facilitate the entire coding process. Coding helps to reduce the data to a set of themes or categories that can be more easily analyzed.

Identifying patterns and themes

After coding the data, the researcher looks for patterns or themes in the coded data. This involves comparing and contrasting the codes and looking for relationships or patterns among them. The identified patterns and themes should help answer the research question.

Interpreting the data

Once patterns and themes have been identified, the next step is to interpret these findings. This involves explaining what the patterns or themes mean in the context of the research question and the case. This interpretation should be grounded in the data, but it can also involve drawing on theoretical concepts or prior research.

Verification of the data

The last step in the analysis is verification. This involves checking the accuracy and consistency of the analysis process and confirming that the findings are supported by the data. This can involve re-checking the original data, checking the consistency of codes, or seeking feedback from research participants or peers.

Like any research method , case study research has its strengths and limitations. Researchers must be aware of these, as they can influence the design, conduct, and interpretation of the study.

Understanding the strengths and limitations of case study research can also guide researchers in deciding whether this approach is suitable for their research question . This section outlines some of the key strengths and limitations of case study research.

Benefits include the following:

• Rich, detailed data: One of the main strengths of case study research is that it can generate rich, detailed data about the case. This can provide a deep understanding of the case and its context, which can be valuable in exploring complex phenomena.
• Flexibility: Case study research is flexible in terms of design , data collection , and analysis . A sufficient degree of flexibility allows the researcher to adapt the study according to the case and the emerging findings.
• Real-world context: Case study research involves studying the case in its real-world context, which can provide valuable insights into the interplay between the case and its context.
• Multiple sources of evidence: Case study research often involves collecting data from multiple sources , which can enhance the robustness and validity of the findings.

On the other hand, researchers should consider the following limitations:

• Generalizability: A common criticism of case study research is that its findings might not be generalizable to other cases due to the specificity and uniqueness of each case.
• Time and resource intensive: Case study research can be time and resource intensive due to the depth of the investigation and the amount of collected data.
• Complexity of analysis: The rich, detailed data generated in case study research can make analyzing the data challenging.
• Subjectivity: Given the nature of case study research, there may be a higher degree of subjectivity in interpreting the data , so researchers need to reflect on this and transparently convey to audiences how the research was conducted.

Being aware of these strengths and limitations can help researchers design and conduct case study research effectively and interpret and report the findings appropriately.

Ready to analyze your data with ATLAS.ti?

See how our intuitive software can draw key insights from your data with a free trial today.

Have a language expert improve your writing

Run a free plagiarism check in 10 minutes, automatically generate references for free.

• Knowledge Base
• Methodology
• Case Study | Definition, Examples & Methods

Case Study | Definition, Examples & Methods

Published on 5 May 2022 by Shona McCombes . Revised on 30 January 2023.

A case study is a detailed study of a specific subject, such as a person, group, place, event, organisation, or phenomenon. Case studies are commonly used in social, educational, clinical, and business research.

A case study research design usually involves qualitative methods , but quantitative methods are sometimes also used. Case studies are good for describing , comparing, evaluating, and understanding different aspects of a research problem .

Table of contents

When to do a case study, step 1: select a case, step 2: build a theoretical framework, step 3: collect your data, step 4: describe and analyse the case.

A case study is an appropriate research design when you want to gain concrete, contextual, in-depth knowledge about a specific real-world subject. It allows you to explore the key characteristics, meanings, and implications of the case.

Case studies are often a good choice in a thesis or dissertation . They keep your project focused and manageable when you don’t have the time or resources to do large-scale research.

You might use just one complex case study where you explore a single subject in depth, or conduct multiple case studies to compare and illuminate different aspects of your research problem.

Prevent plagiarism, run a free check.

Once you have developed your problem statement and research questions , you should be ready to choose the specific case that you want to focus on. A good case study should have the potential to:

• Provide new or unexpected insights into the subject
• Challenge or complicate existing assumptions and theories
• Propose practical courses of action to resolve a problem
• Open up new directions for future research

Unlike quantitative or experimental research, a strong case study does not require a random or representative sample. In fact, case studies often deliberately focus on unusual, neglected, or outlying cases which may shed new light on the research problem.

If you find yourself aiming to simultaneously investigate and solve an issue, consider conducting action research . As its name suggests, action research conducts research and takes action at the same time, and is highly iterative and flexible. 

However, you can also choose a more common or representative case to exemplify a particular category, experience, or phenomenon.

While case studies focus more on concrete details than general theories, they should usually have some connection with theory in the field. This way the case study is not just an isolated description, but is integrated into existing knowledge about the topic. It might aim to:

• Exemplify a theory by showing how it explains the case under investigation
• Expand on a theory by uncovering new concepts and ideas that need to be incorporated
• Challenge a theory by exploring an outlier case that doesn’t fit with established assumptions

To ensure that your analysis of the case has a solid academic grounding, you should conduct a literature review of sources related to the topic and develop a theoretical framework . This means identifying key concepts and theories to guide your analysis and interpretation.

There are many different research methods you can use to collect data on your subject. Case studies tend to focus on qualitative data using methods such as interviews, observations, and analysis of primary and secondary sources (e.g., newspaper articles, photographs, official records). Sometimes a case study will also collect quantitative data .

The aim is to gain as thorough an understanding as possible of the case and its context.

In writing up the case study, you need to bring together all the relevant aspects to give as complete a picture as possible of the subject.

How you report your findings depends on the type of research you are doing. Some case studies are structured like a standard scientific paper or thesis, with separate sections or chapters for the methods , results , and discussion .

Others are written in a more narrative style, aiming to explore the case from various angles and analyse its meanings and implications (for example, by using textual analysis or discourse analysis ).

In all cases, though, make sure to give contextual details about the case, connect it back to the literature and theory, and discuss how it fits into wider patterns or debates.

Cite this Scribbr article

If you want to cite this source, you can copy and paste the citation or click the ‘Cite this Scribbr article’ button to automatically add the citation to our free Reference Generator.

McCombes, S. (2023, January 30). Case Study | Definition, Examples & Methods. Scribbr. Retrieved 29 April 2024, from https://www.scribbr.co.uk/research-methods/case-studies/

Is this article helpful?

Shona McCombes

Other students also liked, correlational research | guide, design & examples, a quick guide to experimental design | 5 steps & examples, descriptive research design | definition, methods & examples.

What is the Case Study Method?

Overview Dropdown up

Overview dropdown down, celebrating 100 years of the case method at hbs.

The 2021-2022 academic year marks the 100-year anniversary of the introduction of the case method at Harvard Business School. Today, the HBS case method is employed in the HBS MBA program, in Executive Education programs, and in dozens of other business schools around the world. As Dean Srikant Datar's says, the case method has withstood the test of time.

Case Discussion Preparation Details Expand All Collapse All

In self-reflection in self-reflection dropdown down, in a small group setting in a small group setting dropdown down, in the classroom in the classroom dropdown down, beyond the classroom beyond the classroom dropdown down, how the case method creates value dropdown up, how the case method creates value dropdown down, in self-reflection, in a small group setting, in the classroom, beyond the classroom.

How Cases Unfold In the Classroom

How cases unfold in the classroom dropdown up, how cases unfold in the classroom dropdown down, preparation guidelines expand all collapse all, read the professor's assignment or discussion questions read the professor's assignment or discussion questions dropdown down, read the first few paragraphs and then skim the case read the first few paragraphs and then skim the case dropdown down, reread the case, underline text, and make margin notes reread the case, underline text, and make margin notes dropdown down, note the key problems on a pad of paper and go through the case again note the key problems on a pad of paper and go through the case again dropdown down, how to prepare for case discussions dropdown up, how to prepare for case discussions dropdown down, read the professor's assignment or discussion questions, read the first few paragraphs and then skim the case, reread the case, underline text, and make margin notes, note the key problems on a pad of paper and go through the case again, case study best practices expand all collapse all, prepare prepare dropdown down, discuss discuss dropdown down, participate participate dropdown down, relate relate dropdown down, apply apply dropdown down, note note dropdown down, understand understand dropdown down, case study best practices dropdown up, case study best practices dropdown down, participate, what can i expect on the first day dropdown down.

Most programs begin with registration, followed by an opening session and a dinner. If your travel plans necessitate late arrival, please be sure to notify us so that alternate registration arrangements can be made for you. Please note the following about registration:

HBS campus programs – Registration takes place in the Chao Center.

India programs – Registration takes place outside the classroom.

Other off-campus programs – Registration takes place in the designated facility.

What happens in class if nobody talks? Dropdown down

Professors are here to push everyone to learn, but not to embarrass anyone. If the class is quiet, they'll often ask a participant with experience in the industry in which the case is set to speak first. This is done well in advance so that person can come to class prepared to share. Trust the process. The more open you are, the more willing you’ll be to engage, and the more alive the classroom will become.

Does everyone take part in "role-playing"? Dropdown down

Professors often encourage participants to take opposing sides and then debate the issues, often taking the perspective of the case protagonists or key decision makers in the case.

View Frequently Asked Questions

Subscribe to Our Emails

Organizing Your Social Sciences Research Assignments

• Annotated Bibliography
• Analyzing a Scholarly Journal Article
• Group Presentations
• Dealing with Nervousness
• Using Visual Aids
• Grading Someone Else's Paper
• Types of Structured Group Activities
• Group Project Survival Skills
• Leading a Class Discussion
• Multiple Book Review Essay
• Reviewing Collected Works
• Writing a Case Analysis Paper
• Writing a Case Study
• About Informed Consent
• Writing Field Notes
• Writing a Policy Memo
• Writing a Reflective Paper
• Writing a Research Proposal
• Generative AI and Writing
• Acknowledgments

A case study research paper examines a person, place, event, condition, phenomenon, or other type of subject of analysis in order to extrapolate  key themes and results that help predict future trends, illuminate previously hidden issues that can be applied to practice, and/or provide a means for understanding an important research problem with greater clarity. A case study research paper usually examines a single subject of analysis, but case study papers can also be designed as a comparative investigation that shows relationships between two or more subjects. The methods used to study a case can rest within a quantitative, qualitative, or mixed-method investigative paradigm.

Case Studies. Writing@CSU. Colorado State University; Mills, Albert J. , Gabrielle Durepos, and Eiden Wiebe, editors. Encyclopedia of Case Study Research . Thousand Oaks, CA: SAGE Publications, 2010 ; “What is a Case Study?” In Swanborn, Peter G. Case Study Research: What, Why and How? London: SAGE, 2010.

How to Approach Writing a Case Study Research Paper

General information about how to choose a topic to investigate can be found under the " Choosing a Research Problem " tab in the Organizing Your Social Sciences Research Paper writing guide. Review this page because it may help you identify a subject of analysis that can be investigated using a case study design.

However, identifying a case to investigate involves more than choosing the research problem . A case study encompasses a problem contextualized around the application of in-depth analysis, interpretation, and discussion, often resulting in specific recommendations for action or for improving existing conditions. As Seawright and Gerring note, practical considerations such as time and access to information can influence case selection, but these issues should not be the sole factors used in describing the methodological justification for identifying a particular case to study. Given this, selecting a case includes considering the following:

• The case represents an unusual or atypical example of a research problem that requires more in-depth analysis? Cases often represent a topic that rests on the fringes of prior investigations because the case may provide new ways of understanding the research problem. For example, if the research problem is to identify strategies to improve policies that support girl's access to secondary education in predominantly Muslim nations, you could consider using Azerbaijan as a case study rather than selecting a more obvious nation in the Middle East. Doing so may reveal important new insights into recommending how governments in other predominantly Muslim nations can formulate policies that support improved access to education for girls.
• The case provides important insight or illuminate a previously hidden problem? In-depth analysis of a case can be based on the hypothesis that the case study will reveal trends or issues that have not been exposed in prior research or will reveal new and important implications for practice. For example, anecdotal evidence may suggest drug use among homeless veterans is related to their patterns of travel throughout the day. Assuming prior studies have not looked at individual travel choices as a way to study access to illicit drug use, a case study that observes a homeless veteran could reveal how issues of personal mobility choices facilitate regular access to illicit drugs. Note that it is important to conduct a thorough literature review to ensure that your assumption about the need to reveal new insights or previously hidden problems is valid and evidence-based.
• The case challenges and offers a counter-point to prevailing assumptions? Over time, research on any given topic can fall into a trap of developing assumptions based on outdated studies that are still applied to new or changing conditions or the idea that something should simply be accepted as "common sense," even though the issue has not been thoroughly tested in current practice. A case study analysis may offer an opportunity to gather evidence that challenges prevailing assumptions about a research problem and provide a new set of recommendations applied to practice that have not been tested previously. For example, perhaps there has been a long practice among scholars to apply a particular theory in explaining the relationship between two subjects of analysis. Your case could challenge this assumption by applying an innovative theoretical framework [perhaps borrowed from another discipline] to explore whether this approach offers new ways of understanding the research problem. Taking a contrarian stance is one of the most important ways that new knowledge and understanding develops from existing literature.
• The case provides an opportunity to pursue action leading to the resolution of a problem? Another way to think about choosing a case to study is to consider how the results from investigating a particular case may result in findings that reveal ways in which to resolve an existing or emerging problem. For example, studying the case of an unforeseen incident, such as a fatal accident at a railroad crossing, can reveal hidden issues that could be applied to preventative measures that contribute to reducing the chance of accidents in the future. In this example, a case study investigating the accident could lead to a better understanding of where to strategically locate additional signals at other railroad crossings so as to better warn drivers of an approaching train, particularly when visibility is hindered by heavy rain, fog, or at night.
• The case offers a new direction in future research? A case study can be used as a tool for an exploratory investigation that highlights the need for further research about the problem. A case can be used when there are few studies that help predict an outcome or that establish a clear understanding about how best to proceed in addressing a problem. For example, after conducting a thorough literature review [very important!], you discover that little research exists showing the ways in which women contribute to promoting water conservation in rural communities of east central Africa. A case study of how women contribute to saving water in a rural village of Uganda can lay the foundation for understanding the need for more thorough research that documents how women in their roles as cooks and family caregivers think about water as a valuable resource within their community. This example of a case study could also point to the need for scholars to build new theoretical frameworks around the topic [e.g., applying feminist theories of work and family to the issue of water conservation].

Eisenhardt, Kathleen M. “Building Theories from Case Study Research.” Academy of Management Review 14 (October 1989): 532-550; Emmel, Nick. Sampling and Choosing Cases in Qualitative Research: A Realist Approach . Thousand Oaks, CA: SAGE Publications, 2013; Gerring, John. “What Is a Case Study and What Is It Good for?” American Political Science Review 98 (May 2004): 341-354; Mills, Albert J. , Gabrielle Durepos, and Eiden Wiebe, editors. Encyclopedia of Case Study Research . Thousand Oaks, CA: SAGE Publications, 2010; Seawright, Jason and John Gerring. "Case Selection Techniques in Case Study Research." Political Research Quarterly 61 (June 2008): 294-308.

Structure and Writing Style

The purpose of a paper in the social sciences designed around a case study is to thoroughly investigate a subject of analysis in order to reveal a new understanding about the research problem and, in so doing, contributing new knowledge to what is already known from previous studies. In applied social sciences disciplines [e.g., education, social work, public administration, etc.], case studies may also be used to reveal best practices, highlight key programs, or investigate interesting aspects of professional work.

In general, the structure of a case study research paper is not all that different from a standard college-level research paper. However, there are subtle differences you should be aware of. Here are the key elements to organizing and writing a case study research paper.

I.  Introduction

As with any research paper, your introduction should serve as a roadmap for your readers to ascertain the scope and purpose of your study . The introduction to a case study research paper, however, should not only describe the research problem and its significance, but you should also succinctly describe why the case is being used and how it relates to addressing the problem. The two elements should be linked. With this in mind, a good introduction answers these four questions:

• What is being studied? Describe the research problem and describe the subject of analysis [the case] you have chosen to address the problem. Explain how they are linked and what elements of the case will help to expand knowledge and understanding about the problem.
• Why is this topic important to investigate? Describe the significance of the research problem and state why a case study design and the subject of analysis that the paper is designed around is appropriate in addressing the problem.
• What did we know about this topic before I did this study? Provide background that helps lead the reader into the more in-depth literature review to follow. If applicable, summarize prior case study research applied to the research problem and why it fails to adequately address the problem. Describe why your case will be useful. If no prior case studies have been used to address the research problem, explain why you have selected this subject of analysis.
• How will this study advance new knowledge or new ways of understanding? Explain why your case study will be suitable in helping to expand knowledge and understanding about the research problem.

Each of these questions should be addressed in no more than a few paragraphs. Exceptions to this can be when you are addressing a complex research problem or subject of analysis that requires more in-depth background information.

II.  Literature Review

The literature review for a case study research paper is generally structured the same as it is for any college-level research paper. The difference, however, is that the literature review is focused on providing background information and  enabling historical interpretation of the subject of analysis in relation to the research problem the case is intended to address . This includes synthesizing studies that help to:

• Place relevant works in the context of their contribution to understanding the case study being investigated . This would involve summarizing studies that have used a similar subject of analysis to investigate the research problem. If there is literature using the same or a very similar case to study, you need to explain why duplicating past research is important [e.g., conditions have changed; prior studies were conducted long ago, etc.].
• Describe the relationship each work has to the others under consideration that informs the reader why this case is applicable . Your literature review should include a description of any works that support using the case to investigate the research problem and the underlying research questions.
• Identify new ways to interpret prior research using the case study . If applicable, review any research that has examined the research problem using a different research design. Explain how your use of a case study design may reveal new knowledge or a new perspective or that can redirect research in an important new direction.
• Resolve conflicts amongst seemingly contradictory previous studies . This refers to synthesizing any literature that points to unresolved issues of concern about the research problem and describing how the subject of analysis that forms the case study can help resolve these existing contradictions.
• Point the way in fulfilling a need for additional research . Your review should examine any literature that lays a foundation for understanding why your case study design and the subject of analysis around which you have designed your study may reveal a new way of approaching the research problem or offer a perspective that points to the need for additional research.
• Expose any gaps that exist in the literature that the case study could help to fill . Summarize any literature that not only shows how your subject of analysis contributes to understanding the research problem, but how your case contributes to a new way of understanding the problem that prior research has failed to do.
• Locate your own research within the context of existing literature [very important!] . Collectively, your literature review should always place your case study within the larger domain of prior research about the problem. The overarching purpose of reviewing pertinent literature in a case study paper is to demonstrate that you have thoroughly identified and synthesized prior studies in relation to explaining the relevance of the case in addressing the research problem.

III.  Method

In this section, you explain why you selected a particular case [i.e., subject of analysis] and the strategy you used to identify and ultimately decide that your case was appropriate in addressing the research problem. The way you describe the methods used varies depending on the type of subject of analysis that constitutes your case study.

If your subject of analysis is an incident or event . In the social and behavioral sciences, the event or incident that represents the case to be studied is usually bounded by time and place, with a clear beginning and end and with an identifiable location or position relative to its surroundings. The subject of analysis can be a rare or critical event or it can focus on a typical or regular event. The purpose of studying a rare event is to illuminate new ways of thinking about the broader research problem or to test a hypothesis. Critical incident case studies must describe the method by which you identified the event and explain the process by which you determined the validity of this case to inform broader perspectives about the research problem or to reveal new findings. However, the event does not have to be a rare or uniquely significant to support new thinking about the research problem or to challenge an existing hypothesis. For example, Walo, Bull, and Breen conducted a case study to identify and evaluate the direct and indirect economic benefits and costs of a local sports event in the City of Lismore, New South Wales, Australia. The purpose of their study was to provide new insights from measuring the impact of a typical local sports event that prior studies could not measure well because they focused on large "mega-events." Whether the event is rare or not, the methods section should include an explanation of the following characteristics of the event: a) when did it take place; b) what were the underlying circumstances leading to the event; and, c) what were the consequences of the event in relation to the research problem.

If your subject of analysis is a person. Explain why you selected this particular individual to be studied and describe what experiences they have had that provide an opportunity to advance new understandings about the research problem. Mention any background about this person which might help the reader understand the significance of their experiences that make them worthy of study. This includes describing the relationships this person has had with other people, institutions, and/or events that support using them as the subject for a case study research paper. It is particularly important to differentiate the person as the subject of analysis from others and to succinctly explain how the person relates to examining the research problem [e.g., why is one politician in a particular local election used to show an increase in voter turnout from any other candidate running in the election]. Note that these issues apply to a specific group of people used as a case study unit of analysis [e.g., a classroom of students].

If your subject of analysis is a place. In general, a case study that investigates a place suggests a subject of analysis that is unique or special in some way and that this uniqueness can be used to build new understanding or knowledge about the research problem. A case study of a place must not only describe its various attributes relevant to the research problem [e.g., physical, social, historical, cultural, economic, political], but you must state the method by which you determined that this place will illuminate new understandings about the research problem. It is also important to articulate why a particular place as the case for study is being used if similar places also exist [i.e., if you are studying patterns of homeless encampments of veterans in open spaces, explain why you are studying Echo Park in Los Angeles rather than Griffith Park?]. If applicable, describe what type of human activity involving this place makes it a good choice to study [e.g., prior research suggests Echo Park has more homeless veterans].

If your subject of analysis is a phenomenon. A phenomenon refers to a fact, occurrence, or circumstance that can be studied or observed but with the cause or explanation to be in question. In this sense, a phenomenon that forms your subject of analysis can encompass anything that can be observed or presumed to exist but is not fully understood. In the social and behavioral sciences, the case usually focuses on human interaction within a complex physical, social, economic, cultural, or political system. For example, the phenomenon could be the observation that many vehicles used by ISIS fighters are small trucks with English language advertisements on them. The research problem could be that ISIS fighters are difficult to combat because they are highly mobile. The research questions could be how and by what means are these vehicles used by ISIS being supplied to the militants and how might supply lines to these vehicles be cut off? How might knowing the suppliers of these trucks reveal larger networks of collaborators and financial support? A case study of a phenomenon most often encompasses an in-depth analysis of a cause and effect that is grounded in an interactive relationship between people and their environment in some way.

NOTE:   The choice of the case or set of cases to study cannot appear random. Evidence that supports the method by which you identified and chose your subject of analysis should clearly support investigation of the research problem and linked to key findings from your literature review. Be sure to cite any studies that helped you determine that the case you chose was appropriate for examining the problem.

IV.  Discussion

The main elements of your discussion section are generally the same as any research paper, but centered around interpreting and drawing conclusions about the key findings from your analysis of the case study. Note that a general social sciences research paper may contain a separate section to report findings. However, in a paper designed around a case study, it is common to combine a description of the results with the discussion about their implications. The objectives of your discussion section should include the following:

Reiterate the Research Problem/State the Major Findings Briefly reiterate the research problem you are investigating and explain why the subject of analysis around which you designed the case study were used. You should then describe the findings revealed from your study of the case using direct, declarative, and succinct proclamation of the study results. Highlight any findings that were unexpected or especially profound.

Explain the Meaning of the Findings and Why They are Important Systematically explain the meaning of your case study findings and why you believe they are important. Begin this part of the section by repeating what you consider to be your most important or surprising finding first, then systematically review each finding. Be sure to thoroughly extrapolate what your analysis of the case can tell the reader about situations or conditions beyond the actual case that was studied while, at the same time, being careful not to misconstrue or conflate a finding that undermines the external validity of your conclusions.

Relate the Findings to Similar Studies No study in the social sciences is so novel or possesses such a restricted focus that it has absolutely no relation to previously published research. The discussion section should relate your case study results to those found in other studies, particularly if questions raised from prior studies served as the motivation for choosing your subject of analysis. This is important because comparing and contrasting the findings of other studies helps support the overall importance of your results and it highlights how and in what ways your case study design and the subject of analysis differs from prior research about the topic.

Consider Alternative Explanations of the Findings Remember that the purpose of social science research is to discover and not to prove. When writing the discussion section, you should carefully consider all possible explanations revealed by the case study results, rather than just those that fit your hypothesis or prior assumptions and biases. Be alert to what the in-depth analysis of the case may reveal about the research problem, including offering a contrarian perspective to what scholars have stated in prior research if that is how the findings can be interpreted from your case.

Acknowledge the Study's Limitations You can state the study's limitations in the conclusion section of your paper but describing the limitations of your subject of analysis in the discussion section provides an opportunity to identify the limitations and explain why they are not significant. This part of the discussion section should also note any unanswered questions or issues your case study could not address. More detailed information about how to document any limitations to your research can be found here .

Suggest Areas for Further Research Although your case study may offer important insights about the research problem, there are likely additional questions related to the problem that remain unanswered or findings that unexpectedly revealed themselves as a result of your in-depth analysis of the case. Be sure that the recommendations for further research are linked to the research problem and that you explain why your recommendations are valid in other contexts and based on the original assumptions of your study.

V.  Conclusion

As with any research paper, you should summarize your conclusion in clear, simple language; emphasize how the findings from your case study differs from or supports prior research and why. Do not simply reiterate the discussion section. Provide a synthesis of key findings presented in the paper to show how these converge to address the research problem. If you haven't already done so in the discussion section, be sure to document the limitations of your case study and any need for further research.

The function of your paper's conclusion is to: 1) reiterate the main argument supported by the findings from your case study; 2) state clearly the context, background, and necessity of pursuing the research problem using a case study design in relation to an issue, controversy, or a gap found from reviewing the literature; and, 3) provide a place to persuasively and succinctly restate the significance of your research problem, given that the reader has now been presented with in-depth information about the topic.

Consider the following points to help ensure your conclusion is appropriate:

• If the argument or purpose of your paper is complex, you may need to summarize these points for your reader.
• If prior to your conclusion, you have not yet explained the significance of your findings or if you are proceeding inductively, use the conclusion of your paper to describe your main points and explain their significance.
• Move from a detailed to a general level of consideration of the case study's findings that returns the topic to the context provided by the introduction or within a new context that emerges from your case study findings.

Note that, depending on the discipline you are writing in or the preferences of your professor, the concluding paragraph may contain your final reflections on the evidence presented as it applies to practice or on the essay's central research problem. However, the nature of being introspective about the subject of analysis you have investigated will depend on whether you are explicitly asked to express your observations in this way.

Problems to Avoid

Overgeneralization One of the goals of a case study is to lay a foundation for understanding broader trends and issues applied to similar circumstances. However, be careful when drawing conclusions from your case study. They must be evidence-based and grounded in the results of the study; otherwise, it is merely speculation. Looking at a prior example, it would be incorrect to state that a factor in improving girls access to education in Azerbaijan and the policy implications this may have for improving access in other Muslim nations is due to girls access to social media if there is no documentary evidence from your case study to indicate this. There may be anecdotal evidence that retention rates were better for girls who were engaged with social media, but this observation would only point to the need for further research and would not be a definitive finding if this was not a part of your original research agenda.

Failure to Document Limitations No case is going to reveal all that needs to be understood about a research problem. Therefore, just as you have to clearly state the limitations of a general research study , you must describe the specific limitations inherent in the subject of analysis. For example, the case of studying how women conceptualize the need for water conservation in a village in Uganda could have limited application in other cultural contexts or in areas where fresh water from rivers or lakes is plentiful and, therefore, conservation is understood more in terms of managing access rather than preserving access to a scarce resource.

Failure to Extrapolate All Possible Implications Just as you don't want to over-generalize from your case study findings, you also have to be thorough in the consideration of all possible outcomes or recommendations derived from your findings. If you do not, your reader may question the validity of your analysis, particularly if you failed to document an obvious outcome from your case study research. For example, in the case of studying the accident at the railroad crossing to evaluate where and what types of warning signals should be located, you failed to take into consideration speed limit signage as well as warning signals. When designing your case study, be sure you have thoroughly addressed all aspects of the problem and do not leave gaps in your analysis that leave the reader questioning the results.

Case Studies. Writing@CSU. Colorado State University; Gerring, John. Case Study Research: Principles and Practices . New York: Cambridge University Press, 2007; Merriam, Sharan B. Qualitative Research and Case Study Applications in Education . Rev. ed. San Francisco, CA: Jossey-Bass, 1998; Miller, Lisa L. “The Use of Case Studies in Law and Social Science Research.” Annual Review of Law and Social Science 14 (2018): TBD; Mills, Albert J., Gabrielle Durepos, and Eiden Wiebe, editors. Encyclopedia of Case Study Research . Thousand Oaks, CA: SAGE Publications, 2010; Putney, LeAnn Grogan. "Case Study." In Encyclopedia of Research Design , Neil J. Salkind, editor. (Thousand Oaks, CA: SAGE Publications, 2010), pp. 116-120; Simons, Helen. Case Study Research in Practice . London: SAGE Publications, 2009;  Kratochwill,  Thomas R. and Joel R. Levin, editors. Single-Case Research Design and Analysis: New Development for Psychology and Education .  Hilldsale, NJ: Lawrence Erlbaum Associates, 1992; Swanborn, Peter G. Case Study Research: What, Why and How? London : SAGE, 2010; Yin, Robert K. Case Study Research: Design and Methods . 6th edition. Los Angeles, CA, SAGE Publications, 2014; Walo, Maree, Adrian Bull, and Helen Breen. “Achieving Economic Benefits at Local Events: A Case Study of a Local Sports Event.” Festival Management and Event Tourism 4 (1996): 95-106.

Writing Tip

At Least Five Misconceptions about Case Study Research

Social science case studies are often perceived as limited in their ability to create new knowledge because they are not randomly selected and findings cannot be generalized to larger populations. Flyvbjerg examines five misunderstandings about case study research and systematically "corrects" each one. To quote, these are:

Misunderstanding 1 :  General, theoretical [context-independent] knowledge is more valuable than concrete, practical [context-dependent] knowledge. Misunderstanding 2 :  One cannot generalize on the basis of an individual case; therefore, the case study cannot contribute to scientific development. Misunderstanding 3 :  The case study is most useful for generating hypotheses; that is, in the first stage of a total research process, whereas other methods are more suitable for hypotheses testing and theory building. Misunderstanding 4 :  The case study contains a bias toward verification, that is, a tendency to confirm the researcher’s preconceived notions. Misunderstanding 5 :  It is often difficult to summarize and develop general propositions and theories on the basis of specific case studies [p. 221].

While writing your paper, think introspectively about how you addressed these misconceptions because to do so can help you strengthen the validity and reliability of your research by clarifying issues of case selection, the testing and challenging of existing assumptions, the interpretation of key findings, and the summation of case outcomes. Think of a case study research paper as a complete, in-depth narrative about the specific properties and key characteristics of your subject of analysis applied to the research problem.

Flyvbjerg, Bent. “Five Misunderstandings About Case-Study Research.” Qualitative Inquiry 12 (April 2006): 219-245.

• << Previous: Writing a Case Analysis Paper
• Next: Writing a Field Report >>
• Last Updated: Mar 6, 2024 1:00 PM
• URL: https://libguides.usc.edu/writingguide/assignments

• SUGGESTED TOPICS
• The Magazine
• Newsletters
• Managing Yourself
• Managing Teams
• Work-life Balance
• The Big Idea
• Data & Visuals
• Reading Lists
• Case Selections
• HBR Learning
• Topic Feeds
• Account Settings
• Email Preferences

What the Case Study Method Really Teaches

• Nitin Nohria

Seven meta-skills that stick even if the cases fade from memory.

It’s been 100 years since Harvard Business School began using the case study method. Beyond teaching specific subject matter, the case study method excels in instilling meta-skills in students. This article explains the importance of seven such skills: preparation, discernment, bias recognition, judgement, collaboration, curiosity, and self-confidence.

During my decade as dean of Harvard Business School, I spent hundreds of hours talking with our alumni. To enliven these conversations, I relied on a favorite question: “What was the most important thing you learned from your time in our MBA program?”

• Nitin Nohria is the George F. Baker Professor of Business Administration, Distinguished University Service Professor, and former dean of Harvard Business School.

Partner Center

• Business Essentials
• Leadership & Management
• Credential of Leadership, Impact, and Management in Business (CLIMB)
• Entrepreneurship & Innovation
• Digital Transformation
• Finance & Accounting
• Business in Society
• For Organizations
• Support Portal
• Media Coverage
• Founding Donors
• Leadership Team

• Harvard Business School →
• HBS Online →
• Business Insights →

Business Insights

Harvard Business School Online's Business Insights Blog provides the career insights you need to achieve your goals and gain confidence in your business skills.

• Career Development
• Communication
• Decision-Making
• Earning Your MBA
• Negotiation
• News & Events
• Productivity
• Staff Spotlight
• Student Profiles
• Work-Life Balance
• AI Essentials for Business
• Alternative Investments
• Business Analytics
• Business Strategy
• Business and Climate Change
• Design Thinking and Innovation
• Digital Marketing Strategy
• Disruptive Strategy
• Economics for Managers
• Entrepreneurship Essentials
• Financial Accounting
• Global Business
• Launching Tech Ventures
• Leadership Principles
• Leadership, Ethics, and Corporate Accountability
• Leading with Finance
• Management Essentials
• Negotiation Mastery
• Organizational Leadership
• Power and Influence for Positive Impact
• Strategy Execution
• Sustainable Business Strategy
• Sustainable Investing
• Winning with Digital Platforms

5 Benefits of Learning Through the Case Study Method

• 28 Nov 2023

While several factors make HBS Online unique —including a global Community and real-world outcomes —active learning through the case study method rises to the top.

In a 2023 City Square Associates survey, 74 percent of HBS Online learners who also took a course from another provider said HBS Online’s case method and real-world examples were better by comparison.

Here’s a primer on the case method, five benefits you could gain, and how to experience it for yourself.

Access your free e-book today.

What Is the Harvard Business School Case Study Method?

The case study method , or case method , is a learning technique in which you’re presented with a real-world business challenge and asked how you’d solve it. After working through it yourself and with peers, you’re told how the scenario played out.

HBS pioneered the case method in 1922. Shortly before, in 1921, the first case was written.

“How do you go into an ambiguous situation and get to the bottom of it?” says HBS Professor Jan Rivkin, former senior associate dean and chair of HBS's master of business administration (MBA) program, in a video about the case method . “That skill—the skill of figuring out a course of inquiry to choose a course of action—that skill is as relevant today as it was in 1921.”

Originally developed for the in-person MBA classroom, HBS Online adapted the case method into an engaging, interactive online learning experience in 2014.

In HBS Online courses , you learn about each case from the business professional who experienced it. After reviewing their videos, you’re prompted to take their perspective and explain how you’d handle their situation.

You then get to read peers’ responses, “star” them, and comment to further the discussion. Afterward, you learn how the professional handled it and their key takeaways.

HBS Online’s adaptation of the case method incorporates the famed HBS “cold call,” in which you’re called on at random to make a decision without time to prepare.

“Learning came to life!” said Sheneka Balogun , chief administration officer and chief of staff at LeMoyne-Owen College, of her experience taking the Credential of Readiness (CORe) program . “The videos from the professors, the interactive cold calls where you were randomly selected to participate, and the case studies that enhanced and often captured the essence of objectives and learning goals were all embedded in each module. This made learning fun, engaging, and student-friendly.”

If you’re considering taking a course that leverages the case study method, here are five benefits you could experience.

5 Benefits of Learning Through Case Studies

1. take new perspectives.

The case method prompts you to consider a scenario from another person’s perspective. To work through the situation and come up with a solution, you must consider their circumstances, limitations, risk tolerance, stakeholders, resources, and potential consequences to assess how to respond.

Taking on new perspectives not only can help you navigate your own challenges but also others’. Putting yourself in someone else’s situation to understand their motivations and needs can go a long way when collaborating with stakeholders.

2. Hone Your Decision-Making Skills

Another skill you can build is the ability to make decisions effectively . The case study method forces you to use limited information to decide how to handle a problem—just like in the real world.

Throughout your career, you’ll need to make difficult decisions with incomplete or imperfect information—and sometimes, you won’t feel qualified to do so. Learning through the case method allows you to practice this skill in a low-stakes environment. When facing a real challenge, you’ll be better prepared to think quickly, collaborate with others, and present and defend your solution.

3. Become More Open-Minded

As you collaborate with peers on responses, it becomes clear that not everyone solves problems the same way. Exposing yourself to various approaches and perspectives can help you become a more open-minded professional.

When you’re part of a diverse group of learners from around the world, your experiences, cultures, and backgrounds contribute to a range of opinions on each case.

On the HBS Online course platform, you’re prompted to view and comment on others’ responses, and discussion is encouraged. This practice of considering others’ perspectives can make you more receptive in your career.

“You’d be surprised at how much you can learn from your peers,” said Ratnaditya Jonnalagadda , a software engineer who took CORe.

In addition to interacting with peers in the course platform, Jonnalagadda was part of the HBS Online Community , where he networked with other professionals and continued discussions sparked by course content.

“You get to understand your peers better, and students share examples of businesses implementing a concept from a module you just learned,” Jonnalagadda said. “It’s a very good way to cement the concepts in one's mind.”

4. Enhance Your Curiosity

One byproduct of taking on different perspectives is that it enables you to picture yourself in various roles, industries, and business functions.

“Each case offers an opportunity for students to see what resonates with them, what excites them, what bores them, which role they could imagine inhabiting in their careers,” says former HBS Dean Nitin Nohria in the Harvard Business Review . “Cases stimulate curiosity about the range of opportunities in the world and the many ways that students can make a difference as leaders.”

Through the case method, you can “try on” roles you may not have considered and feel more prepared to change or advance your career .

5. Build Your Self-Confidence

Finally, learning through the case study method can build your confidence. Each time you assume a business leader’s perspective, aim to solve a new challenge, and express and defend your opinions and decisions to peers, you prepare to do the same in your career.

According to a 2022 City Square Associates survey , 84 percent of HBS Online learners report feeling more confident making business decisions after taking a course.

“Self-confidence is difficult to teach or coach, but the case study method seems to instill it in people,” Nohria says in the Harvard Business Review . “There may well be other ways of learning these meta-skills, such as the repeated experience gained through practice or guidance from a gifted coach. However, under the direction of a masterful teacher, the case method can engage students and help them develop powerful meta-skills like no other form of teaching.”

How to Experience the Case Study Method

If the case method seems like a good fit for your learning style, experience it for yourself by taking an HBS Online course. Offerings span seven subject areas, including:

• Business essentials
• Leadership and management
• Entrepreneurship and innovation
• Finance and accounting
• Business in society

No matter which course or credential program you choose, you’ll examine case studies from real business professionals, work through their challenges alongside peers, and gain valuable insights to apply to your career.

Are you interested in discovering how HBS Online can help advance your career? Explore our course catalog and download our free guide —complete with interactive workbook sections—to determine if online learning is right for you and which course to take.

About the Author

• Bipolar Disorder
• Therapy Center
• When To See a Therapist
• Types of Therapy
• Best Online Therapy
• Best Couples Therapy
• Best Family Therapy
• Managing Stress
• Sleep and Dreaming
• Understanding Emotions
• Self-Improvement
• Healthy Relationships
• Student Resources
• Personality Types
• Guided Meditations
• Verywell Mind Insights
• 2023 Verywell Mind 25
• Mental Health in the Classroom
• Editorial Process
• Meet Our Review Board
• Crisis Support

What Is a Case Study?

Weighing the pros and cons of this method of research

Kendra Cherry, MS, is a psychosocial rehabilitation specialist, psychology educator, and author of the "Everything Psychology Book."

Cara Lustik is a fact-checker and copywriter.

Verywell / Colleen Tighe

• Pros and Cons

What Types of Case Studies Are Out There?

Where do you find data for a case study, how do i write a psychology case study.

A case study is an in-depth study of one person, group, or event. In a case study, nearly every aspect of the subject's life and history is analyzed to seek patterns and causes of behavior. Case studies can be used in many different fields, including psychology, medicine, education, anthropology, political science, and social work.

The point of a case study is to learn as much as possible about an individual or group so that the information can be generalized to many others. Unfortunately, case studies tend to be highly subjective, and it is sometimes difficult to generalize results to a larger population.

While case studies focus on a single individual or group, they follow a format similar to other types of psychology writing. If you are writing a case study, we got you—here are some rules of APA format to reference.  

At a Glance

A case study, or an in-depth study of a person, group, or event, can be a useful research tool when used wisely. In many cases, case studies are best used in situations where it would be difficult or impossible for you to conduct an experiment. They are helpful for looking at unique situations and allow researchers to gather a lot of˜ information about a specific individual or group of people. However, it's important to be cautious of any bias we draw from them as they are highly subjective.

What Are the Benefits and Limitations of Case Studies?

A case study can have its strengths and weaknesses. Researchers must consider these pros and cons before deciding if this type of study is appropriate for their needs.

One of the greatest advantages of a case study is that it allows researchers to investigate things that are often difficult or impossible to replicate in a lab. Some other benefits of a case study:

• Allows researchers to capture information on the 'how,' 'what,' and 'why,' of something that's implemented
• Gives researchers the chance to collect information on why one strategy might be chosen over another
• Permits researchers to develop hypotheses that can be explored in experimental research

On the other hand, a case study can have some drawbacks:

• It cannot necessarily be generalized to the larger population
• Cannot demonstrate cause and effect
• It may not be scientifically rigorous
• It can lead to bias

Researchers may choose to perform a case study if they want to explore a unique or recently discovered phenomenon. Through their insights, researchers develop additional ideas and study questions that might be explored in future studies.

It's important to remember that the insights from case studies cannot be used to determine cause-and-effect relationships between variables. However, case studies may be used to develop hypotheses that can then be addressed in experimental research.

Case Study Examples

There have been a number of notable case studies in the history of psychology. Much of  Freud's work and theories were developed through individual case studies. Some great examples of case studies in psychology include:

• Anna O : Anna O. was a pseudonym of a woman named Bertha Pappenheim, a patient of a physician named Josef Breuer. While she was never a patient of Freud's, Freud and Breuer discussed her case extensively. The woman was experiencing symptoms of a condition that was then known as hysteria and found that talking about her problems helped relieve her symptoms. Her case played an important part in the development of talk therapy as an approach to mental health treatment.
• Phineas Gage : Phineas Gage was a railroad employee who experienced a terrible accident in which an explosion sent a metal rod through his skull, damaging important portions of his brain. Gage recovered from his accident but was left with serious changes in both personality and behavior.
• Genie : Genie was a young girl subjected to horrific abuse and isolation. The case study of Genie allowed researchers to study whether language learning was possible, even after missing critical periods for language development. Her case also served as an example of how scientific research may interfere with treatment and lead to further abuse of vulnerable individuals.

Such cases demonstrate how case research can be used to study things that researchers could not replicate in experimental settings. In Genie's case, her horrific abuse denied her the opportunity to learn a language at critical points in her development.

This is clearly not something researchers could ethically replicate, but conducting a case study on Genie allowed researchers to study phenomena that are otherwise impossible to reproduce.

There are a few different types of case studies that psychologists and other researchers might use:

• Collective case studies : These involve studying a group of individuals. Researchers might study a group of people in a certain setting or look at an entire community. For example, psychologists might explore how access to resources in a community has affected the collective mental well-being of those who live there.
• Descriptive case studies : These involve starting with a descriptive theory. The subjects are then observed, and the information gathered is compared to the pre-existing theory.
• Explanatory case studies : These   are often used to do causal investigations. In other words, researchers are interested in looking at factors that may have caused certain things to occur.
• Exploratory case studies : These are sometimes used as a prelude to further, more in-depth research. This allows researchers to gather more information before developing their research questions and hypotheses .
• Instrumental case studies : These occur when the individual or group allows researchers to understand more than what is initially obvious to observers.
• Intrinsic case studies : This type of case study is when the researcher has a personal interest in the case. Jean Piaget's observations of his own children are good examples of how an intrinsic case study can contribute to the development of a psychological theory.

The three main case study types often used are intrinsic, instrumental, and collective. Intrinsic case studies are useful for learning about unique cases. Instrumental case studies help look at an individual to learn more about a broader issue. A collective case study can be useful for looking at several cases simultaneously.

The type of case study that psychology researchers use depends on the unique characteristics of the situation and the case itself.

There are a number of different sources and methods that researchers can use to gather information about an individual or group. Six major sources that have been identified by researchers are:

• Archival records : Census records, survey records, and name lists are examples of archival records.
• Direct observation : This strategy involves observing the subject, often in a natural setting . While an individual observer is sometimes used, it is more common to utilize a group of observers.
• Documents : Letters, newspaper articles, administrative records, etc., are the types of documents often used as sources.
• Interviews : Interviews are one of the most important methods for gathering information in case studies. An interview can involve structured survey questions or more open-ended questions.
• Participant observation : When the researcher serves as a participant in events and observes the actions and outcomes, it is called participant observation.
• Physical artifacts : Tools, objects, instruments, and other artifacts are often observed during a direct observation of the subject.

If you have been directed to write a case study for a psychology course, be sure to check with your instructor for any specific guidelines you need to follow. If you are writing your case study for a professional publication, check with the publisher for their specific guidelines for submitting a case study.

Here is a general outline of what should be included in a case study.

Section 1: A Case History

This section will have the following structure and content:

Background information : The first section of your paper will present your client's background. Include factors such as age, gender, work, health status, family mental health history, family and social relationships, drug and alcohol history, life difficulties, goals, and coping skills and weaknesses.

Description of the presenting problem : In the next section of your case study, you will describe the problem or symptoms that the client presented with.

Describe any physical, emotional, or sensory symptoms reported by the client. Thoughts, feelings, and perceptions related to the symptoms should also be noted. Any screening or diagnostic assessments that are used should also be described in detail and all scores reported.

Your diagnosis : Provide your diagnosis and give the appropriate Diagnostic and Statistical Manual code. Explain how you reached your diagnosis, how the client's symptoms fit the diagnostic criteria for the disorder(s), or any possible difficulties in reaching a diagnosis.

Section 2: Treatment Plan

This portion of the paper will address the chosen treatment for the condition. This might also include the theoretical basis for the chosen treatment or any other evidence that might exist to support why this approach was chosen.

• Cognitive behavioral approach : Explain how a cognitive behavioral therapist would approach treatment. Offer background information on cognitive behavioral therapy and describe the treatment sessions, client response, and outcome of this type of treatment. Make note of any difficulties or successes encountered by your client during treatment.
• Humanistic approach : Describe a humanistic approach that could be used to treat your client, such as client-centered therapy . Provide information on the type of treatment you chose, the client's reaction to the treatment, and the end result of this approach. Explain why the treatment was successful or unsuccessful.
• Psychoanalytic approach : Describe how a psychoanalytic therapist would view the client's problem. Provide some background on the psychoanalytic approach and cite relevant references. Explain how psychoanalytic therapy would be used to treat the client, how the client would respond to therapy, and the effectiveness of this treatment approach.
• Pharmacological approach : If treatment primarily involves the use of medications, explain which medications were used and why. Provide background on the effectiveness of these medications and how monotherapy may compare with an approach that combines medications with therapy or other treatments.

This section of a case study should also include information about the treatment goals, process, and outcomes.

When you are writing a case study, you should also include a section where you discuss the case study itself, including the strengths and limitiations of the study. You should note how the findings of your case study might support previous research. 

In your discussion section, you should also describe some of the implications of your case study. What ideas or findings might require further exploration? How might researchers go about exploring some of these questions in additional studies?

Need More Tips?

Here are a few additional pointers to keep in mind when formatting your case study:

• Never refer to the subject of your case study as "the client." Instead, use their name or a pseudonym.
• Read examples of case studies to gain an idea about the style and format.
• Remember to use APA format when citing references .

Crowe S, Cresswell K, Robertson A, Huby G, Avery A, Sheikh A. The case study approach .  BMC Med Res Methodol . 2011;11:100.

Crowe S, Cresswell K, Robertson A, Huby G, Avery A, Sheikh A. The case study approach . BMC Med Res Methodol . 2011 Jun 27;11:100. doi:10.1186/1471-2288-11-100

Gagnon, Yves-Chantal.  The Case Study as Research Method: A Practical Handbook . Canada, Chicago Review Press Incorporated DBA Independent Pub Group, 2010.

Yin, Robert K. Case Study Research and Applications: Design and Methods . United States, SAGE Publications, 2017.

By Kendra Cherry, MSEd Kendra Cherry, MS, is a psychosocial rehabilitation specialist, psychology educator, and author of the "Everything Psychology Book."

• Harvard Business School →
• Academic Experience
• Faculty & Research
• The Field Method
• A Global Experience

The HBS Case Method

• Joint Degree Programs
• The Section Experience
• The HBS Case Method →

Take a Seat in the MBA Classroom

• Harvard Business School

How the HBS Case Method Works

How the Case Method Works

• Read and analyze the case. Each case is a 10-20 page document written from the viewpoint of a real person leading a real organization. In addition to background information on the situation, each case ends in a key decision to be made. Your job is to sift through the information, incomplete by design, and decide what you would do.
• Discuss the case. Each morning, you’ll bring your ideas to a small team of classmates from diverse professional backgrounds, your discussion group, to share your findings and listen to theirs. Together, you begin to see the case from different perspectives, better preparing you for class.
• Engage in class. Be prepared to change the way you think as you debate with classmates the best path forward for this organization. The highly engaged conversation is facilitated by the faculty member, but it’s driven by your classmates’ comments and experiences. HBS brings together amazingly talented people from diverse backgrounds and puts that experience front and center. Students do the majority of the talking (and lots of active listening), and your job is to better understand the decision at hand, what you would do in the case protagonist’s shoes, and why. You will not leave a class thinking about the case the same way you thought about it coming in! In addition to learning more about many businesses, in the case method you will develop communication, listening, analysis, and leadership skills. It is a truly dynamic and immersive learning environment.
• Reflect. The case method prepares you to be in leadership positions where you will face time-sensitive decisions with limited information. Reflecting on each class discussion will prepare you to face these situations in your future roles.

Student Perspectives

“I’ve been so touched by how dedicated other people have been to my learning and my success.”

Faculty Perspectives

“The world desperately needs better leadership. It’s actually one of the great gifts of teaching here, you can do something about it.”

Alumni Perspectives

“You walk into work every morning and it's like a fire hose of decisions that need to be made, often without enough information. Just like an HBS case.”

Celebrating the Inaugural HBS Case

“How do you go into an ambiguous situation and get to the bottom of it? That skill – the skill of figuring out a course of inquiry, to choose a course of action – that skill is as relevant today as it was in 1921.”

Case Study Research Method in Psychology

Saul Mcleod, PhD

Editor-in-Chief for Simply Psychology

BSc (Hons) Psychology, MRes, PhD, University of Manchester

Saul Mcleod, PhD., is a qualified psychology teacher with over 18 years of experience in further and higher education. He has been published in peer-reviewed journals, including the Journal of Clinical Psychology.

Learn about our Editorial Process

Olivia Guy-Evans, MSc

Associate Editor for Simply Psychology

BSc (Hons) Psychology, MSc Psychology of Education

Olivia Guy-Evans is a writer and associate editor for Simply Psychology. She has previously worked in healthcare and educational sectors.

On This Page:

Case studies are in-depth investigations of a person, group, event, or community. Typically, data is gathered from various sources using several methods (e.g., observations & interviews).

The case study research method originated in clinical medicine (the case history, i.e., the patient’s personal history). In psychology, case studies are often confined to the study of a particular individual.

The information is mainly biographical and relates to events in the individual’s past (i.e., retrospective), as well as to significant events that are currently occurring in his or her everyday life.

The case study is not a research method, but researchers select methods of data collection and analysis that will generate material suitable for case studies.

Freud (1909a, 1909b) conducted very detailed investigations into the private lives of his patients in an attempt to both understand and help them overcome their illnesses.

This makes it clear that the case study is a method that should only be used by a psychologist, therapist, or psychiatrist, i.e., someone with a professional qualification.

There is an ethical issue of competence. Only someone qualified to diagnose and treat a person can conduct a formal case study relating to atypical (i.e., abnormal) behavior or atypical development.

 Famous Case Studies

• Anna O – One of the most famous case studies, documenting psychoanalyst Josef Breuer’s treatment of “Anna O” (real name Bertha Pappenheim) for hysteria in the late 1800s using early psychoanalytic theory.
• Little Hans – A child psychoanalysis case study published by Sigmund Freud in 1909 analyzing his five-year-old patient Herbert Graf’s house phobia as related to the Oedipus complex.
• Bruce/Brenda – Gender identity case of the boy (Bruce) whose botched circumcision led psychologist John Money to advise gender reassignment and raise him as a girl (Brenda) in the 1960s.
• Genie Wiley – Linguistics/psychological development case of the victim of extreme isolation abuse who was studied in 1970s California for effects of early language deprivation on acquiring speech later in life.
• Phineas Gage – One of the most famous neuropsychology case studies analyzes personality changes in railroad worker Phineas Gage after an 1848 brain injury involving a tamping iron piercing his skull.

Clinical Case Studies

• Studying the effectiveness of psychotherapy approaches with an individual patient
• Assessing and treating mental illnesses like depression, anxiety disorders, PTSD
• Neuropsychological cases investigating brain injuries or disorders

Child Psychology Case Studies

• Studying psychological development from birth through adolescence
• Cases of learning disabilities, autism spectrum disorders, ADHD
• Effects of trauma, abuse, deprivation on development

Types of Case Studies

• Explanatory case studies : Used to explore causation in order to find underlying principles. Helpful for doing qualitative analysis to explain presumed causal links.
• Exploratory case studies : Used to explore situations where an intervention being evaluated has no clear set of outcomes. It helps define questions and hypotheses for future research.
• Descriptive case studies : Describe an intervention or phenomenon and the real-life context in which it occurred. It is helpful for illustrating certain topics within an evaluation.
• Multiple-case studies : Used to explore differences between cases and replicate findings across cases. Helpful for comparing and contrasting specific cases.
• Intrinsic : Used to gain a better understanding of a particular case. Helpful for capturing the complexity of a single case.
• Collective : Used to explore a general phenomenon using multiple case studies. Helpful for jointly studying a group of cases in order to inquire into the phenomenon.

Where Do You Find Data for a Case Study?

There are several places to find data for a case study. The key is to gather data from multiple sources to get a complete picture of the case and corroborate facts or findings through triangulation of evidence. Most of this information is likely qualitative (i.e., verbal description rather than measurement), but the psychologist might also collect numerical data.

1. Primary sources

• Interviews – Interviewing key people related to the case to get their perspectives and insights. The interview is an extremely effective procedure for obtaining information about an individual, and it may be used to collect comments from the person’s friends, parents, employer, workmates, and others who have a good knowledge of the person, as well as to obtain facts from the person him or herself.
• Observations – Observing behaviors, interactions, processes, etc., related to the case as they unfold in real-time.
• Documents & Records – Reviewing private documents, diaries, public records, correspondence, meeting minutes, etc., relevant to the case.

2. Secondary sources

• News/Media – News coverage of events related to the case study.
• Academic articles – Journal articles, dissertations etc. that discuss the case.
• Government reports – Official data and records related to the case context.
• Books/films – Books, documentaries or films discussing the case.

3. Archival records

Searching historical archives, museum collections and databases to find relevant documents, visual/audio records related to the case history and context.

Public archives like newspapers, organizational records, photographic collections could all include potentially relevant pieces of information to shed light on attitudes, cultural perspectives, common practices and historical contexts related to psychology.

4. Organizational records

Organizational records offer the advantage of often having large datasets collected over time that can reveal or confirm psychological insights.

Of course, privacy and ethical concerns regarding confidential data must be navigated carefully.

However, with proper protocols, organizational records can provide invaluable context and empirical depth to qualitative case studies exploring the intersection of psychology and organizations.

• Organizational/industrial psychology research : Organizational records like employee surveys, turnover/retention data, policies, incident reports etc. may provide insight into topics like job satisfaction, workplace culture and dynamics, leadership issues, employee behaviors etc.
• Clinical psychology : Therapists/hospitals may grant access to anonymized medical records to study aspects like assessments, diagnoses, treatment plans etc. This could shed light on clinical practices.
• School psychology : Studies could utilize anonymized student records like test scores, grades, disciplinary issues, and counseling referrals to study child development, learning barriers, effectiveness of support programs, and more.

How do I Write a Case Study in Psychology?

Follow specified case study guidelines provided by a journal or your psychology tutor. General components of clinical case studies include: background, symptoms, assessments, diagnosis, treatment, and outcomes. Interpreting the information means the researcher decides what to include or leave out. A good case study should always clarify which information is the factual description and which is an inference or the researcher’s opinion.

1. Introduction

• Provide background on the case context and why it is of interest, presenting background information like demographics, relevant history, and presenting problem.
• Compare briefly to similar published cases if applicable. Clearly state the focus/importance of the case.

2. Case Presentation

• Describe the presenting problem in detail, including symptoms, duration,and impact on daily life.
• Include client demographics like age and gender, information about social relationships, and mental health history.
• Describe all physical, emotional, and/or sensory symptoms reported by the client.
• Use patient quotes to describe the initial complaint verbatim. Follow with full-sentence summaries of relevant history details gathered, including key components that led to a working diagnosis.
• Summarize clinical exam results, namely orthopedic/neurological tests, imaging, lab tests, etc. Note actual results rather than subjective conclusions. Provide images if clearly reproducible/anonymized.
• Clearly state the working diagnosis or clinical impression before transitioning to management.

3. Management and Outcome

• Indicate the total duration of care and number of treatments given over what timeframe. Use specific names/descriptions for any therapies/interventions applied.
• Present the results of the intervention,including any quantitative or qualitative data collected.
• For outcomes, utilize visual analog scales for pain, medication usage logs, etc., if possible. Include patient self-reports of improvement/worsening of symptoms. Note the reason for discharge/end of care.

4. Discussion

• Analyze the case, exploring contributing factors, limitations of the study, and connections to existing research.
• Analyze the effectiveness of the intervention,considering factors like participant adherence, limitations of the study, and potential alternative explanations for the results.
• Identify any questions raised in the case analysis and relate insights to established theories and current research if applicable. Avoid definitive claims about physiological explanations.
• Offer clinical implications, and suggest future research directions.

5. Additional Items

• Thank specific assistants for writing support only. No patient acknowledgments.
• References should directly support any key claims or quotes included.
• Use tables/figures/images only if substantially informative. Include permissions and legends/explanatory notes.
• Provides detailed (rich qualitative) information.
• Provides insight for further research.
• Permitting investigation of otherwise impractical (or unethical) situations.

Case studies allow a researcher to investigate a topic in far more detail than might be possible if they were trying to deal with a large number of research participants (nomothetic approach) with the aim of ‘averaging’.

Because of their in-depth, multi-sided approach, case studies often shed light on aspects of human thinking and behavior that would be unethical or impractical to study in other ways.

Research that only looks into the measurable aspects of human behavior is not likely to give us insights into the subjective dimension of experience, which is important to psychoanalytic and humanistic psychologists.

Case studies are often used in exploratory research. They can help us generate new ideas (that might be tested by other methods). They are an important way of illustrating theories and can help show how different aspects of a person’s life are related to each other.

The method is, therefore, important for psychologists who adopt a holistic point of view (i.e., humanistic psychologists ).

Limitations

• Lacking scientific rigor and providing little basis for generalization of results to the wider population.
• Researchers’ own subjective feelings may influence the case study (researcher bias).
• Difficult to replicate.
• Time-consuming and expensive.
• The volume of data, together with the time restrictions in place, impacted the depth of analysis that was possible within the available resources.

Because a case study deals with only one person/event/group, we can never be sure if the case study investigated is representative of the wider body of “similar” instances. This means the conclusions drawn from a particular case may not be transferable to other settings.

Because case studies are based on the analysis of qualitative (i.e., descriptive) data , a lot depends on the psychologist’s interpretation of the information she has acquired.

This means that there is a lot of scope for Anna O , and it could be that the subjective opinions of the psychologist intrude in the assessment of what the data means.

For example, Freud has been criticized for producing case studies in which the information was sometimes distorted to fit particular behavioral theories (e.g., Little Hans ).

This is also true of Money’s interpretation of the Bruce/Brenda case study (Diamond, 1997) when he ignored evidence that went against his theory.

Breuer, J., & Freud, S. (1895).  Studies on hysteria . Standard Edition 2: London.

Curtiss, S. (1981). Genie: The case of a modern wild child .

Diamond, M., & Sigmundson, K. (1997). Sex Reassignment at Birth: Long-term Review and Clinical Implications. Archives of Pediatrics & Adolescent Medicine , 151(3), 298-304

Freud, S. (1909a). Analysis of a phobia of a five year old boy. In The Pelican Freud Library (1977), Vol 8, Case Histories 1, pages 169-306

Freud, S. (1909b). Bemerkungen über einen Fall von Zwangsneurose (Der “Rattenmann”). Jb. psychoanal. psychopathol. Forsch ., I, p. 357-421; GW, VII, p. 379-463; Notes upon a case of obsessional neurosis, SE , 10: 151-318.

Harlow J. M. (1848). Passage of an iron rod through the head.  Boston Medical and Surgical Journal, 39 , 389–393.

Harlow, J. M. (1868).  Recovery from the Passage of an Iron Bar through the Head .  Publications of the Massachusetts Medical Society. 2  (3), 327-347.

Money, J., & Ehrhardt, A. A. (1972).  Man & Woman, Boy & Girl : The Differentiation and Dimorphism of Gender Identity from Conception to Maturity. Baltimore, Maryland: Johns Hopkins University Press.

Money, J., & Tucker, P. (1975). Sexual signatures: On being a man or a woman.

Further Information

• Case Study Approach
• Case Study Method
• Enhancing the Quality of Case Studies in Health Services Research
• “We do things together” A case study of “couplehood” in dementia
• Using mixed methods for evaluating an integrative approach to cancer care: a case study

• Columbia University in the City of New York
• Office of Teaching, Learning, and Innovation
• University Policies
• Columbia Online
• Academic Calendar
• Resources and Technology
• Resources and Guides

Case Method Teaching and Learning

What is the case method? How can the case method be used to engage learners? What are some strategies for getting started? This guide helps instructors answer these questions by providing an overview of the case method while highlighting learner-centered and digitally-enhanced approaches to teaching with the case method. The guide also offers tips to instructors as they get started with the case method and additional references and resources.

On this page:

What is case method teaching.

• Case Method at Columbia

Why use the Case Method?

Case method teaching approaches, how do i get started.

• Additional Resources

The CTL is here to help!

For support with implementing a case method approach in your course, email [email protected] to schedule your 1-1 consultation .

Cite this resource: Columbia Center for Teaching and Learning (2019). Case Method Teaching and Learning. Columbia University. Retrieved from [today’s date] from https://ctl.columbia.edu/resources-and-technology/resources/case-method/  

Case method 1 teaching is an active form of instruction that focuses on a case and involves students learning by doing 2 3 . Cases are real or invented stories 4  that include “an educational message” or recount events, problems, dilemmas, theoretical or conceptual issue that requires analysis and/or decision-making.

Case-based teaching simulates real world situations and asks students to actively grapple with complex problems 5 6 This method of instruction is used across disciplines to promote learning, and is common in law, business, medicine, among other fields. See Table 1 below for a few types of cases and the learning they promote.

Table 1: Types of cases and the learning they promote.

For a more complete list, see Case Types & Teaching Methods: A Classification Scheme from the National Center for Case Study Teaching in Science.

Back to Top

Case Method Teaching and Learning at Columbia

The case method is actively used in classrooms across Columbia, at the Morningside campus in the School of International and Public Affairs (SIPA), the School of Business, Arts and Sciences, among others, and at Columbia University Irving Medical campus.

Faculty Spotlight:

Professor Mary Ann Price on Using Case Study Method to Place Pre-Med Students in Real-Life Scenarios

Read more  

Professor De Pinho on Using the Case Method in the Mailman Core

Case method teaching has been found to improve student learning, to increase students’ perception of learning gains, and to meet learning objectives 8 9 . Faculty have noted the instructional benefits of cases including greater student engagement in their learning 10 , deeper student understanding of concepts, stronger critical thinking skills, and an ability to make connections across content areas and view an issue from multiple perspectives 11 . 

Through case-based learning, students are the ones asking questions about the case, doing the problem-solving, interacting with and learning from their peers, “unpacking” the case, analyzing the case, and summarizing the case. They learn how to work with limited information and ambiguity, think in professional or disciplinary ways, and ask themselves “what would I do if I were in this specific situation?”

The case method bridges theory to practice, and promotes the development of skills including: communication, active listening, critical thinking, decision-making, and metacognitive skills 12 , as students apply course content knowledge, reflect on what they know and their approach to analyzing, and make sense of a case. 

Though the case method has historical roots as an instructor-centered approach that uses the Socratic dialogue and cold-calling, it is possible to take a more learner-centered approach in which students take on roles and tasks traditionally left to the instructor. 

Cases are often used as “vehicles for classroom discussion” 13 . Students should be encouraged to take ownership of their learning from a case. Discussion-based approaches engage students in thinking and communicating about a case. Instructors can set up a case activity in which students are the ones doing the work of “asking questions, summarizing content, generating hypotheses, proposing theories, or offering critical analyses” 14 . 

The role of the instructor is to share a case or ask students to share or create a case to use in class, set expectations, provide instructions, and assign students roles in the discussion. Student roles in a case discussion can include: 

• discussion “starters” get the conversation started with a question or posing the questions that their peers came up with; 
• facilitators listen actively, validate the contributions of peers, ask follow-up questions, draw connections, refocus the conversation as needed; 
• recorders take-notes of the main points of the discussion, record on the board, upload to CourseWorks, or type and project on the screen; and 
• discussion “wrappers” lead a summary of the main points of the discussion. 

Prior to the case discussion, instructors can model case analysis and the types of questions students should ask, co-create discussion guidelines with students, and ask for students to submit discussion questions. During the discussion, the instructor can keep time, intervene as necessary (however the students should be doing the talking), and pause the discussion for a debrief and to ask students to reflect on what and how they learned from the case activity. 

Note: case discussions can be enhanced using technology. Live discussions can occur via video-conferencing (e.g., using Zoom ) or asynchronous discussions can occur using the Discussions tool in CourseWorks (Canvas) .

Table 2 includes a few interactive case method approaches. Regardless of the approach selected, it is important to create a learning environment in which students feel comfortable participating in a case activity and learning from one another. See below for tips on supporting student in how to learn from a case in the “getting started” section and how to create a supportive learning environment in the Guide for Inclusive Teaching at Columbia . 

Table 2. Strategies for Engaging Students in Case-Based Learning

Approaches to case teaching should be informed by course learning objectives, and can be adapted for small, large, hybrid, and online classes. Instructional technology can be used in various ways to deliver, facilitate, and assess the case method. For instance, an online module can be created in CourseWorks (Canvas) to structure the delivery of the case, allow students to work at their own pace, engage all learners, even those reluctant to speak up in class, and assess understanding of a case and student learning. Modules can include text, embedded media (e.g., using Panopto or Mediathread ) curated by the instructor, online discussion, and assessments. Students can be asked to read a case and/or watch a short video, respond to quiz questions and receive immediate feedback, post questions to a discussion, and share resources. 

For more information about options for incorporating educational technology to your course, please contact your Learning Designer .

To ensure that students are learning from the case approach, ask them to pause and reflect on what and how they learned from the case. Time to reflect  builds your students’ metacognition, and when these reflections are collected they provides you with insights about the effectiveness of your approach in promoting student learning.

Well designed case-based learning experiences: 1) motivate student involvement, 2) have students doing the work, 3) help students develop knowledge and skills, and 4) have students learning from each other.  

Designing a case-based learning experience should center around the learning objectives for a course. The following points focus on intentional design. 

Identify learning objectives, determine scope, and anticipate challenges. 

• Why use the case method in your course? How will it promote student learning differently than other approaches? 
• What are the learning objectives that need to be met by the case method? What knowledge should students apply and skills should they practice? 
• What is the scope of the case? (a brief activity in a single class session to a semester-long case-based course; if new to case method, start small with a single case). 
• What challenges do you anticipate (e.g., student preparation and prior experiences with case learning, discomfort with discussion, peer-to-peer learning, managing discussion) and how will you plan for these in your design? 
• If you are asking students to use transferable skills for the case method (e.g., teamwork, digital literacy) make them explicit. 

Determine how you will know if the learning objectives were met and develop a plan for evaluating the effectiveness of the case method to inform future case teaching. 

• What assessments and criteria will you use to evaluate student work or participation in case discussion? 
• How will you evaluate the effectiveness of the case method? What feedback will you collect from students? 
• How might you leverage technology for assessment purposes? For example, could you quiz students about the case online before class, accept assignment submissions online, use audience response systems (e.g., PollEverywhere) for formative assessment during class? 

Select an existing case, create your own, or encourage students to bring course-relevant cases, and prepare for its delivery

• Where will the case method fit into the course learning sequence? 
• Is the case at the appropriate level of complexity? Is it inclusive, culturally relevant, and relatable to students? 
• What materials and preparation will be needed to present the case to students? (e.g., readings, audiovisual materials, set up a module in CourseWorks). 

Plan for the case discussion and an active role for students

• What will your role be in facilitating case-based learning? How will you model case analysis for your students? (e.g., present a short case and demo your approach and the process of case learning) (Davis, 2009). 
• What discussion guidelines will you use that include your students’ input? 
• How will you encourage students to ask and answer questions, summarize their work, take notes, and debrief the case? 
• If students will be working in groups, how will groups form? What size will the groups be? What instructions will they be given? How will you ensure that everyone participates? What will they need to submit? Can technology be leveraged for any of these areas? 
• Have you considered students of varied cognitive and physical abilities and how they might participate in the activities/discussions, including those that involve technology? 

Student preparation and expectations

• How will you communicate about the case method approach to your students? When will you articulate the purpose of case-based learning and expectations of student engagement? What information about case-based learning and expectations will be included in the syllabus?
• What preparation and/or assignment(s) will students complete in order to learn from the case? (e.g., read the case prior to class, watch a case video prior to class, post to a CourseWorks discussion, submit a brief memo, complete a short writing assignment to check students’ understanding of a case, take on a specific role, prepare to present a critique during in-class discussion).

Andersen, E. and Schiano, B. (2014). Teaching with Cases: A Practical Guide . Harvard Business Press. 

Bonney, K. M. (2015). Case Study Teaching Method Improves Student Performance and Perceptions of Learning Gains†. Journal of Microbiology & Biology Education , 16 (1), 21–28. https://doi.org/10.1128/jmbe.v16i1.846

Davis, B.G. (2009). Chapter 24: Case Studies. In Tools for Teaching. Second Edition. Jossey-Bass. 

Garvin, D.A. (2003). Making the Case: Professional Education for the world of practice. Harvard Magazine. September-October 2003, Volume 106, Number 1, 56-107.

Golich, V.L. (2000). The ABCs of Case Teaching. International Studies Perspectives. 1, 11-29. 

Golich, V.L.; Boyer, M; Franko, P.; and Lamy, S. (2000). The ABCs of Case Teaching. Pew Case Studies in International Affairs. Institute for the Study of Diplomacy. 

Heath, J. (2015). Teaching & Writing Cases: A Practical Guide. The Case Center, UK. 

Herreid, C.F. (2011). Case Study Teaching. New Directions for Teaching and Learning. No. 128, Winder 2011, 31 – 40. 

Herreid, C.F. (2007). Start with a Story: The Case Study Method of Teaching College Science . National Science Teachers Association. Available as an ebook through Columbia Libraries. 

Herreid, C.F. (2006). “Clicker” Cases: Introducing Case Study Teaching Into Large Classrooms. Journal of College Science Teaching. Oct 2006, 36(2). https://search.proquest.com/docview/200323718?pq-origsite=gscholar  

Krain, M. (2016). Putting the Learning in Case Learning? The Effects of Case-Based Approaches on Student Knowledge, Attitudes, and Engagement. Journal on Excellence in College Teaching. 27(2), 131-153. 

Lundberg, K.O. (Ed.). (2011). Our Digital Future: Boardrooms and Newsrooms. Knight Case Studies Initiative. 

Popil, I. (2011). Promotion of critical thinking by using case studies as teaching method. Nurse Education Today, 31(2), 204–207. https://doi.org/10.1016/j.nedt.2010.06.002

Schiano, B. and Andersen, E. (2017). Teaching with Cases Online . Harvard Business Publishing. 

Thistlethwaite, JE; Davies, D.; Ekeocha, S.; Kidd, J.M.; MacDougall, C.; Matthews, P.; Purkis, J.; Clay D. (2012). The effectiveness of case-based learning in health professional education: A BEME systematic review . Medical Teacher. 2012; 34(6): e421-44. 

Yadav, A.; Lundeberg, M.; DeSchryver, M.; Dirkin, K.; Schiller, N.A.; Maier, K. and Herreid, C.F. (2007). Teaching Science with Case Studies: A National Survey of Faculty Perceptions of the Benefits and Challenges of Using Cases. Journal of College Science Teaching; Sept/Oct 2007; 37(1). 

Weimer, M. (2013). Learner-Centered Teaching: Five Key Changes to Practice. Second Edition. Jossey-Bass.

Additional resources 

Teaching with Cases , Harvard Kennedy School of Government. 

Features “what is a teaching case?” video that defines a teaching case, and provides documents to help students prepare for case learning, Common case teaching challenges and solutions, tips for teaching with cases. 

Promoting excellence and innovation in case method teaching: Teaching by the Case Method , Christensen Center for Teaching & Learning. Harvard Business School. 

National Center for Case Study Teaching in Science . University of Buffalo. 

A collection of peer-reviewed STEM cases to teach scientific concepts and content, promote process skills and critical thinking. The Center welcomes case submissions. Case classification scheme of case types and teaching methods:

• Different types of cases: analysis case, dilemma/decision case, directed case, interrupted case, clicker case, a flipped case, a laboratory case. 
• Different types of teaching methods: problem-based learning, discussion, debate, intimate debate, public hearing, trial, jigsaw, role-play. 

Columbia Resources

Resources available to support your use of case method: The University hosts a number of case collections including: the Case Consortium (a collection of free cases in the fields of journalism, public policy, public health, and other disciplines that include teaching and learning resources; SIPA’s Picker Case Collection (audiovisual case studies on public sector innovation, filmed around the world and involving SIPA student teams in producing the cases); and Columbia Business School CaseWorks , which develops teaching cases and materials for use in Columbia Business School classrooms.

Center for Teaching and Learning

The Center for Teaching and Learning (CTL) offers a variety of programs and services for instructors at Columbia. The CTL can provide customized support as you plan to use the case method approach through implementation. Schedule a one-on-one consultation. 

Office of the Provost

The Hybrid Learning Course Redesign grant program from the Office of the Provost provides support for faculty who are developing innovative and technology-enhanced pedagogy and learning strategies in the classroom. In addition to funding, faculty awardees receive support from CTL staff as they redesign, deliver, and evaluate their hybrid courses.

The Start Small! Mini-Grant provides support to faculty who are interested in experimenting with one new pedagogical strategy or tool. Faculty awardees receive funds and CTL support for a one-semester period.

Explore our teaching resources.

• Blended Learning
• Contemplative Pedagogy
• Inclusive Teaching Guide
• FAQ for Teaching Assistants
• Metacognition

CTL resources and technology for you.

• Overview of all CTL Resources and Technology
• The origins of this method can be traced to Harvard University where in 1870 the Law School began using cases to teach students how to think like lawyers using real court decisions. This was followed by the Business School in 1920 (Garvin, 2003). These professional schools recognized that lecture mode of instruction was insufficient to teach critical professional skills, and that active learning would better prepare learners for their professional lives. ↩
• Golich, V.L. (2000). The ABCs of Case Teaching. International Studies Perspectives. 1, 11-29. ↩
• Herreid, C.F. (2007). Start with a Story: The Case Study Method of Teaching College Science . National Science Teachers Association. Available as an ebook through Columbia Libraries. ↩
• Davis, B.G. (2009). Chapter 24: Case Studies. In Tools for Teaching. Second Edition. Jossey-Bass. ↩
• Andersen, E. and Schiano, B. (2014). Teaching with Cases: A Practical Guide . Harvard Business Press. ↩
• Lundberg, K.O. (Ed.). (2011). Our Digital Future: Boardrooms and Newsrooms. Knight Case Studies Initiative. ↩
• Heath, J. (2015). Teaching & Writing Cases: A Practical Guide. The Case Center, UK. ↩
• Bonney, K. M. (2015). Case Study Teaching Method Improves Student Performance and Perceptions of Learning Gains†. Journal of Microbiology & Biology Education , 16 (1), 21–28. https://doi.org/10.1128/jmbe.v16i1.846 ↩
• Krain, M. (2016). Putting the Learning in Case Learning? The Effects of Case-Based Approaches on Student Knowledge, Attitudes, and Engagement. Journal on Excellence in College Teaching. 27(2), 131-153. ↩
• Thistlethwaite, JE; Davies, D.; Ekeocha, S.; Kidd, J.M.; MacDougall, C.; Matthews, P.; Purkis, J.; Clay D. (2012). The effectiveness of case-based learning in health professional education: A BEME systematic review . Medical Teacher. 2012; 34(6): e421-44. ↩
• Yadav, A.; Lundeberg, M.; DeSchryver, M.; Dirkin, K.; Schiller, N.A.; Maier, K. and Herreid, C.F. (2007). Teaching Science with Case Studies: A National Survey of Faculty Perceptions of the Benefits and Challenges of Using Cases. Journal of College Science Teaching; Sept/Oct 2007; 37(1). ↩
• Popil, I. (2011). Promotion of critical thinking by using case studies as teaching method. Nurse Education Today, 31(2), 204–207. https://doi.org/10.1016/j.nedt.2010.06.002 ↩
• Weimer, M. (2013). Learner-Centered Teaching: Five Key Changes to Practice. Second Edition. Jossey-Bass. ↩
• Herreid, C.F. (2006). “Clicker” Cases: Introducing Case Study Teaching Into Large Classrooms. Journal of College Science Teaching. Oct 2006, 36(2). https://search.proquest.com/docview/200323718?pq-origsite=gscholar ↩

This website uses cookies to identify users, improve the user experience and requires cookies to work. By continuing to use this website, you consent to Columbia University's use of cookies and similar technologies, in accordance with the Columbia University Website Cookie Notice .

• Tools and Resources
• Customer Services
• Contentious Politics and Political Violence
• Governance/Political Change
• Groups and Identities
• History and Politics
• International Political Economy
• Policy, Administration, and Bureaucracy
• Political Anthropology
• Political Behavior
• Political Communication
• Political Economy
• Political Institutions
• Political Philosophy
• Political Psychology
• Political Sociology
• Political Values, Beliefs, and Ideologies
• Politics, Law, Judiciary
• Post Modern/Critical Politics
• Public Opinion
• Qualitative Political Methodology
• Quantitative Political Methodology
• World Politics
• Share This Facebook LinkedIn Twitter

Article contents

Process tracing methods in the social sciences.

• Derek Beach Derek Beach Department of Political Science, Aarhus University
• https://doi.org/10.1093/acrefore/9780190228637.013.176
• Published online: 25 January 2017

Process tracing (PT) is a research method for studying how causal processes work using case study methods. PT can be used for both case studies that aim to gain a greater understanding of the causal dynamics that produced the outcome of a particular historical case and to shed light on generalizable causal mechanisms linking causes and outcomes within a population of cases. PT as a method has three core components: theorization about causal mechanisms linking causes and outcomes, the analysis of the observable empirical manifestations of theorized mechanisms, and questions of case selection and generalization. There are at least three distinct variants of PT that stem from differences in how scholars understand the ontological nature of the theories being traced. This means there is not one “correct” way to use PT.

• process tracing
• case studies
• causal inference
• causal mechanisms
• causal process

Updated in this version

The title, summary, and keywords have all been updated. Additionally, new figures, tables, and text have been added to reflect the latest developments.

Introduction

Process tracing (PT) is a research method for tracing causal processes using case studies. PT can be used to investigate questions such as how low intelligence capacity of security forces can contribute to produce mass violence against civilians ( Winward, 2021 ) and how an epistemic community can gain influence over policy ( Löblová, 2018 ). The analytical added value of PT is that it enables causal inferences to be made about how causal processes/causal mechanisms work using in-depth analysis of one or a small number of cases. 1 Furthermore, when more disaggregated process theories are traced empirically, light is shed on the contextual conditions under which particular processes operate. The trade-off is that not many cases can be traced because it is difficult and time-consuming to study how things work in particular cases using PT.

PT methods can be used for either theory-building or theory-testing purposes. In theory-building mode, the researcher engages both in a thorough “soaking and probing” of the empirics of the case and in a far-reaching search in the theoretical literature to gain clues about potential mechanisms that could link a cause and outcome together, whereas in theory-testing mode, hypotheses about the observable manifestations that a theorized mechanism might leave are tested empirically in a case. In reality, most users of PT engage in a more iterated design that moves back-and-forth between theories and empirics (aka abductive design), with the end product an evidenced process theory that explains how a cause (or set of causes) is linked to an outcome in a case or set of cases.

PT as a method has two very obvious constituent elements: what is being traced at the theoretical level and how processes can be traced empirically. But in contrast to some methods, there is not one “correct” way to do PT because there are considerable differences between how scholars understand the two elements. These differences at the ontological and epistemological levels result in three different variants of PT methods, depicted in Table 1 .

At the level of theory of causal processes/causal mechanisms, the core distinctions are ontological. First, there is a more superficial divide in the literature regarding the level of abstraction that process theories should have, ranging from simple, one-liner-type theoretical explanations to more complex, and even case-specific, process theories. Other things equal, the lower the level of abstraction of the process theory, the more knowledge is gained about how things worked at the theoretical level, and stronger causal inferences about process are possible at the empirical level. However, this does not mean that more detail is always better. After an initial, in-depth case study that traces a detailed process theory in one case, it can be helpful to lift the level of theoretical abstraction to ease the task of assessing whether things worked in a similar fashion in a number of other cases.

More fundamental divides exist with regard to the ontological nature of the causal claims that are made when discussing causal processes and mechanisms. Here, there are (at least) three distinct positions: (a) mechanisms are in essence counterfactual causal claims, (b) mechanisms are causal because of the productive relationships of actors engaging in activities that link causes and outcomes together in cases, and (c) a more interpretivist position that contends that process theories are causal when they are able to capture how social actors construct and reconstruct the social reality they are a part of.

At the empirical level, the distinctions between counterfactual, productive, and social constructivists accounts of the nature of causation have epistemological implications for how causal processes should be traced. When tracing counterfactual claims, some form of controlled comparison of the actual with the potential counterfactual is required to be able to infer that the mechanism made a difference. In contrast, the productive account is sometimes termed the actualist position because causal inferences are made based on assessing whether the expected observable traces left by the activities of actors are present in an actual case. In the social constructivist account, more interpretivist methods are also utilized (sometimes as supplements, sometimes exclusively) to understand how social actors make sense of the practices of actors and social context in which they are embedded (i.e., meaning-making).

Whereas some scholars take a “my-way-or-the-highway,” methodological monist approach to questions related to causation and/or epistemology (e.g., Bevir & Blakely, 2018 ; King et al., 1994 ), a methodological pluralist position is recognizing and understanding that different positions are possible and that different variants have relative strengths and weaknesses in different research situations ( Beach, 2021 ; Runhardt, 2021 ). 2 For instance, if one believes that it is important to capture how social actors understand the diplomatic practices in which they are engaging, a more interpretive variant of PT would have comparative strengths. In contrast, when studying relatively “simple” processes that are repeated frequently (e.g., problem-solving processes in a team within an organization), a counterfactual-based variant that makes inferences through controlled comparisons has relative strengths ( Runhardt, 2021 , pp. 13–14). Methodological pluralism does not mean that anything goes. Instead, what is important is that there is alignment between the underlying ontological positions and the epistemology used to assess them in the PT research design ( Beach & Kaas, 2020 ; Hall, 2003 ).

Unfortunately, there are also examples of published studies in the social sciences in which scholars claim to be engaging in PT but instead merely pay lip service to the method by providing a citation or two in the Methods section, followed by a descriptive narrative of events in a case without linking to an explicit mechanistic theory. An atheoretical description of a sequence of events in a case is a form of narrative analysis that tells who did what and when, but it does not tell why they did it and, most important, why the events were linked in a causal sense. Although a descriptive narrative of what happened can be an important first step in any PT analysis, an atheoretical tracing of events does not shed light on the underlying causal linkage between a cause and an outcome, which is why a narrative description of a process is not the same thing as PT (e.g., Oppermann & Spencer, 2016 ). Fortunately, there are also numerous examples of scholars who implement a PT research design that lives up to the best practices of one of the variants of PT. This article discusses only these studies.

This article proceeds in three steps. First, it introduces the ontological distinctions about what is being traced in PT. Second, it discusses the different positions with regard to how processes and mechanisms can be traced empirically. Third, it discusses issues related to case selection and generalization of process theories in the different variants of PT.

What Is Being Traced? Causal Processes and Mechanisms

PT research probes the theoretical causal mechanisms (i.e., processes) linking causes and outcomes together. This section first discusses differing levels of aggregation of processual theories, followed by a review of the more fundamental differences in how scholars understand the nature of mechanistic causal claims.

Levels of Abstraction of Process Theories

Process tracers work with theories at varying levels of abstraction, ranging from minimalist, one-liner-type theories to detailed, case-specific theories that attempt to capture the particularities of how causal processes played out in a historical case. 3 In minimalist theories, the causal arrow between a cause and outcome is not theorized in any detail ( Elster, 1998 ; Goertz, 2017 ). Minimalist process theories typically take the form of one-liner-type theories of the pathway linking a cause and outcome together. An example is seen in Tannenwald’s (1999 ) article on the nuclear taboo. Tannenwald theorizes three possible pathways that can link norms and the non-use of nuclear weapons; these are depicted in Figure 1 .

Figure 1. Simple, abstract causal process theories and the nuclear taboo.

The process theorization in Tannenwald’s (1999 ) article does not go beyond very abstract one-liners, meaning that what is actually going on theoretically within the arrow(s) remains in a black box. Very abstract terms are used to theorize causal processes, such as “constraint on self-interested decision maker” ( Tannenwald, 1999 , p. 462), but readers are not told more about how these constraints actually work. Do decision makers have to discuss potential use of nuclear weapons among themselves, thereby providing opponents of usage with arguments they can deploy through normative speech acts to shame other actors? Or do the norms mean that decision makers never even discuss nuclear use because they believe it is “wrong”?

The goal of disaggregating causal processes into their constituent parts is to better understand how they work. This requires lowering the level of theoretical abstraction by providing a more-or-less detailed theorization of the actors involved and the activities that provide the causal linkages in the process ( Beach & Pedersen, 2019 ). In the social sciences, actors can be micro-level (i.e., individuals) or macro-level (i.e., collective social actors), with the requirement being that the latter have properties and orientations that enable them to do things that can impact other actors in a process. Activities are what social actors actually do; activities can take the form of speech acts, voting, paying bribes, etc.

It is important to note that a more detailed process theory will still be an analytical abstraction for all but the simplest of processes. Instead of detailing each and every individual and what they are doing in their interactions with each other during a period of time (days, weeks, or months), a detailed process theory attempts to capture the central actors and simplify their activities by only focusing on the most critical interactions. Using a metaphor, not all parts of a movie are equally “interesting.” In an action movie, screen time and special effects money will be concentrated on the final dramatic showdown between the good and bad persons. Similarly, not all parts of a process theory are equally “interesting,” and it can be warranted to focus on the most interesting parts ( Steel, 2008 ). These are the critical causal linkages in the process, involving interactions between actors.

Table 2 illustrates a disaggregated process theory used by Winward (2021 ) to explain the process whereby low intelligence capacities of security forces in a conflict area can lead to mass categorical violence against particular groups. Although the process theory is unpacked into several steps, it is still an analytical abstraction that includes only the most critical steps and linkages without theorizing everything that actors are doing in their interactions with each other. In the theorized process, the cause (low intelligence capacity in a conflict situation) spurs the security forces to approach local civilian elites for assistance in gathering information on threats (Part 1). The local civilian elites then exploit this dependence to settle scores in relation to pre-existing local conflicts with a particular group by providing false information targeted against individuals from the group, and also by encouraging other locals to take matters into their own hands by perpetrating violence against members of the targeted group (Part 2). The security forces use the (false) information provided to detain and interrogate individuals from the targeted group, resulting in an escalating cycle of torture and violence in which the many false confessionals from torture lead to even more detained and tortured individuals (Part 3). Furthermore, an increase in the number of detainees strains the capacities of the security forces, leading them to take extreme steps such as extrajudicial killings to clear out prisons (Part 3). Taken together, the process produces a marked increase in mass categorical violence by state security forces targeted against a particular group.

In contrast to minimalist one-liners, what is going on in-between is more explicitly theorized. This does not mean that disaggregated process theories are necessarily better than minimalist theories. Maintaining a high level of abstraction is a methodological choice that can be warranted in several research situations. First, early in research of a topic, there might be considerable uncertainty about which pathway links a cause and outcome together. Here, a PT study that takes the form of a plausibility probe exploring whether there is any evidence of a particular linkage can be a useful first step before more detailed process theories are traced empirically. Second, when research is more focused on investigating associations between causes and outcomes across many cases, a study that provides confirming evidence of a pathway linking them together makes it more plausible that the found association is actually causal. In the research situation faced by Tannenwald (1999 ), staying at a very high level of abstraction was warranted because there was a low prior confidence in the existence of any form of causal process linking norms and non-use (p. 438). In addition, minimalist studies can be useful after a series of more disaggregated studies to explore the scope of potential process generalizations. In contrast, when the goal of research is focused on understanding how the process worked in a historical case, the theorized process typically has numerous steps and can even include case-specific elements (e.g., particular named actors and specific activities that they perform).

Different Understandings of the Causal Nature of Mechanistic Claims

Causal mechanisms are one of the most widely used but also least understood types of causal claim in the social sciences (e.g. Beach, 2021 ; Brady, 2008 ; Gerring, 2010 ; Hedström & Ylikoski, 2010 ). The essence of making a mechanism-based claim is that the analytical focus shifts from causes and outcomes to the process in-between that links them. That is, mechanisms are not causes but, rather, are causal processes that are triggered by causes in particular contexts and that provide the causal linkage with outcomes. However, beyond this core point, there is disagreement among process tracers about the ontological nature of mechanisms as causal claims. There are (at least) three distinct understandings, all of which imply different epistemological strategies for PT research.

A counterfactual-based understanding of mechanisms defines causation as a situation in which a cause (or causal process/mechanism) is related to an outcome because its absence results in the absence of the outcome, all other things held equal ( Morgan & Winship, 2007 ). The term potential outcomes framework is often used to denote counterfactual claims because one can only assess whether a factor is causal by comparing what actually took place with what potentially could have taken place when it was absent, either in comparable cases or in logical hypotheticals ( Aviles & Reed, 2017 , p. 722; Mahoney & Barrenechea, 2019 ; Runhardt, 2015 ). Conceptually, counterfactual-based mechanism claims are often theorized in minimalist terms as X → M → Y (e.g., Mahoney, 2015 ).

In contrast, in the productive account, a mechanism is causal when there is a sequence of actors engaging in activities that transmit causal forces from the cause to the outcome ( Beach & Pedersen, 2019 ; Clarke et al., 2014 ; Machamer et al., 2000 ). At its core, a mechanistic explanation attempts to explain theoretically how things work within a case or set of cases within a particular context ( Cartwright, 2011 ) by unpacking the activities and the causal linkages they provide to explain why the cause is linked to the outcome. Mechanistic theories are typically viewed as systems in which the spatiotemporal organization of actors and the activities that they perform matter for how the systems works, as does the context within which the systems operate. Taken as a whole, a causal process is viewed in the productive account as more than the sum of its parts, and how it operates is very sensitive to context ( Cartwright, 2011 ; Falleti & Lynch, 2009 ; Sawyer, 2004 ). This means that one cannot just “remove” a part of a process and replace it with some other actor doing something else without changing the rest of the process. Nor can one claim that just because it has been found to work in one case, it should work everywhere.

In the productive account, causal claims are made about actual causal linkages as they operate within single cases. However, there is disagreement within the productive understanding on the question of whether a causal process can occur only once and still be termed causal (i.e., singular causation) ( Beach & Pedersen, 2019 ; Cartwright, 2021 ) or whether there has to be some form of regularity in its operation across cases before the term causal can be applied (e.g., Andersen, 2012 ). Both positions are logically defensible, but they point research in different directions. Thinking in more singular causal terms leads to research aimed at understanding the complexities of how processes worked in a single case, in which process theories are case-specific. In contrast, accepting some form of regularity as a prerequisite for making mechanistic causal claims implies research that has the ambition of making contingent generalizations about mechanisms across a set of cases.

A third understanding of mechanisms takes as its ontological point of departure the claim that the social world is fundamentally different from the natural world. This view is shared among social constructivist ( Guzzini, 2017 ; Norman, 2016 ) and critical realist scholars ( Danermark et al., 2019 ; Sayer, 2000 ). At the ontological level, how actors understand their actions and those of others, and how they understand the social context in which they are embedded, matters for how causal processes play out. This means that processual theorization needs to take seriously the intersubjective understandings and meaning-making of social actors in a particular social context. Pouliot (2014 ) develops an interpretive variant of PT that he terms “practice-tracing,” in which practices are defined as habitual patterns of actions performed by actors. Norman (2016 , 2021 ) puts forward an interpretivist variant in which causal processes are nested in what he terms “constitutive” explanations. The constitutive element is the structural conditions, latent dispositions, and causal capacities that come from a given social context, whereas the causal element is the moving parts. He defines causality as the relations between events, focusing on “how specific actions and events can alter the context in which they appear” ( Norman, 2016 , p. 87).

How Can Process Theories Be Traced Empirically?

There are (at least) three different positions taken on the question of epistemology in the literature that stem from differences in how scholars understand what is being traced: (a) controlled comparisons across cases at the level of process (or parts thereof) that use either real-world cases or logical hypotheticals, (b) evidencing based on the observable traces they leave within cases, and (c) a more interpretive variant of PT that studies processes using interpretive methods such as ethnographies and interpretive interviewing to examine discourses and practices.

Controlled Cross-Case Comparisons

In the controlled comparison variant, evidence takes the form of the difference that the presence/absence of a pathway (or parts thereof) has for the outcome in two or more cases. In effect, this means that the pathway is treated as a counterfactual claim evidenced empirically by measuring the difference that presence/absence makes across the cases ( Mahoney & Barrenechea, 2019 ; Runhardt, 2015 , 2021 , p. 9). Two or more “most similar” cases are compared that are similar in all respects except whether the pathway is present or absent. The cases selected for comparison can be either both real-world cases or involve a comparison with a nonexistent, logical hypothetical case (a “what if” case) ( Levy, 2015 ; Mahoney & Barrenechea, 2019 ).

If the most similar comparison finds that the outcome was present in both cases despite the process being present in one case and absent in the other, this would disconfirm the theorized process as the causal linkage, and vice versa. Note that when the PT variant of controlled comparisons operates with real-world cases, only a small number of cases are used in order to strategically select cases that are as most similar as possible. This marks a methodological difference with large- n mediation analysis, in which one or more observables of a process (i.e., causal mechanisms) are used as indicators that are tested in a controlled comparison across a large number of cases to assess the difference that presence/absence makes ( Imai et al., 2011 ).

The controlled comparison method is illustrated in Figure 2 , based on Runhardt’s (2015 ) description of what a most similar comparison design could look like. Using Bakke’s (2013 ) study of the impact of transnational insurgents in the Second Chechen War, Runhardt suggests that to be able to assess whether the process of watching videos of suicide bombings actually made a difference, the Second Chechen War case should have been compared with another case in which the only difference is that the process is not present. If the difference in presence/absence of the pathway is found to have made a difference, then the conclusion can be made that the pathway produced the difference. The strength of this conclusion depends on the degree to which other factors are similar between the cases.

Figure 2. A controlled comparison of pathway “watching videos.”

In principle, the same form of most similar controlled comparison could be used for assessing disaggregated process theories, although the comparison would have to be repeated for each step of the process theory. Irrespective of whether process theories are disaggregated or not, the core challenge is finding real-world cases in which everything else is so similar that it can be claimed that the only meaningful difference is the presence/absence of the process itself. Therefore, many case study scholars argue for the utility of logical hypotheticals where there are the fewest changes to the actual world as possible ( Mahoney & Barrenechea, 2019 , p. 316). Levy (2008 ) writes, ‘Counterfactual analysis ideally posits an alternative world that is identical to the real world in all theoretically relevant aspects but one, in order to explore the consequences of that difference” (p. 634).

Tracing the Within-Case Observable Manifestations of Processes

An alternative approach to evidencing processes is to trace them empirically through the observable, within-case manifestations of either pathways taken as a whole (minimalist one-liners) or the traces left by the activities performed by actors in each part of a disaggregated process. In the literature, terms such as “causal process observations” ( Brady & Collier, 2011 ), “diagnostic evidence” ( Bennett & Checkel, 2014 , p. 7), or “mechanistic evidence” are also used to denote the observable manifestations left by processes playing out within cases ( Beach & Pedersen, 2019 ; Clarke et al., 2014 ). Observable manifestations can be thought of as the empirical fingerprints left by the operation of a causal process in a case, of if disaggregated, the fingerprints left by the activities of actors that are linkages in the process. Common to all of these terms is that the evidence used does not involve a controlled comparison across two or more cases but instead is any type of empirical material that has probative value in relation to determining whether the process actually took place within a case. These traces can take many different forms. For example, they can involve patterns within cases, such as social networks that emerge between actors during a process. They can also involve temporal sequences—for example, whether a search for alternative solutions in past cases happened before a solution was suggested by an actor. Alternatively, they can be the content of empirical material, such as the speech acts of a particular actor during a meeting.

Following Van Evera (1997 ), many process tracers have tried to systematize how to evaluate the probative value of this type of evidence, often drawing explicitly on Bayesian logic. The following discussion does not introduce Bayesian logic in any detail (for introductions to this, see Beach & Pedersen, 2019 ; Bennet & Checkel, 2014 ; Fairfield & Charman, 2017 ), noting only that there is a discussion in the literature on whether PT should use more formalized, explicit Bayesian analysis (e.g., Bennett et al., 2022 ; Fairfield & Charman, 2017 ) or whether more informal applications of Bayesian reasoning are more useful for PT (e.g., Beach & Pedersen, 2019 ; Zaks, 2021a , 2021b ). Instead, the following discussion presents the underlying Bayesian intuition that not all evidence has the same probative value, and the amount of “updating” is determined by whether one had to find it and whether there are plausible alternative explanations for finding it.

The probative value of evidence is determined by the answers to several questions about what evidence in theory can tell researchers and whether researchers can trust sources (Figure 3 ). When operationalizing a process theory, the researchers is asking what empirically observable fingerprints they might expect to observe in a case if a given actor and activity took place (or overall process if working with a minimalist process theory). For instance, one part of Winward’s (2021 ) process theory was that security forces would approach local civilian elites for information (see Table 2 ). He operationalizes a series of potential observables that could act as evidence, such as “We would also expect to find former elites, or those close to them, who would divulge such soliciting of information when interviewed” ( Winward, 2021 , p. 562).

Figure 3. Moving from process theory to actual empirical sources.

The probative value of a given expected observable is a function of two factors: whether it had to be found (certainty in Bayesian terms) and, if found, whether there are alternative explanations for finding it (uniqueness in Bayesian terms). Whether evidence has to be found (i.e., certainty) relates to the disconfirmatory power of evidence, whereas whether alternative explanations are plausible or not relates to the confirmatory power of evidence.

Some activities can be expected to leave empirical fingerprints in a case, whereas others might leave few traces. Returning to the Tannenwald (1999 ) example discussed previously, if the pathway related to personal moral convictions works through actors not even considering what they consider “wrong” actions, this pathway would leave few empirical traces—indeed, the absence of evidence of actors discussing the nuclear option could potentially act as evidence of deep normative convictions keeping options off the table for discussion.

The confirmatory power of hypothesized observables relates to whether, if found, there are alternative explanations for finding the evidence. If the hypothesized observable is found and there are few alternative explanations, this would enable a strong confirming inference to be made, and vice versa. For instance, if one had theorized that a part of a diplomatic negotiation process is “actor A persuades actor B in meeting using arguments,” a hypothesized observable could be that actor B changes how they talk about a policy after the meeting. However, the change might be purely strategic, in which they changed their position due to other reasons than normative arguments (e.g., material factors such as the threat of military action). Another alternative explanation of finding the observable could be that actor B does not change position but instead is only paying lip service to the views of actor A in public. When there are plausible alternative explanations, finding an observable only provides weak or no confirmation.

Hypothesized observables are still not evidence upon which inferences about the presence/absence of the part of the process can be made. In the within-case tracing PT variant, inferences are only able to be made when the actual sources of the observations (or lack thereof) of the propositions are also evaluated. At the empirical level, researchers have to ask whether a particular observation matches what they expected to find and whether they had access (if not found) and, if found, whether they can trust the source. Researchers might only have very untrustworthy sources for observing the hypothesized observable, even though it would have been very confirming if actually found. Often process tracers use interviews with participants who have a stake in the events being studied, and therefore have incentives to provide biased accounts. In this instance, actually found evidence in an interview would not enable strong confirmation because the source could not be trusted. The questions that should be asked here are common source critical questions. It is only through corroboration across multiple sources and types of evidence that evidence can be trusted. As an example of best practices, Winward (2021 ) includes two appendices that discuss individual sources of evidence and the degree to which they can be trusted.

Interpretive Variants of Process Tracing

Several attempts have been made to develop more interpretivist versions of PT ( Guzzini, 2017 ; Norman, 2016 , 2021 ; Pouliot, 2014 ). What they share is the contention that to understand how social causal processes work, interpretive hermeneutic methods must also be used that try to tap into intersubjective understandings of social actors and how they make sense of their interactions with other social actors—what is termed “experience-near” evidence in the literature ( Danermark et al., 2019 , pp. 30, 33; Geertz, 1974 ).

As examples, Pouliot (2014 ) argues for adding an extra layer of “meaningfulness” to PT analyses by studying the stock of unspoken assumptions and tacit know-how of practitioners to understand their intentions and beliefs with regard to sets of practices that they perform, through the use of interpretivist discourse, interviewing, or ethnographic observation techniques.

Norman (2016 , 2021 ) suggests that interpretive PT uses what he terms “contrastive” explanations that build on counterfactual controlled comparisons of discourses. These can include before/after comparisons or “normal” events compared with an “abnormal” event that changes the trajectory of developments. He puts forward a three-step analytical procedure for interpretive PT that ( Norman, 2021 , p. 19)

map change in the broader institutional setting—for example, by asking actors of “normal” actions, and then what constituted the “abnormal” and thus conflict between actors at a later time;

explore how change reconstituted actor self-understandings; and

assess how the changed self-understandings gave rise to particular actions.

Case Selection and Generalizing About Mechanisms

This section reviews the state-of-the-art regarding case selection, followed by a discussion of whether and how mechanistic generalizations can be made.

Selecting Appropriate Cases for Process Tracing

The core case selection principles of PT are generally agreed upon. First, PT is a case-based method, which requires that concepts (causes, context, and outcomes) are theorized in set-theoretical terms ( Beach & Pedersen, 2016 ; Goertz & Mahoney, 2012 ). This means that concepts are defined by the theoretical attributes that determine whether a given case is in or out of the “set” of the concept—that is, it is a member of the concept or not. For example, if one is interested in tracing a process linking development and democratization, clear definitions of both concepts would be required that enable the scholar to determine whether a given case is a member or not of the concepts.

All PT variants therefore share an interest in positive, “typical” cases in which cause, outcome, and relevant contextual conditions are all present (Table 3 ) ( Beach & Pedersen, 2018 ; Schneider & Rohlfing, 2013 ). In negative cases, where the cause and outcome are not present, there is no ‘process’ to trace. When controlled-comparison variants of PT are used, a typical case is compared with a most similar case in which the mechanism (or part) was not present. If the mechanism makes a difference, the most similar case would be a deviant case consistency in which the outcome as a result does not occur. Cases in which both a cause and an outcome are not present are termed “irrelevant” cases (Table 3 , quadrant III), in which there is obviously no process to trace because the cause and outcome are not present ( Mahoney & Goertz, 2004 ).

Two types of deviant cases are relevant for PT, but only after one has a good understanding of how processes work in typical cases. These are deviant coverage and deviant consistency cases ( Schneider & Rohlfing, 2013 ). A deviant coverage case is one in which a cause or contextual condition is not present, but the outcome has occurred. In this type of case, one is interested in determining what other cause(s) might have produced the outcome. Here, all three variants of PT are relevant for probing what other cause(s) might be present. Given the focus on detecting new causes, processes are typically kept at a very abstract level.

Alternatively, when a cause is present but one or more contextual conditions that allow the operation of a given process are not present, a theory-building PT case study can shed light on alternative causal pathways between a cause and an outcome.

Deviant consistency case are instances in which a process should have linked to the outcome but the process breaks down. Here, tracing a relatively disaggregated process until it breaks down can shed light on omitted contextual conditions that have to be present for a cause to work and/or other causes that also have to be present for the outcome to be produced ( Beach & Pedersen, 2018 ).

Can Mechanistic Generalizations Be Made, and If So, How?

Irrespective of which variant is used, PT case studies end up saying a lot about a little—or in many applications of PT, only one case. In most interpretivist PT applications, there is little or no ambition to generalize process theories because they are understood to be contextually specific to a specific social setting. In contrast, many other PT scholars have ambitions of build more “general” process theories, understood as causal processes that can be expected to work in a similar manner in other cases.

In the literature, there are several different approaches to how mechanistic generalizations can be made. First, there are approaches that claim that when a typical case is “representative” of the population to which generalizations are intended to be made, generalizations can be made after studying a single case. When there is

causal homogeneity among cases that are of the same type and belong to the same term and causal heterogeneity across different types . . . findings from the study of one, say, typical case, travel to all other typical cases of the same term, but not beyond this term. ( Schneider & Rohlfing, 2016 , p. 556)

A similar approach is to claim that the selected typical case was “least likely” for the causal mechanism, and therefore when it works in the least-likely case, it should work everywhere ( George & Bennett, 2005 , pp. 109–125; Levy, 2008 , p. 12). This is even a stronger form of one-to-many generalization because of the amount of knowledge about the underlying population in terms of how the cause and context interact with other causes and contextual conditions in other cases that is required if we are to claim a given case is ‘least-likely’ in relation to other more ‘typical’ cases in the population.

There are other PT scholars who contend that one-to-many strategies risk making generalizations based on hope instead of actual evidence from other cases ( Khosrowi, 2019 ). The literature on causal processes frequently notes that the ways they unfold in a specific case are sensitive to the context that surrounds them ( Falleti & Lynch, 2009 ; Lindquist & Wellstead, 2019 , pp. 31–33). Contextual conditions are sometimes termed “scope” conditions in the literature, but the terms mean the same thing. Contextual conditions can be defined as all “relevant aspects of a setting (analytical, temporal, spatial, or institutional)” in which the analysis is embedded in and which might have an impact on the constitutive parts of a process ( Falleti & Lynch, 2009 , p. 1152). Even when the same causes and outcome are present, different contextual conditions can create differences in the processes linking them together ( Falleti & Lynch, 2009 ; Steel, 2008 ). This means that two cases that look causally homogeneous based on sharing similar causal conditions and an outcome might be heterogeneous at the process level because of contextual differences. For different processes, the whole process may be completely different, or only one or several parts may diverge between two cases.

The solution to the problem of causal complexity and mechanisms is not just to lift the level of theoretical abstraction of the process theory. Of course, logically the more abstract a theorized mechanism (lower intension), the more cases can be found in which it is present (higher extension), and vice versa. This means there is an inherent trade-off between disaggregating causal process theories and how far they can potentially travel, illustrated in Figure 4 . Very abstract one-liner process theories can in principle be present in many different cases because they tell very little about what people are actually doing in the case. However, even simple process theories operate only within particular contexts. For instance, Haggard and Kaufman (2016 ) theorize that mass mobilization is a mechanism linking economic inequality and a democratic transition. However, as they detail in their book, mass mobilization should not be expected to be operative in every case in which economic inequality and democratic transitions took place because there are other pathways in other contexts.

Figure 4. Levels of theoretical abstraction and the external validity of mechanistic claims.

A stronger strategy for generalizing mechanistic claims is to adopt a multiple cases approach ( Beach et al., 2019 , pp. 133–144). Here, an initial PT case study is undertaken to build a theorized process theory at a medium level of abstraction (relatively simple, midrange, or quite detailed). Other PT case studies are then undertaken on other cases that are strategically selected within a population of potential cases in which the process might work based on their scores on conditions that might impact how processes work. These follow-up, generalizing PT case studies can utilize a strategy in which the subsequent PT studies operate with a simpler, more abstract process theory in order to make the analysis more feasible (requires fewer resources). Depending on how many cases are traced, and how contextually sensitive the given process is, process-level generalizations can be made which claim that the process works in at least a roughly analogous manner across a set of cases.

Challenges When Using Process Tracing

Engaging in “good” process tracing (PT) is difficult, but the same can be said of any rigorous social science method. However, potential users of PT face a range of challenges that are relatively unique to PT. First, in contrast to methods such as experimental designs, in PT there is a large variety of different understandings of the method itself and what best practices should be followed. This article has argued that as long as there is alignment between the underlying ontological assumptions and epistemological approach, these differences in PT methods should be viewed as a strength because it allows scholars to choose the variant that best fits the research question and context.

Second, irrespective of which variant is used, PT case studies say a lot about a little—or in many applications of PT, only one case. This can make it difficult to get past peer reviewers, who often want to hear about the “general.”

Finally, scholars engaging in PT face challenges when trying to communicate their findings with scholars from other traditions ( Beach & Kaas, 2020 ). For instance, when working with a disaggregated tracing variant of PT, claims deal with causal linkages between causes and outcomes within a single case ( Beach & Kaas, 2020 ; Clarke et al., 2014 ). This makes it difficult to communicate with scholars who have been trained to assess causal effects (especially those within the so-called potential outcomes framework) because these individuals might have difficulty accepting that fundamentally different types of claims are being made. For instance, a common review comment is that there is no “variation” in the design, even though “variation” is not relevant to evidencing mechanisms when they are understood as productive linkages. Similar challenges face scholars doing interpretivist PT, with reviewers who think in neo-positivist terms finding it very difficult to understand how an interpretivist PT case study taps into the lifeworld of social actors. Furthermore, the process theories used in interpretivist PT studies often are more fluid and sensitive to specific social contexts, making it difficult to communicate with PT scholars who have the ambition of producing more generalizable process theories that can be used across many cases.

There is not an easy answer to these questions, beyond reiterating a plea for methodological pluralism in which scholars appreciate different approaches to learning about the social world that they all care so much about.

• Andersen, H. (2012). The case for regularity in mechanistic causal explanation. Synthese , 189 , 415–432.
• Aviles, N. B. , & Reed, I. A. (2017). Ratio via machina: Three standards of mechanistic explanation in sociology. Sociological Methods & Research , 46 (4), 715–738.
• Bakke, K. M. (2013). Copying and learning from outsiders? Assessing diffusion from transnational insurgents in the Chechen wars. In J. T. Checkel (Ed.), Transnational dynamics of civil war (pp. 31–62). Cambridge University Press.
• Beach, D. (2021). Evidential pluralism and evidence of mechanisms in the social sciences. Synthese , 199 , 8899–8919.
• Beach, D. , & Kaas, J. G. (2020). The great divides: Incommensurability, the impossibility of mixed-methodology, and what to do about it. International Studies Review , 22 (2), 214–235.
• Beach, D. , & Pedersen, R. B. (2016). Casual case studies . University of Michigan Press.
• Beach, D. , & Pedersen, R. B. (2018). Selecting appropriate cases when tracing causal mechanisms. Sociological Methods & Research , 47 (4), 837–871.
• Beach, D. , & Pedersen, R. B. (2019). Process tracing methods . University of Michigan Press.
• Beach, D. , & Pedersen, R. B. , with Siewert, M. (2019). Case selection and nesting of process tracing. In Process tracing methods (pp. 89–128). University of Michigan Press.
• Bennett, A. , & Checkel, J. (2014). Process tracing: From metaphor to analytic tool . Cambridge University Press.
• Bennett, A. , Charman, A. E. , & Fairfield, T. (2022). Understanding Bayesianism: Fundamentals for process tracers . Political Analysis , 30 (2), 298–305.
• Bevir, M. , & Blakely, J. (2018). Interpretive social science: An anti-naturalist approach . Oxford University Press.
• Brady, H. E. (2008). Causation and explanation in social science. In J. M. Box-Steffensmeier , H. E. Brady , & D. Collier (Eds.), The Oxford handbook of political methodology (pp. 217–270). Oxford University Press.
• Brady, H. E. , & Collier, D. (Eds.). (2011). Rethinking social inquiry: Diverse tools shared standards ( 2 nd ed., pp. 161–200). Rowman Littlefield.
• Cartwright, N. (2011). Predicting “it will work for us”: (Way) beyond statistics. In P. McKay Illari , F. Russo , & J. Williamson (Eds.), Causality in the sciences (pp. 750–768). Oxford University Press.
• Cartwright, N. (2021). Rigour versus the need for evidential diversity. Synthese , 199 (4–5), 13095–13119.
• Clarke, B. , Gillies, D. , Illari, P. , Russo, F. , & Williamson, J. (2014). Mechanisms and the evidence hierarchy. Topoi , 33 (2), 339–360.
• Closa, C. , & Palestini, S. (2018). Tutelage andregime survival in regional organizations’ democracy protection: The case of MERCOSUR and UNASUR. World Politics , 70 (3), 443–476.
• Craver, C. F. , & Darden, L. (2013). In search of mechanisms . University of Chicago Press.
• Danermark, B. , Ekström, M. , & Karlsson, J. C. (2019). Explaining society: Critical realism in the social sciences ( 2 nd ed.). Routledge.
• Elster, J. (1998). A plea for mechanisms. In P. Hedström & R. Swedberg (Eds.), Social mechanisms (pp. 45–73). Cambridge University Press.
• Fairfield, T. , & Charman, A. E. (2017). Explicit Bayesian analysis for process tracing: Guidelines, opportunities, and caveats. Political Analysis , 25 (3), 363–380.
• Falleti, T. G. , & Lynch, J. F. (2009). Context and causal mechanisms in political analysis. Comparative Political Studies , 42 , 1143–1166.
• Fujii, L. A. (2018). Interviewing in social science research: A relational approach . Routledge.
• Geertz, C. (1974). “From the native’s point of view”: On the nature of anthropological understanding. Bulletin of the American Academy of Arts and Sciences , 28 (1), 26–45.
• George, A. L. , & Bennett, A. (2005). Case studies and theory development in the social sciences . MIT Press.
• Gerring, J. (2010). Causal mechanisms: Yes but . . .. Comparative Political Studies , 43 (11), 1499–1526.
• Goertz, G. (2017). Multimethod research, causal mechanisms, and case studies: An integrated approach . Princeton University Press.
• Goertz, G. , & Mahoney, J. (2012). A tale of two cultures: Qualitative and quantitative research in the social sciences . Princeton University Press.
• Guzzini, S. (2017). Militarizing politics, essentializing identities: Interpretivist process tracing and the power of geopolitics. Cooperation and Conflict , 52 (3), 423–445.
• Haggard, S. , & Kaufman, R. R. (2016). Dictators and Democrats: Masses, elites, and regime change . Princeton University Press.
• Hall, P. A. (2003). Aligning ontology and methodology in comparative politics. In J. Mahoney , & D. Rueschemeyer (Eds.), Comparative historical analysis in the social sciences (pp. 373–406). Cambridge University Press.
• Hedström, P. , & Ylikoski, P. (2010). Causal mechanisms in the social sciences. Annual Review of Sociology , 36 , 49–67.
• Imai, K. , Keele, L. , Tingley, D. , & Yamamoto, T. (2011). Unpacking the black box of causality: Learning about causal mechanisms from experimental and observational studies. American Political Science Review , 105 (4), 765–789.
• Johais, E. , Bayer, M. , & Lambach, D. (2020). How do states collapse? Towards a model of causal mechanisms. Global Change, Peace & Security , 32 (2), 179–197.
• Khosrowi, D. (2019). Extrapolation of causal effects—Hopes, assumptions, and the extrapolator’s circle. Journal of Economic Methodology , 26 (1), 45–58.
• King, G. , Keohane, R. O. , & Verba, S. (1994). Designing social inquiry: Scientific inference in qualitative research . Princeton University Press.
• Levy, J. (2008). Case studies: Types, designs, and logics of inference. Conflict Management and Peace Science , 25 (1), 1–18.
• Levy, J. (2015). Counterfactuals, causal inference, and historical analysis. Security Studies , 24 (3), 378–402.
• Lindquist, E. , & Wellstead, A. (2019). Policy process research and the causal mechanism movement: Reinvigorating the field? In Capano, Howlett, Ramesh , and Virani (Eds.), Making policies work (pp. 14–38). Elgar.
• Löblová, O. (2018). When epistemic communities fail: Exploring the mechanism of policy influence. Policy Studies Journal , 46 (1), 160–189.
• Machamer, P. , Darden, L. , & Craver, C. F. (2000). Thinking about mechanisms. Philosophy of Science , 67 (1), 1–25.
• Mahoney, J. (2015). Process tracing and historical explanation. Security Studies , 24 (2), 200–218.
• Mahoney, J. , & Barrenechea, R. (2019). The logic of counterfactual analysis in case-study explanation. British Journal of Sociology , 70 (1), 306–338.
• Mahoney, J. , & Goertz, G. (2004). The possibility principle: Choosing negative cases in comparative research. American Political Science Review , 98 (4), 653–669.
• Morgan, S. L. , & Winship, C. (2007). Counterfactuals and causal inference: Methods and principles for social research . Cambridge University Press.
• Norman, L. (2016). The mechanisms of institutional conflict in the European Union . Routledge.
• Norman, L. (2021). Rethinking causal explanation in interpretive international studies. European Journal of International Relations , 27 (3), 936–959.
• O’Mahoney, J. (2017). Making the real: Rhetorical adduction and the Bangladesh Liberation War. International Organization , 71 (2), 317–348.
• Oppermann, K. , & Spencer, A. (2016). Telling stories of failure: Narrative constructions of foreign policy fiascos. Journal of European Public Policy , 23 (5), 685–701.
• Pouliot, V. (2014). Practice tracing. In A. Bennett & J. Checkel (Eds.), Process tracing: From metaphor to analytical tool (pp. 237–259). Cambridge University Press.
• Rohlfing, I. , & Zuber, C. (2021). Check your truth conditions! Clarifying the relationship between theories of causation and social science methods for causal inference. Sociological Methods & Research , 50 (4), 1623–1659.
• Runhardt, R. W. (2015). Evidence for causal mechanisms in social science: Recommendations from Woodward’s manipulability theory of causation. Philosophy of Science , 82 (5), 1296–1307.
• Runhardt, R. W. (2021). Evidential pluralism and epistemic reliability in political science: Deciphering contradictions between process tracing methodologies. Philosophy of the Social Sciences , 51 (4), 425–442.
• Sawyer, R. K. (2004). The mechanisms of emergence. Philosophy of the Social Sciences , 34 (2), 260–282.
• Sayer, A. (2000). Realism and social science . SAGE.
• Schneider, C. , & Rohlfing, I. (2013). Combining QCA and process tracing in set-theoretical multi-method research. Sociological Methods and Research , 42 (4), 559–597.
• Schneider, C. Q. , & Rohlfing, I. (2016). Case studies nested in fuzzy-set QCA on sufficiency: Formalizing case selection and causal inference. Sociological Methods & Research , 45 (3), 526–568.
• Sewell, W. H. (1992). A theory of structure: Duality, agency, and transformation. American Journal of Sociology , 98 (1), 1–29.
• Steel, D. (2008). Across the boundaries: Extrapolation in biology and social science . Oxford University Press.
• Tannenwald, N. (1999). The nuclear taboo: The United States and the normative basis of nuclear non-use. International Organization , 53 (3), 433–468.
• Van Evera, S. (1997). Guide to methods for students of political science . Cornell University Press.
• Widmaier, W. W. (2007). Constructing foreign policy crises: Interpretive leadership in the Cold War and War on Terrorism. International Studies Quarterly , 51 (4), 779–794.
• Winward, M. (2021). Intelligence capacity and mass violence: Evidence from Indonesia. Comparative Political Studies , 54 (3–4), 553–584.
• Zaks, S. (2021a). Updating Bayesian(s): A critical evaluation of Bayesian process tracing. Political Analysis , 29 (1), 58–74.
• Zaks, S. (2021b). Return to the scene of the crime: Revisiting process tracing, Bayesianism, and murder . Political Analysis , 30 , 1–5.

1. Note the terms causal process and causal mechanism are used as synonyms throughout this article.

2. A milder version of monism is to claim that although different understandings of causation are valid, there is one variant that has “most value for the social sciences” ( Rohlfing & Zuber, 2021 , p. 1626).

3. The level of theoretical abstraction should not be confused with actual empirical evidence. When one lowers the level of theoretical abstraction, one is unpacking how the process works in terms of theorized interactions between social actors. The actual evidence of the operation of a mechanism, or parts thereof, will always be case-specific.

Related Articles

• Comparative Public Policy
• Qualitative Comparative Analysis (QCA) and Set Theory
• Reconceptualizing Field Research in Political Science
• Process Tracing in Crisis Decision Making

Printed from Oxford Research Encyclopedias, Politics. Under the terms of the licence agreement, an individual user may print out a single article for personal use (for details see Privacy Policy and Legal Notice).

date: 01 May 2024

• Cookie Policy
• Privacy Policy
• Legal Notice
• Accessibility
• [66.249.64.20|91.193.111.216]
• 91.193.111.216

Character limit 500 /500

This website may not work correctly because your browser is out of date. Please update your browser .

Process tracing in case study research

• Process tracing in case study research File type PDF File size 137.77 KB

This resource examines some of the philosophy science issues related to process tracing, including the roles of causal effects and causal mechanisms in causal explanation and the logic of process tracing. It considers how process tracing stands in relation to common misunderstandings of case study methods and discusses the inductive and theory-testing uses of process tracing. It conclude with views on the strengths and weaknesses of process tracing.

• Introduction
• Causal Effects and Causal Mechanisms as Bases for Causal Inferences
• Process Tracing as a Mode of Inferences on Causal Mechanisms
• Process-Tracing and Historical Explanation
• Process Tracing and the "Degrees of Freedom Problem"
• Process Tracing as a Corrective for the Limits of Mill's Methods
• Inductive and Theory-Testing Uses of Process Tracing
• Conclusions

Bennett B and  Geor ge  A L. (1997),  Process Tracing  in Case Study Research       MacArthur Foundation Workshop on Case Study Methods  October 17-19,  Georgetown University and  Stanford University, USA. Retrieved from  https://polisci.berkeley.edu/sites/default/files/people/u3827/Understanding%20Process%20Tracing.pdf

'Process tracing in case study research' is referenced in:

• Process tracing

Back to top

© 2022 BetterEvaluation. All right reserved.

Thank you for visiting nature.com. You are using a browser version with limited support for CSS. To obtain the best experience, we recommend you use a more up to date browser (or turn off compatibility mode in Internet Explorer). In the meantime, to ensure continued support, we are displaying the site without styles and JavaScript.

• View all journals
• My Account Login
• Explore content
• About the journal
• Publish with us
• Sign up for alerts
• Open access
• Published: 01 April 2024

Adaptive neighborhood rough set model for hybrid data processing: a case study on Parkinson’s disease behavioral analysis

• Imran Raza 1 ,
• Muhammad Hasan Jamal 1 ,
• Rizwan Qureshi 1 ,
• Abdul Karim Shahid 1 ,
• Angel Olider Rojas Vistorte 2 , 3 , 4 ,
• Md Abdus Samad 5 &
• Imran Ashraf 5  

Scientific Reports volume  14 , Article number:  7635 ( 2024 ) Cite this article

242 Accesses

Metrics details

• Computational biology and bioinformatics
• Machine learning

Extracting knowledge from hybrid data, comprising both categorical and numerical data, poses significant challenges due to the inherent difficulty in preserving information and practical meanings during the conversion process. To address this challenge, hybrid data processing methods, combining complementary rough sets, have emerged as a promising approach for handling uncertainty. However, selecting an appropriate model and effectively utilizing it in data mining requires a thorough qualitative and quantitative comparison of existing hybrid data processing models. This research aims to contribute to the analysis of hybrid data processing models based on neighborhood rough sets by investigating the inherent relationships among these models. We propose a generic neighborhood rough set-based hybrid model specifically designed for processing hybrid data, thereby enhancing the efficacy of the data mining process without resorting to discretization and avoiding information loss or practical meaning degradation in datasets. The proposed scheme dynamically adapts the threshold value for the neighborhood approximation space according to the characteristics of the given datasets, ensuring optimal performance without sacrificing accuracy. To evaluate the effectiveness of the proposed scheme, we develop a testbed tailored for Parkinson’s patients, a domain where hybrid data processing is particularly relevant. The experimental results demonstrate that the proposed scheme consistently outperforms existing schemes in adaptively handling both numerical and categorical data, achieving an impressive accuracy of 95% on the Parkinson’s dataset. Overall, this research contributes to advancing hybrid data processing techniques by providing a robust and adaptive solution that addresses the challenges associated with handling hybrid data, particularly in the context of Parkinson’s disease analysis.

Similar content being viewed by others

Hybrid similarity relation based mutual information for feature selection in intuitionistic fuzzy rough framework and its applications

A dynamic fuzzy rule-based inference system using fuzzy inference with semantic reasoning

Improved adaptive-phase fuzzy high utility pattern mining algorithm based on tree-list structure for intelligent decision systems

Introduction.

The advancement of technology has facilitated the accumulation of vast amounts of data from various sources such as databases, web repositories, and files, necessitating robust tools for analysis and decision-making 1 , 2 . Data mining, employing techniques such as support vector machine (SVM), decision trees, neural networks, clustering, fuzzy logic, and genetic algorithms, plays a pivotal role in extracting information and uncovering hidden patterns within the data 3 , 4 . However, the complexity of the data landscape, characterized by high dimensionality, heterogeneity, and non-traditional structures, renders the data mining process inherently challenging 5 , 6 . To tackle these challenges effectively, a combination of complementary and cooperative intelligent techniques, including SVM, fuzzy logic, probabilistic reasoning, genetic algorithms, and neural networks, has been advocated 7 , 8 .

Hybrid intelligent systems, amalgamating various intelligent techniques, have emerged as a promising approach to enhance the efficacy of data mining. Adaptive neuro-fuzzy inference systems (ANFIS) have laid the groundwork for intelligent systems in data mining techniques, providing a foundation for exploring complex data relationships 7 , 8 . Moreover, the theory of rough sets has found practical application in tasks such as attribute selection, data reduction, decision rule generation, and pattern extraction, contributing to the development of intelligent systems for knowledge discovery 7 , 8 . Extracting meaningful knowledge from hybrid data, which encompasses both categorical and numerical data, presents a significant challenge. Two predominant strategies have emerged to address this challenge 9 , 10 . The first strategy involves employing numerical data processing techniques such as Principal Component Analysis (PCA) 11 , 12 , Neural Networks 13 , 14 , 15 , 16 , and SVM 17 . However, this approach necessitates converting categorical data into numerical equivalents, leading to a loss of contextual meaning 18 , 19 . The second strategy leverages rough set theory alongside methods tailored for categorical data. Nonetheless, applying rough set theory to numerical data requires a discretization process, resulting in information loss 20 , 21 . Numerous hybrid data processing methods have been proposed, combining rough sets and fuzzy sets to handle uncertainty 22 , 23 , 24 , 25 , 26 , 27 , 28 , 29 , 30 , 31 , 32 , 33 , 34 , 35 , 36 , 37 , 38 , 39 , 40 , 41 . However, selecting an appropriate rough set model for a given dataset necessitates exploring the inherent relationships among existing models, presenting a challenge for users. The selection and utilization of an appropriate model in data mining thus demand qualitative and quantitative comparisons of existing hybrid data processing models.

This research endeavors to present a comprehensive analysis of hybrid data processing models, with a specific focus on those rooted in neighborhood rough sets (NRS). By investigating the inherent interconnections among these models, this study aims to elucidate their complex dynamics. To address the challenges posed by hybrid data, a novel hybrid model founded on NRS is introduced. This model enhances the efficiency of the data mining process without discretization mitigating information loss and ambiguity in data interpretation. Notably, the adaptability of the proposed model, particularly in adjusting the threshold value governing the neighborhood approximation space, ensures optimal performance aligned with dataset characteristics while maintaining high accuracy. A dedicated testbed tailored for Parkinson’s patients is developed to evaluate the real-world effectiveness of the proposed approach. Furthermore, a rigorous evaluation of the proposed model is conducted, encompassing both accuracy and overall effectiveness. Encouragingly, the results demonstrate that the proposed scheme surpasses alternative approaches, adeptly managing both numerical and categorical data through an adaptive framework.

The major contributions, listed below, collectively emphasize the innovative hybrid data processing model, the adaptive nature of its thresholding mechanism, and the empirical validation using a Parkinson’s patient testbed, underscoring the relevance and significance of the study’s findings.

Novel Hybrid Data Processing Model: This research introduces a novel hybrid data processing model based on NRS, preserving the practical meaning of both numerical and categorical data types. Unlike conventional methods, it minimizes information loss while optimizing interpretability. The proposed distance function combines Euclidean and Levenshtein distances with weighted calculations and dynamic selection mechanisms to enhance accuracy and realism in neighborhood approximation spaces.

Adaptive Thresholding Mechanism: Another key contribution is the integration of an adaptive thresholding mechanism within the hybrid model. This feature dynamically adjusts the threshold value based on dataset characteristics, ensuring optimal performance and yielding more accurate and contextually relevant results.

Empirical Validation through Parkinson’s Testbed: This research provides a dedicated testbed for analyzing behavioral data from Parkinson’s patients, allowing rigorous evaluation of the proposed hybrid data processing model. Utilizing real-world datasets enhances the model’s practical applicability and advances knowledge in medical data analysis and diagnosis.

The subsequent structure of the paper unfolds as follows: section “ Related work ” delves into the related work. The proposed model is introduced in section “ Adaptive neighborhood rough set model ”, Section “ Instrumentation ” underscores the instrumentation aspect, section “ Result and discussion ” unfolds the presentation of results and ensuing discussions, while section “ Conclusion and future work ” provides the concluding remarks for the paper. A list of notations used in this study is provided in Table  1 .

Related work

Rough set-based approaches have been utilized in various applications like bankruptcy prediction 42 , attribute/feature subset selection 43 , 44 , cancer prediction 45 , 46 , etc. In addition, recently, several innovative hybrid models have emerged, blending the realms of fuzzy logic and non-randomized systems (NRSs). One such development is presented by Yin et al. 47 , who introduce a parameterized hybrid fuzzy similarity relation. They apply this relation to the task of granulating multilabel data, subsequently extending it to the domain of multilabel learning. To construct a noise-tolerant multilabel fuzzy NRS model (NT-MLFNRS), they leverage the inclusion relationship between fuzzy neighborhood granules and fuzzy decisions. Building upon NT-MLFNRS, Yin et al. also devise a noise-resistant heuristic multilabel feature selection (NRFSFN) algorithm. To further enhance the efficiency of feature selection and address the complexities associated with handling large-scale multilabel datasets, they culminate their efforts by introducing an efficient extended version of NRFSFN known as ENFSFN.

Sang et al. 48 explore incremental feature selection methodologies, introducing a novel conditional entropy metric tailored for dynamic ordered data robustness. Their approach introduces the concept of a fuzzy dominance neighborhood rough set (FDNRS) and defines a conditional entropy metric with robustness, leveraging the FDNRS model. This metric serves as an evaluation criterion for features, and it is integrated into a heuristic feature selection algorithm. The resulting incremental feature selection algorithm is built upon this innovative model

Wang et al. 19 introduced the Fuzzy Rough Iterative Computational (FRIC) model, addressing challenges in hybrid information systems (HIS). Their framework includes a specialized distance function for object sets, enhancing object differentiation precision within HIS. Utilizing this function, they establish fuzzy symmetric relations among objects to formulate fuzzy rough approximations. Additionally, they introduce evaluation functions like fuzzy positive regions, dependency functions, and attribute importance functions to assess classification capabilities of attribute sets. They developed an attribute reduction algorithm tailored for hybrid data based on FRIC principles. This work contributes significantly to HIS analysis, providing a robust framework for data classification and feature selection in complex hybrid information systems.

Xu et al. 49 introduced a novel Fitting Fuzzy Rough Set (FRS) model enriched with relative dependency complement mutual information. This model addresses challenges related to data distribution and precision enhancement of fuzzy information granules. They utilized relative distance to mitigate the influence of data distribution on fuzzy similarity relationships and introduced a fitting fuzzy neighborhood radius optimized for enhancing the precision of fuzzy information granules. Within this model, the authors conducted a comprehensive analysis of information uncertainty, introducing definitions of relative complement information entropy and formulating a multiview uncertainty measure based on relative dependency complement mutual information. This work significantly advances our understanding of managing information uncertainty within FRS models, making a valuable contribution to computational modeling and data analysis.

Jiang et al. 50 presented an innovative approach for multiattribute decision-making (MADM) rooted in PROMETHEE II methodologies. Building upon the NRS model, they introduce two additional variants of covering-based variable precision fuzzy rough sets (CVPFRSs) by applying fuzzy logical operators, specifically type-I CVPFRSs and type-II CVPFRSs. In the context of MADM, their method entails the selection of medicines using an algorithm that leverages the identified features.

Qu et al. 51 introduced the concept of Adaptive Neighborhood Rough Sets (ANRSs), aiming for effective integration of feature separation and linkage with classification. They utilize the mRMR-based Feature Selection Algorithm (FSRMI), demonstrating outstanding performance across various selected datasets. However, it’s worth noting that FSRMI may not consistently outperform other algorithms on all datasets.

Xu et al. 52 introduced the Fuzzy Neighborhood Joint Entropy Model (FNSIJE) for feature selection, leveraging fuzzy neighborhood self-information measures and joint entropy to capture combined feature information. FNSIJE comprehensively analyzes the neighborhood decision system, considering noise, uncertainty, and ambiguity. To improve classification performance, the authors devised a new forward search method. Experimental results demonstrated the effectiveness of FNSIJE-KS, efficiently selecting fewer features for both low-dimensional UCI datasets and high-dimensional gene datasets while maintaining optimal classification performance. This approach advances feature selection techniques in machine learning and data analysis.

In 53 , the authors introduced a novel multi-label feature selection method utilizing fuzzy NRS to optimize classification performance in multi-label fuzzy neighborhood decision systems. By combining the NRS and FRS models a Multi-Label Fuzzy NRS model is introduced. They devised a fuzzy neighborhood approximation accuracy metric and crafted a hybrid metric integrating fuzzy neighborhood approximate accuracy with fuzzy neighborhood conditional entropy for attribute importance evaluation. Rigorous evaluation of their methods across ten diverse multi-label datasets showcased significant progress in multi-label feature selection techniques, promising enhanced classification performance in complex multi-label scenarios.

Sanget et al. 54 introduced the Fuzzy Dominance Neighborhood Rough Set (NRS) model for Interval-Valued Ordered Decision Systems (IvODS), along with a robust conditional entropy measure to assess monotonic consistency within IvODS. They also presented two incremental feature selection algorithms. Experimental results on nine publicly available datasets showcased the robustness of their proposed metric and the effectiveness and efficiency of the incremental algorithms, particularly in dynamic IvODS updates. This research significantly advances the application of fuzzy dominance NRS models in IvODS scenarios, providing valuable insights for data analysis and decision-making processes.

Zheng et al. 55 generalized the FRSs using axiomatic and constructive approaches. A pair of dual generalized fuzzy approximation operators is defined using arbitrary fuzzy relation in the constructive approach. Different classes of FRSs are characterized using different sets of axioms. The postulates governing fuzzy approximation operators ensure the presence of specific categories of fuzzy relations yielding identical operators. Using a generalized FRS model, Hu et al. 18 introduced an efficient algorithm for hybrid attribute reduction based on fuzzy relations constructing a forward greedy algorithm for hybrid attribute reduction resulting in optimal classification performance with lesser selected features and higher accuracy. Considering the similarity between two objects, Wang et al. 36 redefine fuzzy upper and lower approximations. The existing concepts of knowledge reduction are extending fuzzy environment resulting in a heuristic algorithm to learn fuzzy rules.

Gogoi et al. 56 use rough set theory for generating decision rules from inconsistent data. The proposed scheme uses indiscernibility relation to find inconsistencies in the data generating minimized and non-redundant rules using lower and upper approximations. The proposed scheme is based on the LEM2 algorithm 57 which performs the local covering option for generating minimum and non-redundant sets of classification rules and does not consider the global covering. The scheme is evaluated on a variety of data sets from the UCI Machine Learning Repository. All these data sets are either categorical or numerical having variable feature spaces. The proposed scheme performs consistently better for categorical data sets, as it is designed to handle inconsistencies in the data having at least one inconsistency. Results show that the proposed scheme generates minimized rule without reducing the feature space unlike other schemes, which compromise the feature space.

In 58 , the authors introduced a novel NRS model to address attribute reduction in noisy systems with heterogeneous attributes. This model extends traditional NRS by incorporating tolerance neighborhood relation and probabilistic theory, resulting in more comprehensive information granules. It evaluates the significance of heterogeneous attributes by considering neighborhood dependency and aims to maximize classification consistency within selected feature spaces. The feature space reduction algorithm employs an incremental approach, adding features while preserving maximal dependency in each round and halting when a new feature no longer increases dependency. This approach selects fewer features than other methods while achieving significantly improved classification performance, demonstrating its effectiveness in attribute reduction for noisy systems.

Zhu et al. 59 propose a fault tolerance scheme combining kernel method, NRS, and statistical features to adaptively select sensitive features. They employ a Gaussian kernel function with NRS to map fault data to a high-dimensional space. Their feature selection algorithm utilizes the hyper-sphere radius in high-dimensional feature space as the neighborhood value, selecting features based on significance measure regardless of the classification algorithm. A wrapper deploys a classification algorithm to evaluate selected features, choosing a subset for optimal classification. Experimental results demonstrate precise determination of the neighborhood value by mapping data into a high-dimensional space using the kernel function and hyper-sphere radius. This methodology proficiently selects sensitive fault features, diagnoses fault types, and identifies fault degrees in rolling bearing datasets.

A neighborhood covering a rough set model for the fuzziness of decision systems is proposed that solves the problem of hybrid decision systems having both fuzzy and numerical attributes 60 . The fuzzy neighborhood relation measures the indiscernibility relation and approximates the universe space using information granules, which deal with fuzzy attributes directly. The experimental results evaluate the influence of neighborhood operator size on the accuracy and attribute reduction of fuzzy neighborhood rough sets. The attribute reduction increases with the increase in the threshold size. A feature will not distinguish any samples and cannot reduce attributes if the neighborhood operator exceeds a certain value.

Hou et al. 61 applied NRS reduction techniques to cancer molecular classification, focusing on gene expression profiles. Their method introduced a novel perspective by using gene occurrence probability in selected gene subsets to indicate tumor classification efficacy. Unlike traditional methods, it integrated both Filters and Wrappers, enhancing classification performance while being computationally efficient. Additionally, they developed an ensemble classifier to improve accuracy and stability without overfitting. Experimental results showed the method achieved high prediction accuracy, identified potential cancer biomarkers, and demonstrated stability in performance.

Table  2 gives a comparison of existing rough set-based schemes for quantitative and qualitative analysis. The comparative parameters include handling hybrid data, generalized NRS, attribute reduction, classification, and accuracy rate. Most of the existing schemes do not handle hybrid data sets without discretization resulting in information loss and a lack of practical meanings. Another parameter to evaluate the effectiveness of the existing scheme is the ability to adapt the threshold value according to the given data sets. Most of the schemes do not adapt threshold values for neighborhood approximation space resulting in variable accuracy rates for different datasets. The end-user has to adjust the value of the threshold for different datasets without understanding its impact in terms of overfitting. Selecting a large threshold value will result in more global rules resulting in poor accuracy. There needs to be a mechanism to adaptively choose the value of the threshold considering both the global and local information without compromising on the accuracy rate. The schemes are also evaluated for their ability to attribute reduction using NRS. This can greatly improve processing time and accuracy by not considering insignificant attributes. The comparative analysis shows that most of the NRS-based existing schemes perform better than many other well-known schemes in terms of accuracy. Most of these schemes have a higher accuracy rate than CART, C4.5, and k NN. This makes the NRS-based schemes a choice for attribute reduction and classification.

Adaptive neighborhood rough set model

The detailed analysis of existing techniques highlights the need for a generalized NRS-based classification technique to handle both categorical and numerical data. The proposed NRS-based techniques not only handle the hybrid information granules but also dynamically select the threshold \(\delta \) producing optimal results with a high accuracy rate. The proposed scheme considers a hybrid tuple \(HIS=\langle U_h,\ Q_h,\ V,\ f \rangle \) , where \(U_h\) is nonempty set of hybrid records \(\{x_{h1},\ x_{h2},\ x_{h3},\ \ldots ,\ x_{hn}\}\) , \(Q_h=\left\{ q_{h1},\ q_{h2},\ \ q_{h3},\ \ldots \,\ q_{hn}\right\} \) is the non-empty set of hybrid features. \( V_{q_h}\) is the domain of attribute \(q_h\) and \(V=\ \cup _{q_h\in Q_h}V_{q_h}\) , and \(f=U_h\ x\ Q_h\rightarrow V\) is a total function such \(f\left( x_h,q_h\right) \in V_{q_h}\) for each \(q_h\in Q_h, x_h\in U_h\) , called information function. \(\langle U_h,\ Q_h,\ V,\ f\rangle \) is also known as a decision table if \(Q_h=C_h\cup D\) , where \(C_h\) is the set of hybrid condition attributes and D is the decision attribute.

A neighborhood relation N is calculated using this set of hybrid samples \(U_h\) creating the neighborhood approximation space \(\langle U_h,\ N\rangle \) which contains information granules \( \left\{ \delta ({x_h}_i)\big |{x_h}_i\in U_h\right\} \) based on some distance function \(\Delta \) . For an arbitrary sample \({x_h}_i\in U_h\) and \(B \subseteq C_h\) , the neighborhood \(\delta _B({x_h}_i)\) of \({x_h}_i\) in the subspace B is defined as \(\delta _B\left( {x_h}_i\right) =\{{x_h}_j\left| {x_h}_j\right. \in U_h,\ \Delta B(x_i,x_j) \le \delta \}\) . The scheme proposes a new hybrid distance function to handle both the categorical and numerical features in an approximation space.

The proposed distance function uses Euclidean distance for numerical features and Levenshtein distance for categorical features. The distance function also takes care of the significant features calculating weighted distance for both the categorical and numerical features. The proposed algorithm dynamically selects the distance function at the run time. The use of Levenshtein distance for categorical features provides precise distance for optimal neighborhood approximation space providing better results. Existing techniques add 1 to distance if two strings do not match in calculating the distance for categorical data and add 0 otherwise. This may not result in a realistic neighborhood approximation space.

The neighborhood size depends on the threshold \(\delta \) . The neighborhood will contain more samples if \(\delta \) is greater and results in more rules not considering the local information data. The accuracy rate of the NRS greatly depends on the selection of threshold values. The proposed scheme dynamically calculates the threshold value for any given dataset considering both local and global information. The threshold calculation formula is given below where \({min}_D\) is the minimum distance between the set of training samples and the test sample containing local information and \(R_D\) is the range of distance between the set of training samples and the test sample containing the global information.

The proposed scheme then calculates the lower and upper approximations given a neighborhood space \(\langle U_h, N\rangle \) for \(X \subseteq U_h\) , the lower and upper approximations of X are defined as:

Given a hybrid neighborhood decision table \(HNDT=\langle U_h,\ C_h\cup \ D, V, f\rangle \) , \(\{ X_{h1},X_{h2},\ \ldots ,\ X_{hN} \}\) are the sample hybrid subjects with decision 1 to N , \(\delta _B\left( x_{hi}\right) \) is the information granules generated by attributes \(B \subseteq C_h\) , then the lower and upper approximation is defined as:

and the boundary region of D is defined as:

The lower and upper approximation spaces are the set of rules, which are used to classify a test sample. A test sample forms its neighborhood using a lower approximation having all the rules with a distance less than a dynamically calculated threshold value. The majority voting is used in the neighborhood of a test sample to decide the class of a test sample. K-fold cross-validation is used to measure the accuracy of the proposed scheme where the value k is 10. The algorithm 1 of the proposed scheme has a time complexity of \(O(nm^{2})\) where n is the number of clients and m is the size of the categorial data.

Instrumentation

The proposed generalized rough set model has been rigorously assessed through the development of a testbed designed for the classification of Parkinson’s patients. It has also been subjected to testing using various standard datasets sourced from the University of California at Irvine machine learning data repository 63 . This research underscores the increasing significance of biomedical engineering in healthcare, particularly in light of the growing prevalence of Parkinson’s disease, which ranks as the second most common neurodegenerative condition, impacting over 1% of the population aged 65 and above 64 . The disease manifests through distinct motor symptoms like resting tremors, bradykinesia (slowness of movement), rigidity, and poor balance, with medication-related side effects such as wearing off and dyskinesias 65 .

In this study, to address the need for a reliable quantitative method for assessing motor complications in Parkinson’s patients, the data collection process involves utilizing a home-monitoring system equipped with wireless wearable sensors. These sensors were specifically deployed to closely monitor Parkinson’s patients with severe tremors in real time. It’s important to note that all patients involved in the study were clinically diagnosed with Parkinson’s disease. Additionally, before data collection, proper consent was obtained from each participant, and the study protocol was approved by the ethical committee of our university. The data collected from these sensors is then analyzed, yielding reliable quantitative information that can significantly aid clinical decision-making within both routine patient care and clinical trials of innovative treatments.

Testbed for Parkinson’s patients.

Figure  1 illustrates a real-time Testbed designed for monitoring Parkinson’s patients. This system utilizes a tri-axial accelerometer to capture three signals, one for each axis \((x,\ y,\ and\ z)\) , resulting in a total of 18 channels of data. The sensors employed in this setup employ ZigBee (IEEE 802.15.4 infrastructure) protocol to transmit data to a computer at a sampling rate of 62.5 Hz. To ensure synchronization of the transmitted signals, a transition protocol is applied. These data packets are received through the Serial Forwarder using the TinyOS platform ( http://www.tinyos.net ). The recorded acceleration data is represented as digital signals and can be visualized on an oscilloscope. The frequency domain data is obtained by applying the Fast Fourier Transform (FFT) to the signal, resulting in an ARFF file format that is then employed for classification purposes. The experimental flowchart is shown in Fig.  2 .

Experimental flowchart.

The real-time testbed includes various components to capture data using the Unified Parkinson’s Disease Rating Scale (UPDRS). TelosB MTM-CM5000-MSP and MTM-CM3000-MSP sensors are used to send and receive radio signals from the sensor to the PC. These sensors are based on an open-source TelosB/Tmote Sky platform, designed and developed by the University of California, Berkeley.

TelosB sensor uses the IEEE 802.15.4 wireless structure and the embedded sensors can measure temperature, relative humidity, and light. In CM3000, the USB connector is replaced with an ERNI connector that is compatible with interface modules. Also, the Hirose 51-pin connector makes this more versatile as it can be attachable to any sensor board family, and the coverage area is increased using SMA design by a 5dBi external antenna 66 . These components can be used for a variety of applications such as low-power Wireless Sensor Networks (WSN) platforms, network monitoring, and environment monitoring systems.

MTS-EX1000 sensor board is used for the amplification of the voltage/current value from the accelerometer. The EX1000 is an attachable board that supports the CMXXXX series of wireless sensors network Motes (Hirose 51-pin connector). The basic functionality of EX1000 is to connect the external sensors with CMXX00 communication modules to enhance the mote’s I/O capability and support different kinds of sensors based on the sensor type and its output signal. ADXL-345 Tri-accelerometer sensor is used to calculate body motion along x, y, and z-axis relative to gravity. It is a small, thin, low-power, 3-axis accelerometer that calculates high resolution (13-bit) measurements at up to ±16g. Its digital output, in 16-bit twos complement format, is accessible through either an SPI (3- or 4-wire) or I2C digital interface. A customized main circuit board is used having a programmed IC, registers, and transistors. Its basic functionality is to convert the digital data, accessed through the ADXL-345 sensor, into analog form and send it to MTS1000.

Result and discussion

The proposed generalized and ANRS is evaluated against different data sets taken from the machine learning data repository, at the University of California at Irvine. In addition to these common data sets, a real-time Testbed for Parkinson’s patients is also used to evaluate the proposed scheme. The hybrid data of 500 people was collected using the Testbed for Parkinson’s patients including 10 Parkinson’s patients, 20 people have abnormal and uncontrolled hand movements, and the rest of the samples were taken approximating the hand movements of Parkinson’s patients. The objective of this evaluation is to compare the accuracy rate of the proposed scheme with CART, k NN, and SVM having both simple and complex datasets containing numerical and hybrid features respectively. The results also demonstrate the selection of radius r for dynamically calculating the threshold value.

Table  3 provides the details of the datasets used for the evaluation of the proposed scheme including the training and test ratio used for evaluation in addition to data type, total number of instances, total feature, a feature considered for evaluation, and number of classes. The hybrid datasets are also selected to evaluate to performance of the proposed scheme against the hybrid feature space without discretization preventing information loss.

The accuracy of the NRS is greatly dependent on the threshold value. Most of the existing techniques do not dynamically adapt the threshold \(\delta \) value for different hybrid datasets. This results in the variant of NRS suitable for specific datasets with different threshold values. A specific threshold value may produce better results for one dataset and poor results for others requiring a more generic threshold value catering to different datasets with optimal results. The proposed scheme introduces an adaptable threshold calculation mechanism to achieve optimal results regardless of the datasets under evaluation. The radius value plays a pivotal role in forming a neighborhood, as the threshold values consider both the local and global information of the NRS to calculate neighborhood approximation space. Table  4 shows the accuracy rate having different values of the radius of the NRS. The proposed threshold mechanism provides better results for all datasets if the value of the radius is 0.002. Results also show that assigning no weight to the radius produces poor results, as it will then only consider the local information for the approximation space. Selecting other weights for radius may produce better results for one dataset but not for all datasets.

Table  5 presents the comparative analysis of the proposed scheme with k NN, Naive Bayes, and C45. The results show that the proposed scheme performs well against other well-known techniques for both the categorical and numerical features space. Naive Bayes and C45 also result in information loss, as these techniques cannot process the hybrid data. So the proposed scheme handles the hybrid data without compromising on the information completeness producing acceptable results. K-fold cross-validation is used to measure the accuracy of the proposed scheme. Each dataset is divided into 10 subsets to use one of the K subsets as the test set and the other K-1 subsets as training sets. Then the average accuracy of all K trials is computed with the advantage of having results regardless of the dataset division.

Conclusion and future work

This work evaluates the existing NRS-based scheme for handling hybrid data sets i.e. numerical and categorical features. The comparative analysis of existing NRS-based schemes shows that there is a need for a generic NRS-based approach to adapt the threshold selection forming neighborhood approximation space. A generalized and ANRS-based scheme is proposed to handle both the categorical and numerical features avoiding information loss and lack of practical meanings. The proposed scheme uses a Euclidean and Levenshtein distance to calculate the upper and lower approximation of NRS for numerical and categorical features respectively. Euclidean and Levenshtein distances have been modified to handle the impact of outliers in calculating the approximation spaces. The proposed scheme defines an adaptive threshold mechanism for calculating neighborhood approximation space regardless of the data set under consideration. A Testbed is developed for real-time behavioral analysis of Parkinson’s patients evaluating the effectiveness of the proposed scheme. The evaluation results show that the proposed scheme provides better accuracy than k NN, C4.5, and Naive Bayes for both the categorical and numerical feature space achieving 95% accuracy on the Parkinson’s dataset. The proposed scheme will be evaluated against the hybrid data set having more than two classes in future work. Additionally, in future work, we aim to explore the following areas; (i) conduct longitudinal studies to track the progression of Parkinson’s disease over time, allowing for a deeper understanding of how behavioral patterns evolve and how interventions may impact disease trajectory, (ii) explore the integration of additional data sources, such as genetic data, imaging studies, and environmental factors, to provide a more comprehensive understanding of Parkinson’s disease etiology and progression, (iii) validate our findings in larger and more diverse patient populations and investigate the feasibility of implementing our proposed approach in clinical settings to support healthcare providers in decision-making processes, (iv) investigate novel biomarkers or physiological signals that may provide additional insights into Parkinson’s disease progression and motor complications, potentially leading to the development of new diagnostic and monitoring tools, and (v) conduct patient-centered outcomes research to better understand the impact of Parkinson’s disease on patients’ quality of life, functional abilities, and overall well-being, with a focus on developing personalized treatment approaches.

Data availability

The datasets used in this study are publicly available at the following links:

Bupa 67 : https://doi.org/10.24432/C54G67 , Sonar 68 : https://doi.org/10.24432/C5T01Q , Mammographic Mass 69 : https://doi.org/10.24432/C53K6Z , Haberman’s Survival 70 : https://doi.org/10.24432/C5XK51 , Credit-g 71 : https://doi.org/10.24432/C5NC77 , Lymmography 73 : https://doi.org/10.24432/C54598 , Splice 74 : https://doi.org/10.24432/C5M888 , Optdigits 75 : https://doi.org/10.24432/C50P49 , Pendigits 76 : https://doi.org/10.1137/1.9781611972825.9 , Pageblocks 77 : https://doi.org/10.24432/C5J590 , Statlog 78 : https://doi.org/10.24432/C55887 , Magic04 79 : https://doi.org/10.1609/aaai.v29i1.9277 .

Gaber, M. M. Scientific Data Mining and Knowledge Discovery Vol. 1 (Springer, 2009).

Google Scholar  

Hajirahimi, Z. & Khashei, M. Weighting approaches in data mining and knowledge discovery: A review. Neural Process. Lett. 55 , 10393–10438 (2023).

Article   Google Scholar  

Kantardzic, M. Data Mining: Concepts, Models, Methods, and Algorithms (Wiley, 2011).

Book   Google Scholar  

Shu, X. & Ye, Y. Knowledge discovery: Methods from data mining and machine learning. Soc. Sci. Res. 110 , 102817 (2023).

Article   PubMed   Google Scholar  

Tan, P.-N., Steinbach, M. & Kumar, V. Introduction to Data Mining (Pearson Education India, 2016).

Khan, S. & Shaheen, M. From data mining to wisdom mining. J. Inf. Sci. 49 , 952–975 (2023).

Engelbrecht, A. P. Computational Intelligence: An Introduction (Wiley, 2007).

Bhateja, V., Yang, X.-S., Lin, J.C.-W. & Das, R. Evolution in computational intelligence. In Evolution (Springer, 2023).

Wei, W., Liang, J. & Qian, Y. A comparative study of rough sets for hybrid data. Inf. Sci. 190 , 1–16 (2012).

Article   ADS   MathSciNet   Google Scholar  

Kumari, N. & Acharjya, D. Data classification using rough set and bioinspired computing in healthcare applications—An extensive review. Multimedia Tools Appl. 82 , 13479–13505 (2023).

Martinez, A. M. & Kak, A. C. PCA versus LDA. IEEE Trans. Pattern Anal. Mach. Intell. 23 , 228–233 (2001).

Brereton, R. G. Principal components analysis with several objects and variables. J. Chemom. 37 (4), e3408 (2023).

Article   CAS   Google Scholar  

De, R. K., Basak, J. & Pal, S. K. Neuro-fuzzy feature evaluation with theoretical analysis. Neural Netw. 12 , 1429–1455 (1999).

Talpur, N. et al. Deep neuro-fuzzy system application trends, challenges, and future perspectives: A systematic survey. Artif. Intell. Rev. 56 , 865–913 (2023).

Jang, J.-S.R., Sun, C.-T. & Mizutani, E. Neuro-fuzzy and soft computing—A computational approach to learning and machine intelligence [book review]. IEEE Trans. Autom. Control 42 , 1482–1484 (1997).

Ouifak, H. & Idri, A. Application of neuro-fuzzy ensembles across domains: A systematic review of the two last decades (2000–2022). Eng. Appl. Artif. Intell. 124 , 106582 (2023).

Jung, T. & Kim, J. A new support vector machine for categorical features. Expert Syst. Appl. 229 , 120449 (2023).

Hu, Q., Xie, Z. & Yu, D. Hybrid attribute reduction based on a novel fuzzy-rough model and information granulation. Pattern Recognit. 40 , 3509–3521 (2007).

Article   ADS   Google Scholar  

Wang, P., He, J. & Li, Z. Attribute reduction for hybrid data based on fuzzy rough iterative computation model. Inf. Sci. 632 , 555–575 (2023).

Yeung, D. S., Chen, D., Tsang, E. C., Lee, J. W. & Xizhao, W. On the generalization of fuzzy rough sets. IEEE Trans. Fuzzy Syst. 13 , 343–361 (2005).

Gao, L., Yao, B.-X. & Li, L.-Q. L-fuzzy generalized neighborhood system-based pessimistic l-fuzzy rough sets and its applications. Soft Comput. 27 , 7773–7788 (2023).

Bhatt, R. B. & Gopal, M. On fuzzy-rough sets approach to feature selection. Pattern Recognit. Lett. 26 , 965–975 (2005).

Dubois, D. & Prade, H. Putting fuzzy sets and rough sets together. Intell. Decis. Support 23 , 203–232 (1992).

Jensen, R. & Shen, Q. Fuzzy-rough sets for descriptive dimensionality reduction. In 2002 IEEE World Congress on Computational Intelligence. 2002 IEEE International Conference on Fuzzy Systems. FUZZ-IEEE’02. Proceedings (Cat. No. 02CH37291) , vol. 1, 29–34 (IEEE, 2002).

Pedrycz, W. & Vukovich, G. Feature analysis through information granulation and fuzzy sets. Pattern Recognit. 35 , 825–834 (2002).

Jensen, R. & Shen, Q. Fuzzy-rough sets assisted attribute selection. IEEE Trans. Fuzzy Syst. 15 , 73–89 (2007).

Shen, Q. & Jensen, R. Selecting informative features with fuzzy-rough sets and its application for complex systems monitoring. Pattern Recognit. 37 , 1351–1363 (2004).

Wang, X., Tsang, E. C., Zhao, S., Chen, D. & Yeung, D. S. Learning fuzzy rules from fuzzy samples based on rough set technique. Inf. Sci. 177 , 4493–4514 (2007).

Article   MathSciNet   Google Scholar  

Wei, W., Liang, J., Qian, Y. & Wang, F. An attribute reduction approach and its accelerated version for hybrid data. In 2009 8th IEEE International Conference on Cognitive Informatics , 167–173 (IEEE, 2009).

Yin, T., Chen, H., Li, T., Yuan, Z. & Luo, C. Robust feature selection using label enhancement and \(\beta \) -precision fuzzy rough sets for multilabel fuzzy decision system. Fuzzy Sets Syst. 461 , 108462 (2023).

Yin, T. et al. Exploiting feature multi-correlations for multilabel feature selection in robust multi-neighborhood fuzzy \(\beta \) covering space. Inf. Fusion 104 , 102150 (2024).

Yin, T. et al. A robust multilabel feature selection approach based on graph structure considering fuzzy dependency and feature interaction. IEEE Trans. Fuzzy Syst. 31 , 4516–4528. https://doi.org/10.1109/TFUZZ.2023.3287193 (2023).

Huang, W., She, Y., He, X. & Ding, W. Fuzzy rough sets-based incremental feature selection for hierarchical classification. IEEE Trans. Fuzzy Syst. https://doi.org/10.1109/TFUZZ.2023.3300913 (2023).

Dong, L., Wang, R. & Chen, D. Incremental feature selection with fuzzy rough sets for dynamic data sets. Fuzzy Sets Syst. 467 , 108503 (2023).

Chakraborty, M. K. & Samanta, P. Fuzzy sets and rough sets: A mathematical narrative. In Fuzzy, Rough and Intuitionistic Fuzzy Set Approaches for Data Handling: Theory and Applications , 1–21 (Springer, 2023).

Wang, Z., Chen, H., Yuan, Z. & Li, T. Fuzzy-rough hybrid dimensionality reduction. Fuzzy Sets Syst. 459 , 95–117 (2023).

Xue, Z.-A., Jing, M.-M., Li, Y.-X. & Zheng, Y. Variable precision multi-granulation covering rough intuitionistic fuzzy sets. Granul. Comput. 8 , 577–596 (2023).

Akram, M., Nawaz, H. S. & Deveci, M. Attribute reduction and information granulation in pythagorean fuzzy formal contexts. Expert Systems Appl. 222 , 119794 (2023).

Hu, M., Guo, Y., Chen, D., Tsang, E. C. & Zhang, Q. Attribute reduction based on neighborhood constrained fuzzy rough sets. Knowl. Based Syst. 274 , 110632 (2023).

Zhang, C., Ding, J., Zhan, J., Sangaiah, A. K. & Li, D. Fuzzy intelligence learning based on bounded rationality in IOMT systems: A case study in Parkinson’s disease. IEEE Trans. Comput. Soc. Syst. 10 , 1607–1621. https://doi.org/10.1109/TCSS.2022.3221933 (2023).

Zhang, C. & Zhang, J. Three-way group decisions with incomplete spherical fuzzy information for treating Parkinson’s disease using IOMT devices. Wireless Communications and Mobile Computing , vol. 2022 (2022).

Jain, P., Tiwari, A. K. & Som, T. Improving financial bankruptcy prediction using oversampling followed by fuzzy rough feature selection via evolutionary search. In Computational Management: Applications of Computational Intelligence in Business Management , 455–471 (Springer, 2021).

Shreevastava, S., Singh, S., Tiwari, A. & Som, T. Different classes ratio and Laplace summation operator based intuitionistic fuzzy rough attribute selection. Iran. J. Fuzzy Syst. 18 , 67–82 (2021).

MathSciNet   Google Scholar  

Shreevastava, S., Tiwari, A. & Som, T. Feature subset selection of semi-supervised data: an intuitionistic fuzzy-rough set-based concept. In Proceedings of International Ethical Hacking Conference 2018: eHaCON 2018, Kolkata, India , 303–315 (Springer, 2019).

Tiwari, A. K., Nath, A., Subbiah, K. & Shukla, K. K. Enhanced prediction for observed peptide count in protein mass spectrometry data by optimally balancing the training dataset. Int. J. Pattern Recognit. Artif. Intell. 31 , 1750040 (2017).

Jain, P., Tiwari, A. K. & Som, T. An intuitionistic fuzzy bireduct model and its application to cancer treatment. Comput. Ind. Eng. 168 , 108124 (2022).

Yin, T., Chen, H., Yuan, Z., Li, T. & Liu, K. Noise-resistant multilabel fuzzy neighborhood rough sets for feature subset selection. Inf. Sci. 621 , 200–226 (2023).

Sang, B., Chen, H., Yang, L., Li, T. & Xu, W. Incremental feature selection using a conditional entropy based on fuzzy dominance neighborhood rough sets. IEEE Trans. Fuzzy Syst. 30 , 1683–1697 (2021).

Xu, J., Meng, X., Qu, K., Sun, Y. & Hou, Q. Feature selection using relative dependency complement mutual information in fitting fuzzy rough set model. Appl. Intell. 53 , 18239–18262 (2023).

Jiang, H., Zhan, J. & Chen, D. Promethee ii method based on variable precision fuzzy rough sets with fuzzy neighborhoods. Artif. Intell. Rev. 54 , 1281–1319 (2021).

Qu, K., Xu, J., Han, Z. & Xu, S. Maximum relevance minimum redundancy-based feature selection using rough mutual information in adaptive neighborhood rough sets. Appl. Intell. 53 , 17727–17746 (2023).

Xu, J., Yuan, M. & Ma, Y. Feature selection using self-information and entropy-based uncertainty measure for fuzzy neighborhood rough set. Complex Intell. Syst. 8 , 287–305 (2022).

Xu, J., Shen, K. & Sun, L. Multi-label feature selection based on fuzzy neighborhood rough sets. Complex Intell. Syst. 8 , 2105–2129 (2022).

Sang, B. et al. Feature selection for dynamic interval-valued ordered data based on fuzzy dominance neighborhood rough set. Knowl. Based Syst. 227 , 107223 (2021).

Wu, W.-Z., Mi, J.-S. & Zhang, W.-X. Generalized fuzzy rough sets. Inf. Sci. 151 , 263–282 (2003).

Gogoi, P., Bhattacharyya, D. K. & Kalita, J. K. A rough set-based effective rule generation method for classification with an application in intrusion detection. Int. J. Secur. Netw. 8 , 61–71 (2013).

Grzymala-Busse, J. W. Knowledge acquisition under uncertainty—A rough set approach. J. Intell. Robot. Syst. 1 , 3–16 (1988).

Jing, S. & She, K. Heterogeneous attribute reduction in noisy system based on a generalized neighborhood rough sets model. World Acad. Sci. Eng. Technol. 75 , 1067–1072 (2011).

Zhu, X., Zhang, Y. & Zhu, Y. Intelligent fault diagnosis of rolling bearing based on kernel neighborhood rough sets and statistical features. J. Mech. Sci. Technol. 26 , 2649–2657 (2012).

Zhao, B.-T. & Jia, X.-F. Neighborhood covering rough set model of fuzzy decision system. Int. J. Comput. Sci. Issues 10 , 51 (2013).

Hou, M.-L. et al. Neighborhood rough set reduction-based gene selection and prioritization for gene expression profile analysis and molecular cancer classification. J Biomed Biotechnol. 2010 , 726413 (2010).

Article   PubMed   PubMed Central   Google Scholar  

He, M.-X. & Qiu, D.-D. A intrusion detection method based on neighborhood rough set. TELKOMNIKA Indones. J. Electr. Eng. 11 , 3736–3741 (2013).

ADS   Google Scholar  

Newman, D. J., Hettich, S., Blake, C. L. & Merz, C. UCI repository of machine learning databases (1998).

Aarsland, D. et al. Parkinson disease-associated cognitive impairment. Nat. Rev. Dis. Primers 7 , 47 (2021).

Lang, A. E. & Lozano, A. M. Parkinson’s disease. N. Engl. J. Med. 339 , 1130–1143 (1998).

Article   CAS   PubMed   Google Scholar  

Engin, M. et al. The classification of human tremor signals using artificial neural network. Expert Syst. Appl. 33 , 754–761 (2007).

Liver Disorders. UCI Machine Learning Repository. https://doi.org/10.24432/C54G67 (1990).

Sejnowski, T. & Gorman, R. Connectionist bench (sonar, mines vs. rocks). UCI Machine Learning Repository. https://doi.org/10.24432/C5T01Q

Elter, M. Mammographic Mass. UCI Machine Learning Repository. https://doi.org/10.24432/C53K6Z (2007).

Haberman, S. Haberman’s Survival. UCI Machine Learning Repository. https://doi.org/10.24432/C5XK51 (1999).

Hofmann, H. Statlog (German Credit Data). UCI Machine Learning Repository. https://doi.org/10.24432/C5NC77 (1994).

Kubat, M., Holte, R. C. & Matwin, S. Machine learning for the detection of oil spills in satellite radar images. Mach. Learn. 30 , 195–215 (1998).

Zwitter, M. & Soklic, M. Lymphography. UCI Machine Learning Repository. https://doi.org/10.24432/C54598 (1988).

Molecular Biology (Splice-junction Gene Sequences). UCI Machine Learning Repository. https://doi.org/10.24432/C5M888 (1992).

Alpaydin, E. & Kaynak, C. Optical Recognition of Handwritten Digits. UCI Machine Learning Repository. https://doi.org/10.24432/C50P49 (1998).

Schubert, E., Wojdanowski, R., Zimek, A. & Kriegel, H.-P. On evaluation of outlier rankings and outlier scores. In Proceedings of the 2012 SIAM International Conference on Data Mining , 1047–1058 (SIAM, 2012).

Malerba, D. Page Blocks Classification. UCI Machine Learning Repository. https://doi.org/10.24432/C5J590 (1995).

Srinivasan, A. Statlog (Landsat Satellite). UCI Machine Learning Repository. https://doi.org/10.24432/C55887 (1993).

Rossi, R. A. & Ahmed, N. K. The network data repository with interactive graph analytics and visualization. In AAAI (2015).

Download references

Acknowledgements

This research was funded by the European University of Atlantic.

Author information

Authors and affiliations.

Department of Computer Science, COMSATS University Islamabad, Lahore Campus, Lahore, 54000, Pakistan

Imran Raza, Muhammad Hasan Jamal, Rizwan Qureshi & Abdul Karim Shahid

Universidad Europea del Atlántico, Isabel Torres 21, 39011, Santander, Spain

Angel Olider Rojas Vistorte

Universidad Internacional Iberoamericana Campeche, 24560, Campeche, Mexico

Universidade Internacional do Cuanza, Cuito, Bié, Angola

Department of Information and Communication Engineering, Yeungnam University, Gyeongsan-si, Gyeongsangbuk-do, 38541, South Korea

Md Abdus Samad & Imran Ashraf

You can also search for this author in PubMed   Google Scholar

Contributions

Imran Raza: Conceptualization, Formal analysis, Writing—original draft; Muhammad Hasan Jamal: Conceptualization, Data curation, Writing—original draft; Rizwan Qureshi: Data curation, Formal analysis, Methodology; Abdul Karim Shahid: Project administration, Software, Visualization; Angel Olider Rojas Vistorte: Funding acquisition, Investigation, Project administration; Md Abdus Samad: Investigation, Software, Resources; Imran Ashraf: Supervision, Validation, Writing —review and editing. All authors reviewed the manuscript and approved it.

Corresponding authors

Correspondence to Md Abdus Samad or Imran Ashraf .

Ethics declarations

Competing interests.

The authors declare no competing interests.

Additional information

Publisher's note.

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Open Access This article is licensed under a Creative Commons Attribution 4.0 International License, which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if changes were made. The images or other third party material in this article are included in the article’s Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article’s Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit http://creativecommons.org/licenses/by/4.0/ .

Reprints and permissions

About this article

Cite this article.

Raza, I., Jamal, M.H., Qureshi, R. et al. Adaptive neighborhood rough set model for hybrid data processing: a case study on Parkinson’s disease behavioral analysis. Sci Rep 14 , 7635 (2024). https://doi.org/10.1038/s41598-024-57547-4

Download citation

Received : 01 October 2023

Accepted : 19 March 2024

Published : 01 April 2024

DOI : https://doi.org/10.1038/s41598-024-57547-4

Share this article

Anyone you share the following link with will be able to read this content:

Sorry, a shareable link is not currently available for this article.

Provided by the Springer Nature SharedIt content-sharing initiative

By submitting a comment you agree to abide by our Terms and Community Guidelines . If you find something abusive or that does not comply with our terms or guidelines please flag it as inappropriate.

Quick links

• Explore articles by subject
• Guide to authors
• Editorial policies

Sign up for the Nature Briefing newsletter — what matters in science, free to your inbox daily.

• Open access
• Published: 22 April 2024

Artificial intelligence and medical education: application in classroom instruction and student assessment using a pharmacology & therapeutics case study

• Kannan Sridharan 1 &
• Reginald P. Sequeira 1  

BMC Medical Education volume  24 , Article number:  431 ( 2024 ) Cite this article

511 Accesses

1 Altmetric

Metrics details

Artificial intelligence (AI) tools are designed to create or generate content from their trained parameters using an online conversational interface. AI has opened new avenues in redefining the role boundaries of teachers and learners and has the potential to impact the teaching-learning process.

In this descriptive proof-of- concept cross-sectional study we have explored the application of three generative AI tools on drug treatment of hypertension theme to generate: (1) specific learning outcomes (SLOs); (2) test items (MCQs- A type and case cluster; SAQs; OSPE); (3) test standard-setting parameters for medical students.

Analysis of AI-generated output showed profound homology but divergence in quality and responsiveness to refining search queries. The SLOs identified key domains of antihypertensive pharmacology and therapeutics relevant to stages of the medical program, stated with appropriate action verbs as per Bloom’s taxonomy. Test items often had clinical vignettes aligned with the key domain stated in search queries. Some test items related to A-type MCQs had construction defects, multiple correct answers, and dubious appropriateness to the learner’s stage. ChatGPT generated explanations for test items, this enhancing usefulness to support self-study by learners. Integrated case-cluster items had focused clinical case description vignettes, integration across disciplines, and targeted higher levels of competencies. The response of AI tools on standard-setting varied. Individual questions for each SAQ clinical scenario were mostly open-ended. The AI-generated OSPE test items were appropriate for the learner’s stage and identified relevant pharmacotherapeutic issues. The model answers supplied for both SAQs and OSPEs can aid course instructors in planning classroom lessons, identifying suitable instructional methods, establishing rubrics for grading, and for learners as a study guide. Key lessons learnt for improving AI-generated test item quality are outlined.

Conclusions

AI tools are useful adjuncts to plan instructional methods, identify themes for test blueprinting, generate test items, and guide test standard-setting appropriate to learners’ stage in the medical program. However, experts need to review the content validity of AI-generated output. We expect AIs to influence the medical education landscape to empower learners, and to align competencies with curriculum implementation. AI literacy is an essential competency for health professionals.

Peer Review reports

Artificial intelligence (AI) has great potential to revolutionize the field of medical education from curricular conception to assessment [ 1 ]. AIs used in medical education are mostly generative AI large language models that were developed and validated based on billions to trillions of parameters [ 2 ]. AIs hold promise in the incorporation of history-taking, assessment, diagnosis, and management of various disorders [ 3 ]. While applications of AIs in undergraduate medical training are being explored, huge ethical challenges remain in terms of data collection, maintaining anonymity, consent, and ownership of the provided data [ 4 ]. AIs hold a promising role amongst learners because they can deliver a personalized learning experience by tracking their progress and providing real-time feedback, thereby enhancing their understanding in the areas they are finding difficult [ 5 ]. Consequently, a recent survey has shown that medical students have expressed their interest in acquiring competencies related to the use of AIs in healthcare during their undergraduate medical training [ 6 ].

Pharmacology and Therapeutics (P & T) is a core discipline embedded in the undergraduate medical curriculum, mostly in the pre-clerkship phase. However, the application of therapeutic principles forms one of the key learning objectives during the clerkship phase of the undergraduate medical career. Student assessment in pharmacology & therapeutics (P&T) is with test items such as multiple-choice questions (MCQs), integrated case cluster questions, short answer questions (SAQs), and objective structured practical examination (OSPE) in the undergraduate medical curriculum. It has been argued that AIs possess the ability to communicate an idea more creatively than humans [ 7 ]. It is imperative that with access to billions of trillions of datasets the AI platforms hold promise in playing a crucial role in the conception of various test items related to any of the disciplines in the undergraduate medical curriculum. Additionally, AIs provide an optimized curriculum for a program/course/topic addressing multidimensional problems [ 8 ], although robust evidence for this claim is lacking.

The existing literature has evaluated the knowledge, attitude, and perceptions of adopting AI in medical education. Integration of AIs in medical education is the need of the hour in all health professional education. However, the academic medical fraternity facing challenges in the incorporation of AIs in the medical curriculum due to factors such as inadequate grounding in data analytics, lack of high-quality firm evidence favoring the utility of AIs in medical education, and lack of funding [ 9 ]. Open-access AI platforms are available free to users without any restrictions. Hence, as a proof-of-concept, we chose to explore the utility of three AI platforms to identify specific learning objectives (SLOs) related to pharmacology discipline in the management of hypertension for medical students at different stages of their medical training.

Study design and ethics

The present study is observational, cross-sectional in design, conducted in the Department of Pharmacology & Therapeutics, College of Medicine and Medical Sciences, Arabian Gulf University, Kingdom of Bahrain, between April and August 2023. Ethical Committee approval was not sought given the nature of this study that neither had any interaction with humans, nor collection of any personal data was involved.

Study procedure

We conducted the present study in May-June 2023 with the Poe© chatbot interface created by Quora© that provides access to the following three AI platforms:

Sage Poe [ 10 ]: A generative AI search engine developed by Anthropic © that conceives a response based on the written input provided. Quora has renamed Sage Poe as Assistant © from July 2023 onwards.

Claude-Instant [ 11 ]: A retrieval-based AI search engine developed by Anthropic © that collates a response based on pre-written responses amongst the existing databases.

ChatGPT version 3.5 [ 12 ]: A generative architecture-based AI search engine developed by OpenAI © trained on large and diverse datasets.

We queried the chatbots to generate SLOs, A-type MCQs, integrated case cluster MCQs, integrated SAQs, and OSPE test items in the domain of systemic hypertension related to the P&T discipline. Separate prompts were used to generate outputs for pre-clerkship (preclinical) phase students, and at the time of graduation (before starting residency programs). Additionally, we have also evaluated the ability of these AI platforms to estimate the proportion of students correctly answering these test items. We used the following queries for each of these objectives:

Specific learning objectives

Can you generate specific learning objectives in the pharmacology discipline relevant to undergraduate medical students during their pre-clerkship phase related to anti-hypertensive drugs?

Can you generate specific learning objectives in the pharmacology discipline relevant to undergraduate medical students at the time of graduation related to anti-hypertensive drugs?

A-type MCQs

In the initial query used for A-type of item, we specified the domains (such as the mechanism of action, pharmacokinetics, adverse reactions, and indications) so that a sample of test items generated without any theme-related clutter, shown below:

Write 20 single best answer MCQs with 5 choices related to anti-hypertensive drugs for undergraduate medical students during the pre-clerkship phase of which 5 MCQs should be related to mechanism of action, 5 MCQs related to pharmacokinetics, 5 MCQs related to adverse reactions, and 5 MCQs should be related to indications.

The MCQs generated with the above search query were not based on clinical vignettes. We queried again to generate MCQs using clinical vignettes specifically because most medical schools have adopted problem-based learning (PBL) in their medical curriculum.

Write 20 single best answer MCQs with 5 choices related to anti-hypertensive drugs for undergraduate medical students during the pre-clerkship phase using a clinical vignette for each MCQ of which 5 MCQs should be related to the mechanism of action, 5 MCQs related to pharmacokinetics, 5 MCQs related to adverse reactions, and 5 MCQs should be related to indications.

We attempted to explore whether AI platforms can provide useful guidance on standard-setting. Hence, we used the following search query.

Can you do a simulation with 100 undergraduate medical students to take the above questions and let me know what percentage of students got each MCQ correct?

Integrated case cluster MCQs

Write 20 integrated case cluster MCQs with 2 questions in each cluster with 5 choices for undergraduate medical students during the pre-clerkship phase integrating pharmacology and physiology related to systemic hypertension with a case vignette.

Write 20 integrated case cluster MCQs with 2 questions in each cluster with 5 choices for undergraduate medical students during the pre-clerkship phase integrating pharmacology and physiology related to systemic hypertension with a case vignette. Please do not include ‘none of the above’ as the choice. (This modified search query was used because test items with ‘None of the above’ option were generated with the previous search query).

Write 20 integrated case cluster MCQs with 2 questions in each cluster with 5 choices for undergraduate medical students at the time of graduation integrating pharmacology and physiology related to systemic hypertension with a case vignette.

Integrated short answer questions

Write a short answer question scenario with difficult questions based on the theme of a newly diagnosed hypertensive patient for undergraduate medical students with the main objectives related to the physiology of blood pressure regulation, risk factors for systemic hypertension, pathophysiology of systemic hypertension, pathological changes in the systemic blood vessels in hypertension, pharmacological management, and non-pharmacological treatment of systemic hypertension.

Write a short answer question scenario with moderately difficult questions based on the theme of a newly diagnosed hypertensive patient for undergraduate medical students with the main objectives related to the physiology of blood pressure regulation, risk factors for systemic hypertension, pathophysiology of systemic hypertension, pathological changes in the systemic blood vessels in hypertension, pharmacological management, and non-pharmacological treatment of systemic hypertension.

Write a short answer question scenario with questions based on the theme of a newly diagnosed hypertensive patient for undergraduate medical students at the time of graduation with the main objectives related to the physiology of blood pressure regulation, risk factors for systemic hypertension, pathophysiology of systemic hypertension, pathological changes in the systemic blood vessels in hypertension, pharmacological management, and non-pharmacological treatment of systemic hypertension.

Can you generate 5 OSPE pharmacology and therapeutics prescription writing exercises for the assessment of undergraduate medical students at the time of graduation related to anti-hypertensive drugs?

Can you generate 5 OSPE pharmacology and therapeutics prescription writing exercises containing appropriate instructions for the patients for the assessment of undergraduate medical students during their pre-clerkship phase related to anti-hypertensive drugs?

Can you generate 5 OSPE pharmacology and therapeutics prescription writing exercises containing appropriate instructions for the patients for the assessment of undergraduate medical students at the time of graduation related to anti-hypertensive drugs?

Both authors independently evaluated the AI-generated outputs, and a consensus was reached. We cross-checked the veracity of answers suggested by AIs as per the Joint National Commission Guidelines (JNC-8) and Goodman and Gilman’s The Pharmacological Basis of Therapeutics (2023), a reference textbook [ 13 , 14 ]. Errors in the A-type MCQs were categorized as item construction defects, multiple correct answers, and uncertain appropriateness to the learner’s level. Test items in the integrated case cluster MCQs, SAQs and OSPEs were evaluated with the Preliminary Conceptual Framework for Establishing Content Validity of AI-Generated Test Items based on the following domains: technical accuracy, comprehensiveness, education level, and lack of construction defects (Table  1 ). The responses were categorized as complete and deficient for each domain.

The pre-clerkship phase SLOs identified by Sage Poe, Claude-Instant, and ChatGPT are listed in the electronic supplementary materials 1 – 3 , respectively. In general, a broad homology in SLOs generated by the three AI platforms was observed. All AI platforms identified appropriate action verbs as per Bloom’s taxonomy to state the SLO; action verbs such as describe, explain, recognize, discuss, identify, recommend, and interpret are used to state the learning outcome. The specific, measurable, achievable, relevant, time-bound (SMART) SLOs generated by each AI platform slightly varied. All key domains of antihypertensive pharmacology to be achieved during the pre-clerkship (pre-clinical) years were relevant for graduating doctors. The SLOs addressed current JNC Treatment Guidelines recommended classes of antihypertensive drugs, the mechanism of action, pharmacokinetics, adverse effects, indications/contraindications, dosage adjustments, monitoring therapy, and principles of monotherapy and combination therapy.

The SLOs to be achieved by undergraduate medical students at the time of graduation identified by Sage Poe, Claude-Instant, and ChatGPT listed in electronic supplementary materials 4 – 6 , respectively. The identified SLOs emphasize the application of pharmacology knowledge within a clinical context, focusing on competencies needed to function independently in early residency stages. These SLOs go beyond knowledge recall and mechanisms of action to encompass competencies related to clinical problem-solving, rational prescribing, and holistic patient management. The SLOs generated require higher cognitive ability of the learner: action verbs such as demonstrate, apply, evaluate, analyze, develop, justify, recommend, interpret, manage, adjust, educate, refer, design, initiate & titrate were frequently used.

The MCQs for the pre-clerkship phase identified by Sage Poe, Claude-Instant, and ChatGPT listed in the electronic supplementary materials 7 – 9 , respectively, and those identified with the search query based on the clinical vignette in electronic supplementary materials ( 10 – 12 ).

All MCQs generated by the AIs in each of the four domains specified [mechanism of action (MOA); pharmacokinetics; adverse drug reactions (ADRs), and indications for antihypertensive drugs] are quality test items with potential content validity. The test items on MOA generated by Sage Poe included themes such as renin-angiotensin-aldosterone (RAAS) system, beta-adrenergic blockers (BB), calcium channel blockers (CCB), potassium channel openers, and centrally acting antihypertensives; on pharmacokinetics included high oral bioavailability/metabolism in liver [angiotensin receptor blocker (ARB)-losartan], long half-life and renal elimination [angiotensin converting enzyme inhibitors (ACEI)-lisinopril], metabolism by both liver and kidney (beta-blocker (BB)-metoprolol], rapid onset- short duration of action (direct vasodilator-hydralazine), and long-acting transdermal drug delivery (centrally acting-clonidine). Regarding the ADR theme, dry cough, angioedema, and hyperkalemia by ACEIs in susceptible patients, reflex tachycardia by CCB/amlodipine, and orthostatic hypotension by CCB/verapamil addressed. Clinical indications included the drug of choice for hypertensive patients with concomitant comorbidity such as diabetics (ACEI-lisinopril), heart failure and low ejection fraction (BB-carvedilol), hypertensive urgency/emergency (alpha cum beta receptor blocker-labetalol), stroke in patients with history recurrent stroke or transient ischemic attack (ARB-losartan), and preeclampsia (methyldopa).

Almost similar themes under each domain were identified by the Claude-Instant AI platform with few notable exceptions: hydrochlorothiazide (instead of clonidine) in MOA and pharmacokinetics domains, respectively; under the ADR domain ankle edema/ amlodipine, sexual dysfunction and fatigue in male due to alpha-1 receptor blocker; under clinical indications the best initial monotherapy for clinical scenarios such as a 55-year old male with Stage-2 hypertension; a 75-year-old man Stage 1 hypertension; a 35-year-old man with Stage I hypertension working on night shifts; and a 40-year-old man with stage 1 hypertension and hyperlipidemia.

As with Claude-Instant AI, ChatGPT-generated test items on MOA were mostly similar. However, under the pharmacokinetic domain, immediate- and extended-release metoprolol, the effect of food to enhance the oral bioavailability of ramipril, and the highest oral bioavailability of amlodipine compared to other commonly used antihypertensives were the themes identified. Whereas the other ADR themes remained similar, constipation due to verapamil was a new theme addressed. Notably, in this test item, amlodipine was an option that increased the difficulty of this test item because amlodipine therapy is also associated with constipation, albeit to a lesser extent, compared to verapamil. In the clinical indication domain, the case description asking “most commonly used in the treatment of hypertension and heart failure” is controversial because the options listed included losartan, ramipril, and hydrochlorothiazide but the suggested correct answer was ramipril. This is a good example to stress the importance of vetting the AI-generated MCQ by experts for content validity and to assure robust psychometrics. The MCQ on the most used drug in the treatment of “hypertension and diabetic nephropathy” is more explicit as opposed to “hypertension and diabetes” by Claude-Instant because the therapeutic concept of reducing or delaying nephropathy must be distinguished from prevention of nephropathy, although either an ACEI or ARB is the drug of choice for both indications.

It is important to align student assessment to the curriculum; in the PBL curriculum, MCQs with a clinical vignette are preferred. The modification of the query specifying the search to generate MCQs with a clinical vignette on domains specified previously gave appropriate output by all three AI platforms evaluated (Sage Poe; Claude- Instant; Chat GPT). The scenarios generated had a good clinical fidelity and educational fit for the pre-clerkship student perspective.

The errors observed with AI outputs on the A-type MCQs are summarized in Table  2 . No significant pattern was observed except that Claude-Instant© generated test items in a stereotyped format such as the same choices for all test items related to pharmacokinetics and indications, and all the test items in the ADR domain are linked to the mechanisms of action of drugs. This illustrates the importance of reviewing AI-generated test items by content experts for content validity to ensure alignment with evidence-based medicine and up-to-date treatment guidelines.

The test items generated by ChatGPT had the advantage of explanations supplied rendering these more useful for learners to support self-study. The following examples illustrate this assertion: “ A patient with hypertension is started on a medication that works by blocking beta-1 receptors in the heart (metoprolol)”. Metoprolol is a beta blocker that works by blocking beta-1 receptors in the heart, which reduces heart rate and cardiac output, resulting in a decrease in blood pressure. However, this explanation is incomplete because there is no mention of other less important mechanisms, of beta receptor blockers on renin release. Also, these MCQs were mostly recall type: Which of the following medications is known to have a significant first-pass effect? The explanation reads: propranolol is known to have a significant first pass-effect, meaning that a large portion of the drug is metabolized by the liver before it reaches systemic circulation. Losartan, amlodipine, ramipril, and hydrochlorothiazide do not have significant first-pass effect. However, it is also important to extend the explanation further by stating that the first-pass effect of propranolol does not lead to total loss of pharmacological activity because the metabolite hydroxy propranolol also has potent beta-blocking activity. Another MCQ test item had a construction defect: “A patient with hypertension is started on a medication that can cause photosensitivity. Which of the following medications is most likely responsible?” Options included: losartan, amlodipine, ramipril, hydrochlorothiazide, hydrochlorothiazide/triamterene. The explanation states that hydrochlorothiazide (HCTZ) can cause photosensitivity, which is increased sensitivity to sunlight that can cause skin rashes and sunburns. Losartan, amlodipine, ramipril, and HCTZ/triamterene are less likely to cause photosensitivity. However, it is irrational to claim that HCTZ/triamterene, one of the wrong options, is less likely to cause photosensitivity. The difficulty index of such test items is likely unacceptable in high-stake tests to make equitable psychometric decisions.

The responses from Sage Poe, Claude-Instant, and ChatGPT on guidance for standard-setting methods are listed in the electronic supplementary materials 13 – 15 . Sage Poe offered this information with the caveat that “the results of this simulation were purely hypothetical and do not reflect the actual performance of any real students”. The simulation estimates of examinees correctly answering test items ranged from 60 to 90% for the mechanism of action, 65–85% for pharmacokinetics, 60–80% for adverse reactions, and 75–90% for clinical indications of antihypertensives.

In contrast, Claude-Instant admitted that “Performing a full simulation with 100 medical students is beyond the scope of what I can do as an AI assistant. I can generate sample MCQ questions and answers, but I do not have access to a population of medical students to administer the questions. A true simulation that administers questions to real students and analyzes the results would require access to a database of medical students, a platform to deliver the questions, and code to analyze the responses. As an AI assistant, I lack these capabilities. While I cannot perform a full simulation, here are some considerations for administering MCQ questions to medical students: provide details on the purpose and instructions for the test to ensure students understand what is expected out of them; consider including some easier questions in addition to more challenging ones to boost students’ confidence and motivation; avoid ambiguous wording and ensure each question has only one unambiguously correct answer option; when analyzing results, look for questions factors that may have impacted performance, like unclear wording or answer options that are too similar. Focusing on weak questions can help improve future tests; compare performance across different student groups to identify areas where more teaching may be needed; provide detailed answer explanations and review sessions after the test to help students learn from any errors and reinforce correct concepts”. However, ChatGPT offered the simulation result estimates for the 20 MCQ on antihypertensive drugs: mechanism of action ranged from 67 to 92%, pharmacokinetics 63–86%, adverse effects 65–82%, and clinical indications 64–89%. Furthermore, it also stated that “Overall, the performance of the students was quite good, with most questions having a response rate of over 70%. However, there were some questions where the projected correct response rate was rather low, such as Question #5 (Mechanism of Action of Hydrochlorothiazide; see Electronic Supplementary Material 12 ) and Question 18 (Indications for Verapamil; see Electronic Supplementary Material 10 ). This may suggest areas where students need more focused education or review.”

We asked AI assistants to generate 20 integrated case cluster MCQs with 2 test items in each cluster with five options for undergraduate medical students in the pre-clerkship phase integrating pharmacology and physiology related to systemic hypertension with a case vignette and the responses by Sage Poe, Claude-Instant, and ChatGPT are listed in the electronic supplementary materials ( 16 – 18 ). In all instances, the test items generated had focused case descriptions in the form of a clinical vignette, and horizontal integration across the pathophysiology of hypertension and pharmacology of antihypertensive drugs. These test items mostly targeted the ‘knows (knowledge)’ or ‘knows how (competence)’ level on Miller’s pyramid and are suitable for assessing the clinical competence of pre-clerkship medical students, especially in an integrated PBL curriculum. Both the AI assistants generated excellent clinical vignettes and themes; however, most of the cluster MCQs by ChatGPT had “None of the above” as an option, which is often considered a test item construction flaw. Notwithstanding these limitations, case cluster integrated test items are valuable for learners to integrate their knowledge of different basic medical sciences and their application to clinical sciences. This integrated approach can be used for both instructional and student assessment purposes to make the course more meaningful. Indeed, one of the basic tenets of PBL is curriculum integration.

In the next query, we asked AI assistants to write integrated case cluster MCQs with 2 test items in each cluster with 5 options for undergraduate medical students at the time of graduation integrating pharmacology and physiology of hypertension with a case vignette. The responses are listed in the electronic supplementary materials 19 – 21 . Claude-Instant has provided only partial responses to both the queries. Overall, the information provided in case vignettes requires the learner to interpret the clinical information and make therapeutic decisions. Such test items are appropriate for assessing the minimum competency of medical school graduates to start internship or residency programs; these MCQs are generally comparable to test items used in USMLE Part 2. The evaluation of the integrated case cluster test items provided by all the AI platforms is summarized in Table  3 . In general, the AI outputs had at least one construction defect, and did not include all the core sub-topics to a sufficient degree.

When asked to simulate the above-generated test items to 100 undergraduate medical students at the time of graduation and provide a percentage of students who are likely to correctly answer each item, the AI assistant responded:

“ As an AI language model, I cannot simulate the responses of 100 undergraduate medical students likely to obtain the correct answer for each question. However, I can provide some general information about the difficulty level of each question based on the complexity of the concepts being tested and the level of integration between pharmacology and physiology ”.

AI assistant went on to clarify that questions that require knowledge of basic pharmacology principles, such as the mechanism of action of specific drugs, are likely to be easier for students to answer correctly. Test items that require an understanding of the physiological mechanisms underlying hypertension and correlating with symptoms are likely to be more challenging for students. The AI assistant sorted these test items into two categories accordingly. Overall, the difficulty level of the test item is based on the level of integration between pharmacology and pathophysiology. Test items that require an understanding of both pharmacological and physiological mechanisms are likely to be more challenging for students requiring a strong foundation in both pharmacology and physiology concepts to be able to correctly answer integrated case-cluster MCQs.

Short answer questions

The responses to a search query on generating SAQs appropriate to the pre-clerkship phase Sage Poe, Claude-Instant, and ChatGPT generated items are listed in the electronic supplementary materials 22 – 24 for difficult questions and 25–27 for moderately difficult questions.

It is apparent from these case vignette descriptions that the short answer question format varied. Accordingly, the scope for asking individual questions for each scenario is open-ended. In all instances, model answers are supplied which are helpful for the course instructor to plan classroom lessons, identify appropriate instructional methods, and establish rubrics for grading the answer scripts, and as a study guide for students.

We then wanted to see to what extent AI can differentiate the difficulty of the SAQ by replacing the search term “difficult” with “moderately difficult” in the above search prompt: the changes in the revised case scenarios are substantial. Perhaps the context of learning and practice (and the level of the student in the MD/medical program) may determine the difficulty level of SAQ generated. It is worth noting that on changing the search from cardiology to internal medicine rotation in Sage Poe the case description also changed. Thus, it is essential to select an appropriate AI assistant, perhaps by trial and error, to generate quality SAQs. Most of the individual questions tested stand-alone knowledge and did not require students to demonstrate integration.

The responses of Sage Poe, Claude-Instant, and ChatGPT for the search query to generate SAQs at the time of graduation are listed in the electronic supplementary materials 28 – 30 . It is interesting to note how AI assistants considered the stage of the learner while generating the SAQ. The response by Sage Poe is illustrative for comparison. “You are a newly graduated medical student who is working in a hospital” versus “You are a medical student in your pre-clerkship.”

Some questions were retained, deleted, or modified to align with competency appropriate to the context (Electronic Supplementary Materials 28 – 30 ). Overall, the test items at both levels from all AI platforms were technically accurate and thorough addressing the topics related to different disciplines (Table  3 ). The differences in learning objective transition are summarized in Table  4 . A comparison of learning objectives revealed that almost all objectives remained the same except for a few (Table  5 ).

A similar trend was apparent with test items generated by other AI assistants, such as ChatGPT. The contrasting differences in questions are illustrated by the vertical integration of basic sciences and clinical sciences (Table  6 ).

Taken together, these in-depth qualitative comparisons suggest that AI assistants such as Sage Poe and ChatGPT consider the learner’s stage of training in designing test items, learning outcomes, and answers expected from the examinee. It is critical to state the search query explicitly to generate quality output by AI assistants.

The OSPE test items generated by Claude-Instant and ChatGPT appropriate to the pre-clerkship phase (without mentioning “appropriate instructions for the patients”) are listed in the electronic supplementary materials 31 and 32 and with patient instructions on the electronic supplementary materials 33 and 34 . For reasons unknown, Sage Poe did not provide any response to this search query.

The five OSPE items generated were suitable to assess the prescription writing competency of pre-clerkship medical students. The clinical scenarios identified by the three AI platforms were comparable; these scenarios include patients with hypertension and impaired glucose tolerance in a 65-year-old male, hypertension with chronic kidney disease (CKD) in a 55-year-old woman, resistant hypertension with obstructive sleep apnea in a 45-year-old man, and gestational hypertension at 32 weeks in a 35-year-old (Claude-Instant AI). Incorporating appropriate instructions facilitates the learner’s ability to educate patients and maximize safe and effective therapy. The OSPE item required students to write a prescription with guidance to start conservatively, choose an appropriate antihypertensive drug class (drug) based on the patients’ profile, specifying drug name, dose, dosing frequency, drug quantity to be dispensed, patient name, date, refill, and caution as appropriate, in addition to prescribers’ name, signature, and license number. In contrast, ChatGPT identified clinical scenarios to include patients with hypertension and CKD, hypertension and bronchial asthma, gestational diabetes, hypertension and heart failure, and hypertension and gout (ChatGPT). Guidance for dosage titration, warnings to be aware, safety monitoring, and frequency of follow-up and dose adjustment. These test items are designed to assess learners’ knowledge of P & T of antihypertensives, as well as their ability to provide appropriate instructions to patients. These clinical scenarios for writing prescriptions assess students’ ability to choose an appropriate drug class, write prescriptions with proper labeling and dosing, reflect drug safety profiles, and risk factors, and make modifications to meet the requirements of special populations. The prescription is required to state the drug name, dose, dosing frequency, patient name, date, refills, and cautions or instructions as needed. A conservative starting dose, once or twice daily dosing frequency based on the drug, and instructions to titrate the dose slowly if required.

The responses from Claude-Instant and ChatGPT for the search query related to generating OSPE test items at the time of graduation are listed in electronic supplementary materials 35 and 36 . In contrast to the pre-clerkship phase, OSPEs generated for graduating doctors’ competence assessed more advanced drug therapy comprehension. For example, writing a prescription for:

(1) A 65-year- old male with resistant hypertension and CKD stage 3 to optimize antihypertensive regimen required the answer to include starting ACEI and diuretic, titrating the dosage over two weeks, considering adding spironolactone or substituting ACEI with an ARB, and need to closely monitor serum electrolytes and kidney function closely.

(2) A 55-year-old woman with hypertension and paroxysmal arrhythmia required the answer to include switching ACEI to ARB due to cough, adding a CCB or beta blocker for rate control needs, and adjusting the dosage slowly and monitoring for side effects.

(3) A 45-year-old man with masked hypertension and obstructive sleep apnea require adding a centrally acting antihypertensive at bedtime and increasing dosage as needed based on home blood pressure monitoring and refer to CPAP if not already using one.

(4) A 75-year-old woman with isolated systolic hypertension and autonomic dysfunction to require stopping diuretic and switching to an alpha blocker, upward dosage adjustment and combining with other antihypertensives as needed based on postural blood pressure changes and symptoms.

(5) A 35-year-old pregnant woman with preeclampsia at 29 weeks require doubling methyldopa dose and consider adding labetalol or nifedipine based on severity and educate on signs of worsening and to follow-up immediately for any concerning symptoms.

These case scenarios are designed to assess the ability of the learner to comprehend the complexity of antihypertensive regimens, make evidence-based regimen adjustments, prescribe multidrug combinations based on therapeutic response and tolerability, monitor complex patients for complications, and educate patients about warning signs and follow-up.

A similar output was provided by ChatGPT, with clinical scenarios such as prescribing for patients with hypertension and myocardial infarction; hypertension and chronic obstructive pulmonary airway disease (COPD); hypertension and a history of angina; hypertension and a history of stroke, and hypertension and advanced renal failure. In these cases, wherever appropriate, pharmacotherapeutic issues like taking ramipril after food to reduce side effects such as giddiness; selection of the most appropriate beta-blocker such as nebivolol in patients with COPD comorbidity; the importance of taking amlodipine at the same time every day with or without food; preference for telmisartan among other ARBs in stroke; choosing furosemide in patients with hypertension and edema and taking the medication with food to reduce the risk of gastrointestinal adverse effect are stressed.

The AI outputs on OSPE test times were observed to be technically accurate, thorough in addressing core sub-topics suitable for the learner’s level and did not have any construction defects (Table  3 ). Both AIs provided the model answers with explanatory notes. This facilitates the use of such OSPEs for self-assessment by learners for formative assessment purposes. The detailed instructions are helpful in creating optimized therapy regimens, and designing evidence-based regimens, to provide appropriate instructions to patients with complex medical histories. One can rely on multiple AI sources to identify, shortlist required case scenarios, and OSPE items, and seek guidance on expected model answers with explanations. The model answer guidance for antihypertensive drug classes is more appropriate (rather than a specific drug of a given class) from a teaching/learning perspective. We believe that these scenarios can be refined further by providing a focused case history along with relevant clinical and laboratory data to enhance clinical fidelity and bring a closer fit to the competency framework.

In the present study, AI tools have generated SLOs that comply with the current principles of medical education [ 15 ]. AI tools are valuable in constructing SLOs and so are especially useful for medical fraternities where training in medical education is perceived as inadequate, more so in the early stages of their academic career. Data suggests that only a third of academics in medical schools have formal training in medical education [ 16 ] which is a limitation. Thus, the credibility of alternatives, such as the AIs, is evaluated to generate appropriate course learning outcomes.

We observed that the AI platforms in the present study generated quality test items suitable for different types of assessment purposes. The AI-generated outputs were similar with minor variation. We have used generative AIs in the present study that could generate new content from their training dataset [ 17 ]. Problem-based and interactive learning approaches are referred to as “bottom-up” where learners obtain first-hand experience in solving the cases first and then indulge in discussion with the educators to refine their understanding and critical thinking skills [ 18 ]. We suggest that AI tools can be useful for this approach for imparting the core knowledge and skills related to Pharmacology and Therapeutics to undergraduate medical students. A recent scoping review evaluating the barriers to writing quality test items based on 13 studies has concluded that motivation, time constraints, and scheduling were the most common [ 19 ]. AI tools can be valuable considering the quick generation of quality test items and time management. However, as observed in the present study, the AI-generated test items nevertheless require scrutiny by faculty members for content validity. Moreover, it is important to train faculty in AI technology-assisted teaching and learning. The General Medical Council recommends taking every opportunity to raise the profile of teaching in medical schools [ 20 ]. Hence, both the academic faculty and the institution must consider investing resources in AI training to ensure appropriate use of the technology [ 21 ].

The AI outputs assessed in the present study had errors, particularly with A-type MCQs. One notable observation was that often the AI tools were unable to differentiate the differences between ACEIs and ARBs. AI platforms access several structured and unstructured data, in addition to images, audio, and videos. Hence, the AI platforms can commit errors due to extracting details from unauthenticated sources [ 22 ] created a framework identifying 28 factors for reconstructing the path of AI failures and for determining corrective actions. This is an area of interest for AI technical experts to explore. Also, this further iterates the need for human examination of test items before using them for assessment purposes.

There are concerns that AIs can memorize and provide answers from their training dataset, which they are not supposed to do [ 23 ]. Hence, the use of AIs-generated test items for summative examinations is debatable. It is essential to ensure and enhance the security features of AI tools to reduce or eliminate cross-contamination of test items. Researchers have emphasized that AI tools will only reach their potential if developers and users can access full-text non-PDF formats that help machines comprehend research papers and generate the output [ 24 ].

AI platforms may not always have access to all standard treatment guidelines. However, in the present study, it was observed that all three AI platforms generally provided appropriate test items regarding the choice of medications, aligning with recommendations from contemporary guidelines and standard textbooks in pharmacology and therapeutics. The prompts used in the study were specifically focused on the pre-clerkship phase of the undergraduate medical curriculum (and at the time of their graduation) and assessed fundamental core concepts, which were also reflected in the AI outputs. Additionally, the recommended first-line antihypertensive drug classes have been established for several decades, and information regarding their pharmacokinetics, ADRs, and indications is well-documented in the literature.

Different paradigms and learning theories have been proposed to support AI in education. These paradigms include AI- directed (learner as recipient), AI-supported (learner as collaborator), and AI-empowered (learner as leader) that are based on Behaviorism, Cognitive-Social constructivism, and Connectivism-Complex adaptive systems, respectively [ 25 ]. AI techniques have potential to stimulate and advance instructional and learning sciences. More recently a three- level model that synthesizes and unifies existing learning theories to model the roles of AIs in promoting learning process has been proposed [ 26 ]. The different components of our study rely upon these paradigms and learning theories as the theoretical underpinning.

Strengths and limitations

To the best of our knowledge, this is the first study evaluating the utility of AI platforms in generating test items related to a discipline in the undergraduate medical curriculum. We have evaluated the AI’s ability to generate outputs related to most types of assessment in the undergraduate medical curriculum. The key lessons learnt for improving the AI-generated test item quality from the present study are outlined in Table  7 . We used a structured framework for assessing the content validity of the test items. However, we have demonstrated using a single case study (hypertension) as a pilot experiment. We chose to evaluate anti-hypertensive drugs as it is a core learning objective and one of the most common disorders relevant to undergraduate medical curricula worldwide. It would be interesting to explore the output from AI platforms for other common (and uncommon/region-specific) disorders, non-/semi-core objectives, and disciplines other than Pharmacology and Therapeutics. An area of interest would be to look at the content validity of the test items generated for different curricula (such as problem-based, integrated, case-based, and competency-based) during different stages of the learning process. Also, we did not attempt to evaluate the generation of flowcharts, algorithms, or figures for generating test items. Another potential area for exploring the utility of AIs in medical education would be repeated procedural practices such as the administration of drugs through different routes by trainee residents [ 27 ]. Several AI tools have been identified for potential application in enhancing classroom instructions and assessment purposes pending validation in prospective studies [ 28 ]. Lastly, we did not administer the AI-generated test items to students and assessed their performance and so could not comment on the validity of test item discrimination and difficulty indices. Additionally, there is a need to confirm the generalizability of the findings to other complex areas in the same discipline as well as in other disciplines that pave way for future studies. The conceptual framework used in the present study for evaluating the AI-generated test items needs to be validated in a larger population. Future studies may also try to evaluate the variations in the AI outputs with repetition of the same queries.

Notwithstanding ongoing discussions and controversies, AI tools are potentially useful adjuncts to optimize instructional methods, test blueprinting, test item generation, and guidance for test standard-setting appropriate to learners’ stage in the medical program. However, experts need to critically review the content validity of AI-generated output. These challenges and caveats are to be addressed before the use of widespread use of AIs in medical education can be advocated.

Data availability

All the data included in this study are provided as Electronic Supplementary Materials.

Tolsgaard MG, Pusic MV, Sebok-Syer SS, Gin B, Svendsen MB, Syer MD, Brydges R, Cuddy MM, Boscardin CK. The fundamentals of Artificial Intelligence in medical education research: AMEE Guide 156. Med Teach. 2023;45(6):565–73.

Article   Google Scholar  

Sriwastwa A, Ravi P, Emmert A, Chokshi S, Kondor S, Dhal K, Patel P, Chepelev LL, Rybicki FJ, Gupta R. Generative AI for medical 3D printing: a comparison of ChatGPT outputs to reference standard education. 3D Print Med. 2023;9(1):21.

Azer SA, Guerrero APS. The challenges imposed by artificial intelligence: are we ready in medical education? BMC Med Educ. 2023;23(1):680.

Masters K. Ethical use of Artificial Intelligence in Health Professions Education: AMEE Guide 158. Med Teach. 2023;45(6):574–84.

Nagi F, Salih R, Alzubaidi M, Shah H, Alam T, Shah Z, Househ M. Applications of Artificial Intelligence (AI) in Medical Education: a scoping review. Stud Health Technol Inf. 2023;305:648–51.

Google Scholar  

Mehta N, Harish V, Bilimoria K, et al. Knowledge and attitudes on artificial intelligence in healthcare: a provincial survey study of medical students. MedEdPublish. 2021;10(1):75.

Mir MM, Mir GM, Raina NT, Mir SM, Mir SM, Miskeen E, Alharthi MH, Alamri MMS. Application of Artificial Intelligence in Medical Education: current scenario and future perspectives. J Adv Med Educ Prof. 2023;11(3):133–40.

Garg T. Artificial Intelligence in Medical Education. Am J Med. 2020;133(2):e68.

Matheny ME, Whicher D, Thadaney IS. Artificial intelligence in health care: a report from the National Academy of Medicine. JAMA. 2020;323(6):509–10.

Sage Poe. Available at: https://poe.com/Assistant (Accessed on. 3rd June 2023).

Claude-Instant: Available at: https://poe.com/Claude-instant (Accessed on 3rd. June 2023).

ChatGPT: Available at: https://poe.com/ChatGPT (Accessed on 3rd. June 2023).

James PA, Oparil S, Carter BL, Cushman WC, Dennison-Himmelfarb C, Handler J, Lackland DT, LeFevre ML, MacKenzie TD, Ogedegbe O, Smith SC Jr, Svetkey LP, Taler SJ, Townsend RR, Wright JT Jr, Narva AS, Ortiz E. 2014 evidence-based guideline for the management of high blood pressure in adults: report from the panel members appointed to the Eighth Joint National Committee (JNC 8). JAMA. 2014;311(5):507–20.

Eschenhagen T. Treatment of hypertension. In: Brunton LL, Knollmann BC, editors. Goodman & Gilman’s the pharmacological basis of therapeutics. 14th ed. New York: McGraw Hill; 2023.

Shabatura J. September. Using Bloom’s taxonomy to write effective learning outcomes. https://tips.uark.edu/using-blooms-taxonomy/ (Accessed on 19th 2023).

Trainor A, Richards JB. Training medical educators to teach: bridging the gap between perception and reality. Isr J Health Policy Res. 2021;10(1):75.

Boscardin C, Gin B, Golde PB, Hauer KE. ChatGPT and generative artificial intelligence for medical education: potential and opportunity. Acad Med. 2023. https://doi.org/10.1097/ACM.0000000000005439 . (Published ahead of print).

Duong MT, Rauschecker AM, Rudie JD, Chen PH, Cook TS, Bryan RN, Mohan S. Artificial intelligence for precision education in radiology. Br J Radiol. 2019;92(1103):20190389.

Karthikeyan S, O’Connor E, Hu W. Barriers and facilitators to writing quality items for medical school assessments - a scoping review. BMC Med Educ. 2019;19(1):123.

Developing teachers and trainers in undergraduate medical education. Advice supplementary to Tomorrow’s Doctors. (2009). https://www.gmc-uk.org/-/media/documents/Developing_teachers_and_trainers_in_undergraduate_medical_education___guidance_0815.pdf_56440721.pdf (Accessed on 19th September 2023).

Cooper A, Rodman A. AI and Medical Education - A 21st-Century Pandora’s Box. N Engl J Med. 2023;389(5):385–7.

Chanda SS, Banerjee DN. Omission and commission errors underlying AI failures. AI Soc. 2022;17:1–24.

Narayanan A, Kapoor S. ‘GPT-4 and Professional Benchmarks: The Wrong Answer to the Wrong Question’. Substack newsletter. AI Snake Oil (blog). https://aisnakeoil.substack.com/p/gpt-4-and-professional-benchmarks (Accessed on 19th September 2023).

Brainard J. November. As scientists face a flood of papers, AI developers aim to help. Science, 21 2023. doi.10.1126/science.adn0669.

Ouyang F, Jiao P. Artificial intelligence in education: the three paradigms. Computers Education: Artif Intell. 2021;2:100020.

Gibson D, Kovanovic V, Ifenthaler D, Dexter S, Feng S. Learning theories for artificial intelligence promoting learning processes. Br J Edu Technol. 2023;54(5):1125–46.

Guerrero DT, Asaad M, Rajesh A, Hassan A, Butler CE. Advancing Surgical Education: the Use of Artificial Intelligence in Surgical Training. Am Surg. 2023;89(1):49–54.

Lee S. AI tools for educators. EIT InnoEnergy Master School Teachers Conference. 2023. https://www.slideshare.net/ignatia/ai-toolkit-for-educators?from_action=save (Accessed on 24th September 2023).

Download references

Author information

Authors and affiliations.

Department of Pharmacology & Therapeutics, College of Medicine & Medical Sciences, Arabian Gulf University, Manama, Kingdom of Bahrain

Kannan Sridharan & Reginald P. Sequeira

You can also search for this author in PubMed   Google Scholar

Contributions

RPS– Conceived the idea; KS– Data collection and curation; RPS and KS– Data analysis; RPS and KS– wrote the first draft and were involved in all the revisions.

Corresponding author

Correspondence to Kannan Sridharan .

Ethics declarations

Ethics approval and consent to participate.

Not applicable as neither there was any interaction with humans, nor any personal data was collected in this research study.

Consent for publication

Not applicable.

Competing interests

The authors declare no competing interests.

Additional information

Publisher’s note.

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Electronic supplementary material

Below is the link to the electronic supplementary material.

Supplementary Material 1

Rights and permissions.

Open Access This article is licensed under a Creative Commons Attribution 4.0 International License, which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if changes were made. The images or other third party material in this article are included in the article’s Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article’s Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit http://creativecommons.org/licenses/by/4.0/ . The Creative Commons Public Domain Dedication waiver ( http://creativecommons.org/publicdomain/zero/1.0/ ) applies to the data made available in this article, unless otherwise stated in a credit line to the data.

Reprints and permissions

About this article

Cite this article.

Sridharan, K., Sequeira, R.P. Artificial intelligence and medical education: application in classroom instruction and student assessment using a pharmacology & therapeutics case study. BMC Med Educ 24 , 431 (2024). https://doi.org/10.1186/s12909-024-05365-7

Download citation

Received : 26 September 2023

Accepted : 28 March 2024

Published : 22 April 2024

DOI : https://doi.org/10.1186/s12909-024-05365-7

Share this article

Anyone you share the following link with will be able to read this content:

Sorry, a shareable link is not currently available for this article.

Provided by the Springer Nature SharedIt content-sharing initiative

• Medical education
• Pharmacology
• Therapeutics

BMC Medical Education

ISSN: 1472-6920

• Submission enquiries: [email protected]
• General enquiries: [email protected]

A real-valued label noise cleaning method based on ensemble iterative filtering with noise score

• Original Article
• Published: 29 April 2024

Cite this article

• Chuang Li 1 ,
• Zhizhong Mao   ORCID: orcid.org/0000-0002-2658-3297 1 &
• Mingxing Jia 1  

Real-world data always contain noise for a variety of reasons. In a regression task, noisy labels interfere with the construction of an accurate model, leading to a decline in the prediction accuracy. Methods that have emerged to deal with continuous label noise are rather limited in contrast with those on class noise cleaning techniques. To address this gap, we propose a novel noise filter to clean noisy instances with real-valued label noise. This method combines several filtering strategies. First, an iterative filtering process is carried out, allowing us to avoid using potential noisy examples in each new filtering iteration. Second, we develop a noise score to assess the noise level of each detected noisy instance. The higher the noise score is, the more likely that the instance is noisy. Finally, an ensemble filtering scheme is implemented. The fusion of detection from different models makes the determination of noisy examples even more reliable. The validity of the proposed method is verified through extensive experiments. We discuss the selection of the best hyperparameters, and compare the developed method with several state-of-the-art noise filters using public regression datasets. The outcomes show that our method not only achieves a good balance between the elimination of noisy samples and the retention of clean samples but also outperforms all the other compared methods, especially at higher noise levels. Simultaneously, the results of a case study of temperature prediction in an electric arc furnace suggest that training a domain-related regressor on a dataset preprocessed with the proposed noise filter contributes to a great improvement in the prediction accuracy.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Price includes VAT (Russian Federation)

Instant access to the full article PDF.

Rent this article via DeepDyve

Institutional subscriptions

Data availability

The data used in the experiments mainly comes from KEEL and UCI repositories. Please refer to references [ 38 ] and [ 39 ] for detail.

Kang Z, Pan H, Hoi SCH et al (2020) Robust graph learning from noisy data. IEEE Trans Cybernet 50(5):1833–1843

Article   Google Scholar  

Sáez JA, Corchado E (2019) KSUFS: a novel unsupervised feature selection method based on statistical tests for standard and big data problems. IEEE Access 7:99754–99770

Frenay B, Verleysen M (2014) Classification in the presence of label noise: a survey. IEEE Trans Neural Netw Learn Syst 25(5):845–869

Zhu X, Wu X (2004) Class noise vs. attribute noise: a quantitative study. Artif Intell Rev 22:177–210

Sáez JA, Galar M, Luengo J et al (2014) Analyzing the presence of noise in multi-class problems: alleviating its influence with the one-vs-one decomposition. Knowl Inf Syst 38:179–206

Gamberger D, Lavrac N, Dzeroski S (1996) Noise elimination in inductive concept learning: a case study in medical diagnosis. In: proceedings of the 7th international workshop on algorithmic learning theory, pp 199–212

García S, Luengo J, Herrera F (2016) Tutorial on practical tips of the most influential data preprocessing algorithms in data mining. Knowl Based Syst 98:1–29

Sáez JA, Galar M, Luengo J et al (2016) INFFC: an iterative class noise filter based on the fusion of classifiers with noise sensitivity control. Inform Fusion 27:19–32

Luengo J, Shim SO, Alshomrani S et al (2018) CNC-NOS: class noise cleaning by ensemble filtering and noise scoring. Knowl Based Syst 140:27–49

Nematzadeh Z, Ibrahim R, Selamat A (2020) Improving class noise detection and classification performance: a new two-filter CNDC model. Appl Soft Comput 94:106428

Li C, Sheng VS, Jiang L et al (2016) Noise filtering to improve data and model quality for crowdsourcing. Knowl Based Syst 107:96–103

Jeatrakul P, Wong KW, Fung CC (2010) Data cleaning for classification using misclassification analysis. J Adv Comput Intell Intell Inf 14:297–302

Algan G, Ulusoy I (2020) Image classification with deep learning in the presence of noisy labels: a survey. Knowl Based Syst 215:106771

Wang Y, Liu W, Ma X, et al (2018) Iterative learning with open-set noisy labels. In: proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pp 8688–8696

Daiki T, Daiki I, Toshihiko Y et al (2018) Joint optimization framework for learning with noisy labels. In: proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pp 5552–5560

Yu X, Han B, Yao J et al (2019) How does disagreement help generalization against label corruption? In: international conference on machine learning, pp 7164–7173

Kordos M, Blachnik M (2012) Instance selection with neural networks for regression problems. In: international conference on artificial neural networks, pp 263–270

Martín J, Sáez JA, Corchado E (2021) On the regressand noise problem: model robustness and synergy with regression-adapted noise filters. IEEE Access 9:145800–145816

González AA, Pastor JFD, Rodríguez JJ et al (2016) Instance selection for regression by discretization. Expert Syst Appl 54:340–350

González AA, Pastor JFD, Rodríguez JJ et al (2016) Instance selection for regression: adapting DROP. Neurocomputing 201:66–81

Sofie V, Assche AV (2003) Ensemble methods for noise elimination in classification problems. Multiple classifier systems. Springer, Berlin, pp 317–325

Google Scholar  

Khoshgoftaar TM, Rebours P (2007) Improving software quality prediction by noise filtering techniques. J Comput Sci Technol 22:387–396

Gamberger D, Lavrac N, Dzeroski S (2000) Noise detection and elimination in data preprocessing: experiments in medical domains. Appl Artif Intell 14(2):205–223

Berghout T, Mouss LH, Kadri O et al (2020) Aircraft engines remaining useful life prediction with an adaptive denoising online sequential extreme learning machine. Eng Appl Artif Intel 96:103936

Lv M, Hong Z, Chen L et al (2020) Temporal multi-graph convolutional network for traffic flow prediction. IEEE Trans Intell Transp Syst 22(6):3337–3348

Ge L, Wu K, Zeng Y et al (2020) Multi-scale spatiotemporal graph convolution network for air quality prediction. Appl Intell 51:3491–3505

Shine P, Scully T, Upton J et al (2019) Annual electricity consumption prediction and future expansion analysis on dairy farms using a support vector machine. Appl Energy 250:1110–1119

Kara F, Aslantaş K, Çiçek A (2016) Prediction of cutting temperature in orthogonal machining of AISI 316L using artificial neural network. Appl Soft Comput 38:64–74

Wang RY, Storey VC, Firth CP (1995) A framework for analysis of data quality research. IEEE Trans Knowl Data Eng 7:623–640

Fernandez JMM, Cabal VA, Montequin VR et al (2008) Online estimation of electric arc furnace tap temperature by using fuzzy neural networks. Eng Appl Artif Intel 21(7):1001–1012

Brodley CE, Friedl MA (1999) Identifying mislabeled training data. J Artif Intell Res 11(1):131–167

Sun J, Zhao F, Wang C et al (2007) Identifying and correcting mislabeled training instances. In: proceedings of the future generation communication and networking, pp 244–250

Tomek I (1976) An experiment with the edited nearest-neighbor rule. IEEE Trans Syst Man Cybernet 6(6):448–452

MathSciNet   Google Scholar  

Aha DW, Kibler D, Albert MK (1991) Instance-based learning algorithms. Mach Learn 6:37–66

Jiang G, Wang W, Qian Y et al (2021) A unified sample selection framework for output noise filtering: an error-bound perspective. J Mach Learn Res 22:1–66

González AA, Blachnik M, Kordos M et al (2016) Fusion of instance selection methods in regression tasks. Inform Fusion 30:69–79

Angelova A, Mostafam YA, Perona P (2005) Pruning training sets for learning of object categories. In proceedings of the IEEE computer society conference on computer vision and pattern recognition, pp 494–501

Fdez JA, Fernandez A, Luengo J et al (2011) KEEL data-mining software tool: data set repository, integration of algorithms and experimental analysis framework. J Mult Valued Logic Soft Comput 17(2–3):255–287

Dheeru D, Graff C (2017) UCI Machine learning repository. http://archive.ics.uci.edu/ml . Accessed 2017

Zhao L, Gkountouna O, Pfoser D (2019) Spatial auto-regressive dependency interpretable learning based on spatial topological constraints. ACM Trans Spat Algorithms Syst 5(3):1–28

Acı CI, Akay MF (2015) A hybrid congestion control algorithm for broadcast-based architectures with multiple input queues. J Supercomput 71:1907–1931

Zhou F, Claire Q, King RD (2014) Predicting the geographical origin of music. In proceedings of the IEEE international conference on data mining, pp 1115–1120

Kaya H, Tüfekci P, Uzun E (2019) Predicting CO and NOx emissions from gas turbines: novel data and a benchmark PEMS. Turk J Electr Eng Comput Sci 27(6):4783–4796

Moro S, Rita P, Vala B (2016) Predicting social media performance metrics and evaluation of the impact on brand building: a data mining approach. J Bus Res 69(9):3341–3351

Vergara A, Vembu S, Ayhan T et al (2012) Chemical gas sensor drift compensation using classifier ensembles. Sens Actuators B Chem 166:320–329

Lujan IR, Fonollosa J, Vergara A et al (2014) On the calibration of sensor arrays for pattern recognition using the minimal number of experiments. Chemom Intell Lab Syst 130:123–134

Hoseinzade E, Haratizadeh S (2019) CNNpred: CNN-based stock market prediction using a diverse set of variables. Expert Syst Appl 129:273–285

Rafiei MH, Adeli H (2016) A novel machine learning model for estimation of sale prices of real estate units. J Constr Eng Manag 142(2):04015066

Vito SDE, Massera E, Piga M et al (2008) On field calibration of an electronic nose for benzene estimation in an urban pollution monitoring scenario. Sens Actuators B Chem 129(2):750–757

Fanaee TH, Gama J (2014) Event labeling combining ensemble detectors and background knowledge. Prog Artif Intell 2(2):113–127

Huang GB, Zhu QY, Siew CK (2006) Extreme learning machine: theory and applications. Neurocomputing 70(1):489–501

Demšar J (2006) Statistical comparisons of classifiers over multiple data sets. J Mach Learn Res 7:1–30

García S, Fernández A, Luengo J et al (2010) Advanced nonparametric tests for multiple comparisons in the design of experiments in computational intelligence and data mining: experimental analysis of power. Inform Sci 180(10):2044–2064

Holm S (1979) A simple sequentially rejective multiple test procedure. Scand J Stat 6:65–70

Hay T, Visuri VV, Aula M et al (2020) A review of mathematical process models for the electric arc furnace process. Steel Res Int 92(3):2000395

Li C, Mao Z (2022) Generative adversarial network–based real-time temperature prediction model for heating stage of electric arc furnace. Trans Inst Meas Control 44(8):1669–1684

Yuan P, Wang F, Mao Z (2006) Endpoint prediction of EAF based on G-SVM. J Iron Steel Res Int 18(10):7–10

Fernandez JMM, Menendez C, Ortega FA et al (2009) A smart modelling for the casting temperature prediction in an electric arc furnace. Int J Comput Math 86(7):1182–1193

Sismanis P (2019) Prediction of productivity and energy consumption in a consteel furnace using data-science models. In: proceedings of the 22th international conference on business information systems, pp 85–99

Download references

Acknowledgements

This work was supported by the Key Program of National Natural Science Foundation of China (No. 51634002) and National Natural Science Foundation of China (No. 61773101).

Author information

Authors and affiliations.

College of Information Science and Engineering, Northeastern University, Shenyang, 110819, China

Chuang Li, Zhizhong Mao & Mingxing Jia

You can also search for this author in PubMed   Google Scholar

Corresponding author

Correspondence to Zhizhong Mao .

Ethics declarations

Conflict of interest.

The authors declare that there are no conflicts of interest.

Additional information

Publisher's note.

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.

Reprints and permissions

About this article

Li, C., Mao, Z. & Jia, M. A real-valued label noise cleaning method based on ensemble iterative filtering with noise score. Int. J. Mach. Learn. & Cyber. (2024). https://doi.org/10.1007/s13042-024-02137-z

Download citation

Received : 17 January 2023

Accepted : 13 March 2024

Published : 29 April 2024

DOI : https://doi.org/10.1007/s13042-024-02137-z

Share this article

Anyone you share the following link with will be able to read this content:

Sorry, a shareable link is not currently available for this article.

Provided by the Springer Nature SharedIt content-sharing initiative

• Real-valued label noise
• Noise filter
• Iterative filtering
• Noise score
• Ensemble scheme
• Find a journal
• Publish with us
• Track your research