ways to analyse case study

• PRO Courses Guides New Tech Help Pro Expert Videos About wikiHow Pro Upgrade Sign In
• EDIT Edit this Article
• EXPLORE Tech Help Pro About Us Random Article Quizzes Request a New Article Community Dashboard This Or That Game Popular Categories Arts and Entertainment Artwork Books Movies Computers and Electronics Computers Phone Skills Technology Hacks Health Men's Health Mental Health Women's Health Relationships Dating Love Relationship Issues Hobbies and Crafts Crafts Drawing Games Education & Communication Communication Skills Personal Development Studying Personal Care and Style Fashion Hair Care Personal Hygiene Youth Personal Care School Stuff Dating All Categories Arts and Entertainment Finance and Business Home and Garden Relationship Quizzes Cars & Other Vehicles Food and Entertaining Personal Care and Style Sports and Fitness Computers and Electronics Health Pets and Animals Travel Education & Communication Hobbies and Crafts Philosophy and Religion Work World Family Life Holidays and Traditions Relationships Youth
• Browse Articles
• Learn Something New
• Quizzes Hot
• This Or That Game
• Train Your Brain
• Explore More
• Support wikiHow
• About wikiHow
• Log in / Sign up
• Education and Communications

How to Analyse a Case Study

Last Updated: April 13, 2024 Fact Checked

This article was co-authored by Sarah Evans . Sarah Evans is a Public Relations & Social Media Expert based in Las Vegas, Nevada. With over 14 years of industry experience, Sarah is the Founder & CEO of Sevans PR. Her team offers strategic communications services to help clients across industries including tech, finance, medical, real estate, law, and startups. The agency is renowned for its development of the "reputation+" methodology, a data-driven and AI-powered approach designed to elevate brand credibility, trust, awareness, and authority in a competitive marketplace. Sarah’s thought leadership has led to regular appearances on The Doctors TV show, CBS Las Vegas Now, and as an Adobe influencer. She is a respected contributor at Entrepreneur magazine, Hackernoon, Grit Daily, and KLAS Las Vegas. Sarah has been featured in PR Daily and PR Newswire and is a member of the Forbes Agency Council. She received her B.A. in Communications and Public Relations from Millikin University. This article has been fact-checked, ensuring the accuracy of any cited facts and confirming the authority of its sources. This article has been viewed 410,963 times.

Case studies are used in many professional education programs, primarily in business school, to present real-world situations to students and to assess their ability to parse out the important aspects of a given dilemma. In general, a case study should include, in order: background on the business environment, description of the given business, identification of a key problem or issue, steps taken to address the issue, your assessment of that response, and suggestions for better business strategy. The steps below will guide you through the process of analyzing a business case study in this way.

• Describe the nature of the organization under consideration and its competitors. Provide general information about the market and customer base. Indicate any significant changes in the business environment or any new endeavors upon which the business is embarking.

• Analyze its management structure, employee base, and financial history. Describe annual revenues and profit. Provide figures on employment. Include details about private ownership, public ownership, and investment holdings. Provide a brief overview of the business's leaders and command chain.

• In all likelihood, there will be several different factors at play. Decide which is the main concern of the case study by examining what most of the data talks about, the main problems facing the business, and the conclusions at the end of the study. Examples might include expansion into a new market, response to a competitor's marketing campaign, or a changing customer base. [3] X Research source

• Draw on the information you gathered and trace a chronological progression of steps taken (or not taken). Cite data included in the case study, such as increased marketing spending, purchasing of new property, changed revenue streams, etc.

• Indicate whether or not each aspect of the response met its goal and whether the response overall was well-crafted. Use numerical benchmarks, like a desired customer share, to show whether goals were met; analyze broader issues, like employee management policies, to talk about the response as a whole. [4] X Research source

• Suggest alternative or improved measures that could have been taken by the business, using specific examples and backing up your suggestions with data and calculations.

Community Q&A

• Always read a case study several times. At first, you should read just for the basic details. On each subsequent reading, look for details about a specific topic: competitors, business strategy, management structure, financial loss. Highlight phrases and sections relating to these topics and take notes. Thanks Helpful 0 Not Helpful 0
• In the preliminary stages of analyzing a case study, no detail is insignificant. The biggest numbers can often be misleading, and the point of an analysis is often to dig deeper and find otherwise unnoticed variables that drive a situation. Thanks Helpful 0 Not Helpful 0
• If you are analyzing a case study for a consulting company interview, be sure to direct your comments towards the matters handled by the company. For example, if the company deals with marketing strategy, focus on the business's successes and failures in marketing; if you are interviewing for a financial consulting job, analyze how well the business keeps their books and their investment strategy. Thanks Helpful 0 Not Helpful 0

• Do not use impassioned or emphatic language in your analysis. Business case studies are a tool for gauging your business acumen, not your personal beliefs. When assigning blame or identifying flaws in strategy, use a detached, disinterested tone. Thanks Helpful 15 Not Helpful 4

Things You'll Need

You might also like.

Expert Interview

Thanks for reading our article! If you’d like to learn more about business writing, check out our in-depth interview with Sarah Evans .

• ↑ https://www.gvsu.edu/cms4/asset/CC3BFEEB-C364-E1A1-A5390F221AC0FD2D/business_case_analysis_gg_final.pdf
• ↑ https://bizfluent.com/12741914/how-to-analyze-a-business-case-study
• ↑ http://www.business-fundas.com/2009/how-to-analyze-business-case-studies/
• ↑ https://writingcenter.uagc.edu/writing-case-study-analysis
• http://college.cengage.com/business/resources/casestudies/students/analyzing.htm

About This Article

• Send fan mail to authors

Reader Success Stories

Lisa Upshur

Jun 15, 2019

Did this article help you?

Tejiri Aren

Jul 21, 2016

Jul 15, 2017

Jenn M.T. Tseka

Jul 3, 2016

Devanand Sbuurayan

Dec 6, 2020

Featured Articles

Trending Articles

Watch Articles

• Terms of Use
• Privacy Policy
• Do Not Sell or Share My Info
• Not Selling Info

Don’t miss out! Sign up for

wikiHow’s newsletter

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.

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

Case Studies: How to analyse a case study

• What are Case Studies?
• Finding Case Studies
• In Journal Articles
• How to analyse a case study
• Major Case Study Providers
• Irish companies
• Teaching with Case Studies

Links for Analysing case studies

• Case Studies A useful Cengage Learning guide to analyzing and writing case studies.
• How to Analyze a Case Study By Pearson Prentice Hall.
• Guide to Case Analysis By McGraw Hill College Division.
• Case Study Analysis from About.com

Case Study Analysis

• MBA Depot - Guide to Case Analysis
• University of Auckland Library case study guide
• Penn State Universtity Case Writing Guide
• << Previous: In Journal Articles
• Next: Videos >>
• Last Updated: Mar 1, 2024 2:05 PM
• URL: https://ait.libguides.com/casestudies

• 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.”

• 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

Do Your Students Know How to Analyze a Case—Really?

Explore more.

• Case Teaching
• Student Engagement

J ust as actors, athletes, and musicians spend thousands of hours practicing their craft, business students benefit from practicing their critical-thinking and decision-making skills. Students, however, often have limited exposure to real-world problem-solving scenarios; they need more opportunities to practice tackling tough business problems and deciding on—and executing—the best solutions.

To ensure students have ample opportunity to develop these critical-thinking and decision-making skills, we believe business faculty should shift from teaching mostly principles and ideas to mostly applications and practices. And in doing so, they should emphasize the case method, which simulates real-world management challenges and opportunities for students.

To help educators facilitate this shift and help students get the most out of case-based learning, we have developed a framework for analyzing cases. We call it PACADI (Problem, Alternatives, Criteria, Analysis, Decision, Implementation); it can improve learning outcomes by helping students better solve and analyze business problems, make decisions, and develop and implement strategy. Here, we’ll explain why we developed this framework, how it works, and what makes it an effective learning tool.

The Case for Cases: Helping Students Think Critically

Business students must develop critical-thinking and analytical skills, which are essential to their ability to make good decisions in functional areas such as marketing, finance, operations, and information technology, as well as to understand the relationships among these functions. For example, the decisions a marketing manager must make include strategic planning (segments, products, and channels); execution (digital messaging, media, branding, budgets, and pricing); and operations (integrated communications and technologies), as well as how to implement decisions across functional areas.

Faculty can use many types of cases to help students develop these skills. These include the prototypical “paper cases”; live cases , which feature guest lecturers such as entrepreneurs or corporate leaders and on-site visits; and multimedia cases , which immerse students into real situations. Most cases feature an explicit or implicit decision that a protagonist—whether it is an individual, a group, or an organization—must make.

For students new to learning by the case method—and even for those with case experience—some common issues can emerge; these issues can sometimes be a barrier for educators looking to ensure the best possible outcomes in their case classrooms. Unsure of how to dig into case analysis on their own, students may turn to the internet or rely on former students for “answers” to assigned cases. Or, when assigned to provide answers to assignment questions in teams, students might take a divide-and-conquer approach but not take the time to regroup and provide answers that are consistent with one other.

To help address these issues, which we commonly experienced in our classes, we wanted to provide our students with a more structured approach for how they analyze cases—and to really think about making decisions from the protagonists’ point of view. We developed the PACADI framework to address this need.

PACADI: A Six-Step Decision-Making Approach

The PACADI framework is a six-step decision-making approach that can be used in lieu of traditional end-of-case questions. It offers a structured, integrated, and iterative process that requires students to analyze case information, apply business concepts to derive valuable insights, and develop recommendations based on these insights.

Prior to beginning a PACADI assessment, which we’ll outline here, students should first prepare a two-paragraph summary—a situation analysis—that highlights the key case facts. Then, we task students with providing a five-page PACADI case analysis (excluding appendices) based on the following six steps.

Step 1: Problem definition. What is the major challenge, problem, opportunity, or decision that has to be made? If there is more than one problem, choose the most important one. Often when solving the key problem, other issues will surface and be addressed. The problem statement may be framed as a question; for example, How can brand X improve market share among millennials in Canada? Usually the problem statement has to be re-written several times during the analysis of a case as students peel back the layers of symptoms or causation.

Step 2: Alternatives. Identify in detail the strategic alternatives to address the problem; three to five options generally work best. Alternatives should be mutually exclusive, realistic, creative, and feasible given the constraints of the situation. Doing nothing or delaying the decision to a later date are not considered acceptable alternatives.

Step 3: Criteria. What are the key decision criteria that will guide decision-making? In a marketing course, for example, these may include relevant marketing criteria such as segmentation, positioning, advertising and sales, distribution, and pricing. Financial criteria useful in evaluating the alternatives should be included—for example, income statement variables, customer lifetime value, payback, etc. Students must discuss their rationale for selecting the decision criteria and the weights and importance for each factor.

Step 4: Analysis. Provide an in-depth analysis of each alternative based on the criteria chosen in step three. Decision tables using criteria as columns and alternatives as rows can be helpful. The pros and cons of the various choices as well as the short- and long-term implications of each may be evaluated. Best, worst, and most likely scenarios can also be insightful.

Step 5: Decision. Students propose their solution to the problem. This decision is justified based on an in-depth analysis. Explain why the recommendation made is the best fit for the criteria.

Step 6: Implementation plan. Sound business decisions may fail due to poor execution. To enhance the likeliness of a successful project outcome, students describe the key steps (activities) to implement the recommendation, timetable, projected costs, expected competitive reaction, success metrics, and risks in the plan.

“Students note that using the PACADI framework yields ‘aha moments’—they learned something surprising in the case that led them to think differently about the problem and their proposed solution.”

PACADI’s Benefits: Meaningfully and Thoughtfully Applying Business Concepts

The PACADI framework covers all of the major elements of business decision-making, including implementation, which is often overlooked. By stepping through the whole framework, students apply relevant business concepts and solve management problems via a systematic, comprehensive approach; they’re far less likely to surface piecemeal responses.

As students explore each part of the framework, they may realize that they need to make changes to a previous step. For instance, when working on implementation, students may realize that the alternative they selected cannot be executed or will not be profitable, and thus need to rethink their decision. Or, they may discover that the criteria need to be revised since the list of decision factors they identified is incomplete (for example, the factors may explain key marketing concerns but fail to address relevant financial considerations) or is unrealistic (for example, they suggest a 25 percent increase in revenues without proposing an increased promotional budget).

In addition, the PACADI framework can be used alongside quantitative assignments, in-class exercises, and business and management simulations. The structured, multi-step decision framework encourages careful and sequential analysis to solve business problems. Incorporating PACADI as an overarching decision-making method across different projects will ultimately help students achieve desired learning outcomes. As a practical “beyond-the-classroom” tool, the PACADI framework is not a contrived course assignment; it reflects the decision-making approach that managers, executives, and entrepreneurs exercise daily. Case analysis introduces students to the real-world process of making business decisions quickly and correctly, often with limited information. This framework supplies an organized and disciplined process that students can readily defend in writing and in class discussions.

PACADI in Action: An Example

Here’s an example of how students used the PACADI framework for a recent case analysis on CVS, a large North American drugstore chain.

The CVS Prescription for Customer Value*

PACADI Stage

Summary Response

How should CVS Health evolve from the “drugstore of your neighborhood” to the “drugstore of your future”?

Alternatives

A1. Kaizen (continuous improvement)

A2. Product development

A3. Market development

A4. Personalization (micro-targeting)

Criteria (include weights)

C1. Customer value: service, quality, image, and price (40%)

C2. Customer obsession (20%)

C3. Growth through related businesses (20%)

C4. Customer retention and customer lifetime value (20%)

Each alternative was analyzed by each criterion using a Customer Value Assessment Tool

Alternative 4 (A4): Personalization was selected. This is operationalized via: segmentation—move toward segment-of-1 marketing; geodemographics and lifestyle emphasis; predictive data analysis; relationship marketing; people, principles, and supply chain management; and exceptional customer service.

Implementation

Partner with leading medical school

Curbside pick-up

Pet pharmacy

E-newsletter for customers and employees

Employee incentive program

CVS beauty days

Expand to Latin America and Caribbean

Healthier/happier corner

Holiday toy drives/community outreach

*Source: A. Weinstein, Y. Rodriguez, K. Sims, R. Vergara, “The CVS Prescription for Superior Customer Value—A Case Study,” Back to the Future: Revisiting the Foundations of Marketing from Society for Marketing Advances, West Palm Beach, FL (November 2, 2018).

Results of Using the PACADI Framework

When faculty members at our respective institutions at Nova Southeastern University (NSU) and the University of North Carolina Wilmington have used the PACADI framework, our classes have been more structured and engaging. Students vigorously debate each element of their decision and note that this framework yields an “aha moment”—they learned something surprising in the case that led them to think differently about the problem and their proposed solution.

These lively discussions enhance individual and collective learning. As one external metric of this improvement, we have observed a 2.5 percent increase in student case grade performance at NSU since this framework was introduced.

Tips to Get Started

The PACADI approach works well in in-person, online, and hybrid courses. This is particularly important as more universities have moved to remote learning options. Because students have varied educational and cultural backgrounds, work experience, and familiarity with case analysis, we recommend that faculty members have students work on their first case using this new framework in small teams (two or three students). Additional analyses should then be solo efforts.

To use PACADI effectively in your classroom, we suggest the following:

Advise your students that your course will stress critical thinking and decision-making skills, not just course concepts and theory.

Use a varied mix of case studies. As marketing professors, we often address consumer and business markets; goods, services, and digital commerce; domestic and global business; and small and large companies in a single MBA course.

As a starting point, provide a short explanation (about 20 to 30 minutes) of the PACADI framework with a focus on the conceptual elements. You can deliver this face to face or through videoconferencing.

Give students an opportunity to practice the case analysis methodology via an ungraded sample case study. Designate groups of five to seven students to discuss the case and the six steps in breakout sessions (in class or via Zoom).

Ensure case analyses are weighted heavily as a grading component. We suggest 30–50 percent of the overall course grade.

Once cases are graded, debrief with the class on what they did right and areas needing improvement (30- to 40-minute in-person or Zoom session).

Encourage faculty teams that teach common courses to build appropriate instructional materials, grading rubrics, videos, sample cases, and teaching notes.

When selecting case studies, we have found that the best ones for PACADI analyses are about 15 pages long and revolve around a focal management decision. This length provides adequate depth yet is not protracted. Some of our tested and favorite marketing cases include Brand W , Hubspot , Kraft Foods Canada , TRSB(A) , and Whiskey & Cheddar .

Art Weinstein , Ph.D., is a professor of marketing at Nova Southeastern University, Fort Lauderdale, Florida. He has published more than 80 scholarly articles and papers and eight books on customer-focused marketing strategy. His latest book is Superior Customer Value—Finding and Keeping Customers in the Now Economy . Dr. Weinstein has consulted for many leading technology and service companies.

Herbert V. Brotspies , D.B.A., is an adjunct professor of marketing at Nova Southeastern University. He has over 30 years’ experience as a vice president in marketing, strategic planning, and acquisitions for Fortune 50 consumer products companies working in the United States and internationally. His research interests include return on marketing investment, consumer behavior, business-to-business strategy, and strategic planning.

John T. Gironda , Ph.D., is an assistant professor of marketing at the University of North Carolina Wilmington. His research has been published in Industrial Marketing Management, Psychology & Marketing , and Journal of Marketing Management . He has also presented at major marketing conferences including the American Marketing Association, Academy of Marketing Science, and Society for Marketing Advances.

Related Articles

We use cookies to understand how you use our site and to improve your experience, including personalizing content. Learn More . By continuing to use our site, you accept our use of cookies and revised Privacy Policy .

We use essential cookies to make Venngage work. By clicking “Accept All Cookies”, you agree to the storing of cookies on your device to enhance site navigation, analyze site usage, and assist in our marketing efforts.

Manage Cookies

Cookies and similar technologies collect certain information about how you’re using our website. Some of them are essential, and without them you wouldn’t be able to use Venngage. But others are optional, and you get to choose whether we use them or not.

Strictly Necessary Cookies

These cookies are always on, as they’re essential for making Venngage work, and making it safe. Without these cookies, services you’ve asked for can’t be provided.

Show cookie providers

• Google Login

Functionality Cookies

These cookies help us provide enhanced functionality and personalisation, and remember your settings. They may be set by us or by third party providers.

Performance Cookies

These cookies help us analyze how many people are using Venngage, where they come from and how they're using it. If you opt out of these cookies, we can’t get feedback to make Venngage better for you and all our users.

• Google Analytics

Targeting Cookies

These cookies are set by our advertising partners to track your activity and show you relevant Venngage ads on other sites as you browse the internet.

• Google Tag Manager
• Infographics
• Daily Infographics
• Template Lists
• Graphic Design
• Graphs and Charts
• Data Visualization
• Human Resources
• Beginner Guides

Blog Business

How to Present a Case Study like a Pro (With Examples)

By Danesh Ramuthi , Sep 07, 2023

Okay, let’s get real: case studies can be kinda snooze-worthy. But guess what? They don’t have to be!

In this article, I will cover every element that transforms a mere report into a compelling case study, from selecting the right metrics to using persuasive narrative techniques.

And if you’re feeling a little lost, don’t worry! There are cool tools like Venngage’s Case Study Creator to help you whip up something awesome, even if you’re short on time. Plus, the pre-designed case study templates are like instant polish because let’s be honest, everyone loves a shortcut.

Click to jump ahead: 

What is a case study presentation?

What is the purpose of presenting a case study, how to structure a case study presentation, how long should a case study presentation be, 5 case study presentation examples with templates, 6 tips for delivering an effective case study presentation, 5 common mistakes to avoid in a case study presentation, how to present a case study faqs.

A case study presentation involves a comprehensive examination of a specific subject, which could range from an individual, group, location, event, organization or phenomenon.

They’re like puzzles you get to solve with the audience, all while making you think outside the box.

Unlike a basic report or whitepaper, the purpose of a case study presentation is to stimulate critical thinking among the viewers. 

The primary objective of a case study is to provide an extensive and profound comprehension of the chosen topic. You don’t just throw numbers at your audience. You use examples and real-life cases to make you think and see things from different angles.

The primary purpose of presenting a case study is to offer a comprehensive, evidence-based argument that informs, persuades and engages your audience.

Here’s the juicy part: presenting that case study can be your secret weapon. Whether you’re pitching a groundbreaking idea to a room full of suits or trying to impress your professor with your A-game, a well-crafted case study can be the magic dust that sprinkles brilliance over your words.

Think of it like digging into a puzzle you can’t quite crack . A case study lets you explore every piece, turn it over and see how it fits together. This close-up look helps you understand the whole picture, not just a blurry snapshot.

It’s also your chance to showcase how you analyze things, step by step, until you reach a conclusion. It’s all about being open and honest about how you got there.

Besides, presenting a case study gives you an opportunity to connect data and real-world scenarios in a compelling narrative. It helps to make your argument more relatable and accessible, increasing its impact on your audience.

One of the contexts where case studies can be very helpful is during the job interview. In some job interviews, you as candidates may be asked to present a case study as part of the selection process.

Having a case study presentation prepared allows the candidate to demonstrate their ability to understand complex issues, formulate strategies and communicate their ideas effectively.

The way you present a case study can make all the difference in how it’s received. A well-structured presentation not only holds the attention of your audience but also ensures that your key points are communicated clearly and effectively.

In this section, let’s go through the key steps that’ll help you structure your case study presentation for maximum impact.

Let’s get into it. 

Open with an introductory overview 

Start by introducing the subject of your case study and its relevance. Explain why this case study is important and who would benefit from the insights gained. This is your opportunity to grab your audience’s attention.

Explain the problem in question

Dive into the problem or challenge that the case study focuses on. Provide enough background information for the audience to understand the issue. If possible, quantify the problem using data or metrics to show the magnitude or severity.

Detail the solutions to solve the problem

After outlining the problem, describe the steps taken to find a solution. This could include the methodology, any experiments or tests performed and the options that were considered. Make sure to elaborate on why the final solution was chosen over the others.

Key stakeholders Involved

Talk about the individuals, groups or organizations that were directly impacted by or involved in the problem and its solution. 

Stakeholders may experience a range of outcomes—some may benefit, while others could face setbacks.

For example, in a business transformation case study, employees could face job relocations or changes in work culture, while shareholders might be looking at potential gains or losses.

Discuss the key results & outcomes

Discuss the results of implementing the solution. Use data and metrics to back up your statements. Did the solution meet its objectives? What impact did it have on the stakeholders? Be honest about any setbacks or areas for improvement as well.

Include visuals to support your analysis

Visual aids can be incredibly effective in helping your audience grasp complex issues. Utilize charts, graphs, images or video clips to supplement your points. Make sure to explain each visual and how it contributes to your overall argument.

Pie charts illustrate the proportion of different components within a whole, useful for visualizing market share, budget allocation or user demographics.

This is particularly useful especially if you’re displaying survey results in your case study presentation.

Stacked charts on the other hand are perfect for visualizing composition and trends. This is great for analyzing things like customer demographics, product breakdowns or budget allocation in your case study.

Consider this example of a stacked bar chart template. It provides a straightforward summary of the top-selling cake flavors across various locations, offering a quick and comprehensive view of the data.

Not the chart you’re looking for? Browse Venngage’s gallery of chart templates to find the perfect one that’ll captivate your audience and level up your data storytelling.

Recommendations and next steps

Wrap up by providing recommendations based on the case study findings. Outline the next steps that stakeholders should take to either expand on the success of the project or address any remaining challenges.

Acknowledgments and references

Thank the people who contributed to the case study and helped in the problem-solving process. Cite any external resources, reports or data sets that contributed to your analysis.

Feedback & Q&A session

Open the floor for questions and feedback from your audience. This allows for further discussion and can provide additional insights that may not have been considered previously.

Closing remarks

Conclude the presentation by summarizing the key points and emphasizing the takeaways. Thank your audience for their time and participation and express your willingness to engage in further discussions or collaborations on the subject.

Well, the length of a case study presentation can vary depending on the complexity of the topic and the needs of your audience. However, a typical business or academic presentation often lasts between 15 to 30 minutes. 

This time frame usually allows for a thorough explanation of the case while maintaining audience engagement. However, always consider leaving a few minutes at the end for a Q&A session to address any questions or clarify points made during the presentation.

When it comes to presenting a compelling case study, having a well-structured template can be a game-changer. 

It helps you organize your thoughts, data and findings in a coherent and visually pleasing manner. 

Not all case studies are created equal and different scenarios require distinct approaches for maximum impact. 

To save you time and effort, I have curated a list of 5 versatile case study presentation templates, each designed for specific needs and audiences. 

Here are some best case study presentation examples that showcase effective strategies for engaging your audience and conveying complex information clearly.

1 . Lab report case study template

Ever feel like your research gets lost in a world of endless numbers and jargon? Lab case studies are your way out!

Think of it as building a bridge between your cool experiment and everyone else. It’s more than just reporting results – it’s explaining the “why” and “how” in a way that grabs attention and makes sense.

This lap report template acts as a blueprint for your report, guiding you through each essential section (introduction, methods, results, etc.) in a logical order.

Want to present your research like a pro? Browse our research presentation template gallery for creative inspiration!

2. Product case study template

It’s time you ditch those boring slideshows and bullet points because I’ve got a better way to win over clients: product case study templates.

Instead of just listing features and benefits, you get to create a clear and concise story that shows potential clients exactly what your product can do for them. It’s like painting a picture they can easily visualize, helping them understand the value your product brings to the table.

Grab the template below, fill in the details, and watch as your product’s impact comes to life!

3. Content marketing case study template

In digital marketing, showcasing your accomplishments is as vital as achieving them. 

A well-crafted case study not only acts as a testament to your successes but can also serve as an instructional tool for others. 

With this coral content marketing case study template—a perfect blend of vibrant design and structured documentation, you can narrate your marketing triumphs effectively.

4. Case study psychology template

Understanding how people tick is one of psychology’s biggest quests and case studies are like magnifying glasses for the mind. They offer in-depth looks at real-life behaviors, emotions and thought processes, revealing fascinating insights into what makes us human.

Writing a top-notch case study, though, can be a challenge. It requires careful organization, clear presentation and meticulous attention to detail. That’s where a good case study psychology template comes in handy.

Think of it as a helpful guide, taking care of formatting and structure while you focus on the juicy content. No more wrestling with layouts or margins – just pour your research magic into crafting a compelling narrative.

5. Lead generation case study template

Lead generation can be a real head-scratcher. But here’s a little help: a lead generation case study.

Think of it like a friendly handshake and a confident resume all rolled into one. It’s your chance to showcase your expertise, share real-world successes and offer valuable insights. Potential clients get to see your track record, understand your approach and decide if you’re the right fit.

No need to start from scratch, though. This lead generation case study template guides you step-by-step through crafting a clear, compelling narrative that highlights your wins and offers actionable tips for others. Fill in the gaps with your specific data and strategies, and voilà! You’ve got a powerful tool to attract new customers.

Related: 15+ Professional Case Study Examples [Design Tips + Templates]

So, you’ve spent hours crafting the perfect case study and are now tasked with presenting it. Crafting the case study is only half the battle; delivering it effectively is equally important. 

Whether you’re facing a room of executives, academics or potential clients, how you present your findings can make a significant difference in how your work is received. 

Forget boring reports and snooze-inducing presentations! Let’s make your case study sing. Here are some key pointers to turn information into an engaging and persuasive performance:

• Know your audience : Tailor your presentation to the knowledge level and interests of your audience. Remember to use language and examples that resonate with them.
• Rehearse : Rehearsing your case study presentation is the key to a smooth delivery and for ensuring that you stay within the allotted time. Practice helps you fine-tune your pacing, hone your speaking skills with good word pronunciations and become comfortable with the material, leading to a more confident, conversational and effective presentation.
• Start strong : Open with a compelling introduction that grabs your audience’s attention. You might want to use an interesting statistic, a provocative question or a brief story that sets the stage for your case study.
• Be clear and concise : Avoid jargon and overly complex sentences. Get to the point quickly and stay focused on your objectives.
• Use visual aids : Incorporate slides with graphics, charts or videos to supplement your verbal presentation. Make sure they are easy to read and understand.
• Tell a story : Use storytelling techniques to make the case study more engaging. A well-told narrative can help you make complex data more relatable and easier to digest.

Ditching the dry reports and slide decks? Venngage’s case study templates let you wow customers with your solutions and gain insights to improve your business plan. Pre-built templates, visual magic and customer captivation – all just a click away. Go tell your story and watch them say “wow!”

Nailed your case study, but want to make your presentation even stronger? Avoid these common mistakes to ensure your audience gets the most out of it:

Overloading with information

A case study is not an encyclopedia. Overloading your presentation with excessive data, text or jargon can make it cumbersome and difficult for the audience to digest the key points. Stick to what’s essential and impactful. Need help making your data clear and impactful? Our data presentation templates can help! Find clear and engaging visuals to showcase your findings.

Lack of structure

Jumping haphazardly between points or topics can confuse your audience. A well-structured presentation, with a logical flow from introduction to conclusion, is crucial for effective communication.

Ignoring the audience

Different audiences have different needs and levels of understanding. Failing to adapt your presentation to your audience can result in a disconnect and a less impactful presentation.

Poor visual elements

While content is king, poor design or lack of visual elements can make your case study dull or hard to follow. Make sure you use high-quality images, graphs and other visual aids to support your narrative.

Not focusing on results

A case study aims to showcase a problem and its solution, but what most people care about are the results. Failing to highlight or adequately explain the outcomes can make your presentation fall flat.

How to start a case study presentation?

Starting a case study presentation effectively involves a few key steps:

• Grab attention : Open with a hook—an intriguing statistic, a provocative question or a compelling visual—to engage your audience from the get-go.
• Set the stage : Briefly introduce the subject, context and relevance of the case study to give your audience an idea of what to expect.
• Outline objectives : Clearly state what the case study aims to achieve. Are you solving a problem, proving a point or showcasing a success?
• Agenda : Give a quick outline of the key sections or topics you’ll cover to help the audience follow along.
• Set expectations : Let your audience know what you want them to take away from the presentation, whether it’s knowledge, inspiration or a call to action.

How to present a case study on PowerPoint and on Google Slides?

Presenting a case study on PowerPoint and Google Slides involves a structured approach for clarity and impact using presentation slides :

• Title slide : Start with a title slide that includes the name of the case study, your name and any relevant institutional affiliations.
• Introduction : Follow with a slide that outlines the problem or situation your case study addresses. Include a hook to engage the audience.
• Objectives : Clearly state the goals of the case study in a dedicated slide.
• Findings : Use charts, graphs and bullet points to present your findings succinctly.
• Analysis : Discuss what the findings mean, drawing on supporting data or secondary research as necessary.
• Conclusion : Summarize key takeaways and results.
• Q&A : End with a slide inviting questions from the audience.

What’s the role of analysis in a case study presentation?

The role of analysis in a case study presentation is to interpret the data and findings, providing context and meaning to them. 

It helps your audience understand the implications of the case study, connects the dots between the problem and the solution and may offer recommendations for future action.

Is it important to include real data and results in the presentation?

Yes, including real data and results in a case study presentation is crucial to show experience,  credibility and impact. Authentic data lends weight to your findings and conclusions, enabling the audience to trust your analysis and take your recommendations more seriously

How do I conclude a case study presentation effectively?

To conclude a case study presentation effectively, summarize the key findings, insights and recommendations in a clear and concise manner. 

End with a strong call-to-action or a thought-provoking question to leave a lasting impression on your audience.

What’s the best way to showcase data in a case study presentation ?

The best way to showcase data in a case study presentation is through visual aids like charts, graphs and infographics which make complex information easily digestible, engaging and creative. 

Don’t just report results, visualize them! This template for example lets you transform your social media case study into a captivating infographic that sparks conversation.

Choose the type of visual that best represents the data you’re showing; for example, use bar charts for comparisons or pie charts for parts of a whole. 

Ensure that the visuals are high-quality and clearly labeled, so the audience can quickly grasp the key points. 

Keep the design consistent and simple, avoiding clutter or overly complex visuals that could distract from the message.

Choose a template that perfectly suits your case study where you can utilize different visual aids for maximum impact. 

Need more inspiration on how to turn numbers into impact with the help of infographics? Our ready-to-use infographic templates take the guesswork out of creating visual impact for your case studies with just a few clicks.

Related: 10+ Case Study Infographic Templates That Convert

Congrats on mastering the art of compelling case study presentations! This guide has equipped you with all the essentials, from structure and nuances to avoiding common pitfalls. You’re ready to impress any audience, whether in the boardroom, the classroom or beyond.

And remember, you’re not alone in this journey. Venngage’s Case Study Creator is your trusty companion, ready to elevate your presentations from ordinary to extraordinary. So, let your confidence shine, leverage your newly acquired skills and prepare to deliver presentations that truly resonate.

Go forth and make a lasting impact!

How to write a case study — examples, templates, and tools

It’s a marketer’s job to communicate the effectiveness of a product or service to potential and current customers to convince them to buy and keep business moving. One of the best methods for doing this is to share success stories that are relatable to prospects and customers based on their pain points, experiences, and overall needs.

That’s where case studies come in. Case studies are an essential part of a content marketing plan. These in-depth stories of customer experiences are some of the most effective at demonstrating the value of a product or service. Yet many marketers don’t use them, whether because of their regimented formats or the process of customer involvement and approval.

A case study is a powerful tool for showcasing your hard work and the success your customer achieved. But writing a great case study can be difficult if you’ve never done it before or if it’s been a while. This guide will show you how to write an effective case study and provide real-world examples and templates that will keep readers engaged and support your business.

In this article, you’ll learn:

What is a case study?

How to write a case study, case study templates, case study examples, case study tools.

A case study is the detailed story of a customer’s experience with a product or service that demonstrates their success and often includes measurable outcomes. Case studies are used in a range of fields and for various reasons, from business to academic research. They’re especially impactful in marketing as brands work to convince and convert consumers with relatable, real-world stories of actual customer experiences.

The best case studies tell the story of a customer’s success, including the steps they took, the results they achieved, and the support they received from a brand along the way. To write a great case study, you need to:

• Celebrate the customer and make them — not a product or service — the star of the story.
• Craft the story with specific audiences or target segments in mind so that the story of one customer will be viewed as relatable and actionable for another customer.
• Write copy that is easy to read and engaging so that readers will gain the insights and messages intended.
• Follow a standardized format that includes all of the essentials a potential customer would find interesting and useful.
• Support all of the claims for success made in the story with data in the forms of hard numbers and customer statements.

Case studies are a type of review but more in depth, aiming to show — rather than just tell — the positive experiences that customers have with a brand. Notably, 89% of consumers read reviews before deciding to buy, and 79% view case study content as part of their purchasing process. When it comes to B2B sales, 52% of buyers rank case studies as an important part of their evaluation process.

Telling a brand story through the experience of a tried-and-true customer matters. The story is relatable to potential new customers as they imagine themselves in the shoes of the company or individual featured in the case study. Showcasing previous customers can help new ones see themselves engaging with your brand in the ways that are most meaningful to them.

Besides sharing the perspective of another customer, case studies stand out from other content marketing forms because they are based on evidence. Whether pulling from client testimonials or data-driven results, case studies tend to have more impact on new business because the story contains information that is both objective (data) and subjective (customer experience) — and the brand doesn’t sound too self-promotional.

Case studies are unique in that there’s a fairly standardized format for telling a customer’s story. But that doesn’t mean there isn’t room for creativity. It’s all about making sure that teams are clear on the goals for the case study — along with strategies for supporting content and channels — and understanding how the story fits within the framework of the company’s overall marketing goals.

Here are the basic steps to writing a good case study.

1. Identify your goal

Start by defining exactly who your case study will be designed to help. Case studies are about specific instances where a company works with a customer to achieve a goal. Identify which customers are likely to have these goals, as well as other needs the story should cover to appeal to them.

The answer is often found in one of the buyer personas that have been constructed as part of your larger marketing strategy. This can include anything from new leads generated by the marketing team to long-term customers that are being pressed for cross-sell opportunities. In all of these cases, demonstrating value through a relatable customer success story can be part of the solution to conversion.

2. Choose your client or subject

Who you highlight matters. Case studies tie brands together that might otherwise not cross paths. A writer will want to ensure that the highlighted customer aligns with their own company’s brand identity and offerings. Look for a customer with positive name recognition who has had great success with a product or service and is willing to be an advocate.

The client should also match up with the identified target audience. Whichever company or individual is selected should be a reflection of other potential customers who can see themselves in similar circumstances, having the same problems and possible solutions.

Some of the most compelling case studies feature customers who:

• Switch from one product or service to another while naming competitors that missed the mark.
• Experience measurable results that are relatable to others in a specific industry.
• Represent well-known brands and recognizable names that are likely to compel action.
• Advocate for a product or service as a champion and are well-versed in its advantages.

Whoever or whatever customer is selected, marketers must ensure they have the permission of the company involved before getting started. Some brands have strict review and approval procedures for any official marketing or promotional materials that include their name. Acquiring those approvals in advance will prevent any miscommunication or wasted effort if there is an issue with their legal or compliance teams.

3. Conduct research and compile data

Substantiating the claims made in a case study — either by the marketing team or customers themselves — adds validity to the story. To do this, include data and feedback from the client that defines what success looks like. This can be anything from demonstrating return on investment (ROI) to a specific metric the customer was striving to improve. Case studies should prove how an outcome was achieved and show tangible results that indicate to the customer that your solution is the right one.

This step could also include customer interviews. Make sure that the people being interviewed are key stakeholders in the purchase decision or deployment and use of the product or service that is being highlighted. Content writers should work off a set list of questions prepared in advance. It can be helpful to share these with the interviewees beforehand so they have time to consider and craft their responses. One of the best interview tactics to keep in mind is to ask questions where yes and no are not natural answers. This way, your subject will provide more open-ended responses that produce more meaningful content.

4. Choose the right format

There are a number of different ways to format a case study. Depending on what you hope to achieve, one style will be better than another. However, there are some common elements to include, such as:

• An engaging headline
• A subject and customer introduction
• The unique challenge or challenges the customer faced
• The solution the customer used to solve the problem
• The results achieved
• Data and statistics to back up claims of success
• A strong call to action (CTA) to engage with the vendor

It’s also important to note that while case studies are traditionally written as stories, they don’t have to be in a written format. Some companies choose to get more creative with their case studies and produce multimedia content, depending on their audience and objectives. Case study formats can include traditional print stories, interactive web or social content, data-heavy infographics, professionally shot videos, podcasts, and more.

5. Write your case study

We’ll go into more detail later about how exactly to write a case study, including templates and examples. Generally speaking, though, there are a few things to keep in mind when writing your case study.

• Be clear and concise. Readers want to get to the point of the story quickly and easily, and they’ll be looking to see themselves reflected in the story right from the start.
• Provide a big picture. Always make sure to explain who the client is, their goals, and how they achieved success in a short introduction to engage the reader.
• Construct a clear narrative. Stick to the story from the perspective of the customer and what they needed to solve instead of just listing product features or benefits.
• Leverage graphics. Incorporating infographics, charts, and sidebars can be a more engaging and eye-catching way to share key statistics and data in readable ways.
• Offer the right amount of detail. Most case studies are one or two pages with clear sections that a reader can skim to find the information most important to them.
• Include data to support claims. Show real results — both facts and figures and customer quotes — to demonstrate credibility and prove the solution works.

6. Promote your story

Marketers have a number of options for distribution of a freshly minted case study. Many brands choose to publish case studies on their website and post them on social media. This can help support SEO and organic content strategies while also boosting company credibility and trust as visitors see that other businesses have used the product or service.

Marketers are always looking for quality content they can use for lead generation. Consider offering a case study as gated content behind a form on a landing page or as an offer in an email message. One great way to do this is to summarize the content and tease the full story available for download after the user takes an action.

Sales teams can also leverage case studies, so be sure they are aware that the assets exist once they’re published. Especially when it comes to larger B2B sales, companies often ask for examples of similar customer challenges that have been solved.

Now that you’ve learned a bit about case studies and what they should include, you may be wondering how to start creating great customer story content. Here are a couple of templates you can use to structure your case study.

Template 1 — Challenge-solution-result format

• Start with an engaging title. This should be fewer than 70 characters long for SEO best practices. One of the best ways to approach the title is to include the customer’s name and a hint at the challenge they overcame in the end.
• Create an introduction. Lead with an explanation as to who the customer is, the need they had, and the opportunity they found with a specific product or solution. Writers can also suggest the success the customer experienced with the solution they chose.
• Present the challenge. This should be several paragraphs long and explain the problem the customer faced and the issues they were trying to solve. Details should tie into the company’s products and services naturally. This section needs to be the most relatable to the reader so they can picture themselves in a similar situation.
• Share the solution. Explain which product or service offered was the ideal fit for the customer and why. Feel free to delve into their experience setting up, purchasing, and onboarding the solution.
• Explain the results. Demonstrate the impact of the solution they chose by backing up their positive experience with data. Fill in with customer quotes and tangible, measurable results that show the effect of their choice.
• Ask for action. Include a CTA at the end of the case study that invites readers to reach out for more information, try a demo, or learn more — to nurture them further in the marketing pipeline. What you ask of the reader should tie directly into the goals that were established for the case study in the first place.

Template 2 — Data-driven format

• Start with an engaging title. Be sure to include a statistic or data point in the first 70 characters. Again, it’s best to include the customer’s name as part of the title.
• Create an overview. Share the customer’s background and a short version of the challenge they faced. Present the reason a particular product or service was chosen, and feel free to include quotes from the customer about their selection process.
• Present data point 1. Isolate the first metric that the customer used to define success and explain how the product or solution helped to achieve this goal. Provide data points and quotes to substantiate the claim that success was achieved.
• Present data point 2. Isolate the second metric that the customer used to define success and explain what the product or solution did to achieve this goal. Provide data points and quotes to substantiate the claim that success was achieved.
• Present data point 3. Isolate the final metric that the customer used to define success and explain what the product or solution did to achieve this goal. Provide data points and quotes to substantiate the claim that success was achieved.
• Summarize the results. Reiterate the fact that the customer was able to achieve success thanks to a specific product or service. Include quotes and statements that reflect customer satisfaction and suggest they plan to continue using the solution.
• Ask for action. Include a CTA at the end of the case study that asks readers to reach out for more information, try a demo, or learn more — to further nurture them in the marketing pipeline. Again, remember that this is where marketers can look to convert their content into action with the customer.

While templates are helpful, seeing a case study in action can also be a great way to learn. Here are some examples of how Adobe customers have experienced success.

Juniper Networks

One example is the Adobe and Juniper Networks case study , which puts the reader in the customer’s shoes. The beginning of the story quickly orients the reader so that they know exactly who the article is about and what they were trying to achieve. Solutions are outlined in a way that shows Adobe Experience Manager is the best choice and a natural fit for the customer. Along the way, quotes from the client are incorporated to help add validity to the statements. The results in the case study are conveyed with clear evidence of scale and volume using tangible data.

The story of Lenovo’s journey with Adobe is one that spans years of planning, implementation, and rollout. The Lenovo case study does a great job of consolidating all of this into a relatable journey that other enterprise organizations can see themselves taking, despite the project size. This case study also features descriptive headers and compelling visual elements that engage the reader and strengthen the content.

Tata Consulting

When it comes to using data to show customer results, this case study does an excellent job of conveying details and numbers in an easy-to-digest manner. Bullet points at the start break up the content while also helping the reader understand exactly what the case study will be about. Tata Consulting used Adobe to deliver elevated, engaging content experiences for a large telecommunications client of its own — an objective that’s relatable for a lot of companies.

Case studies are a vital tool for any marketing team as they enable you to demonstrate the value of your company’s products and services to others. They help marketers do their job and add credibility to a brand trying to promote its solutions by using the experiences and stories of real customers.

When you’re ready to get started with a case study:

• Think about a few goals you’d like to accomplish with your content.
• Make a list of successful clients that would be strong candidates for a case study.
• Reach out to the client to get their approval and conduct an interview.
• Gather the data to present an engaging and effective customer story.

Adobe can help

There are several Adobe products that can help you craft compelling case studies. Adobe Experience Platform helps you collect data and deliver great customer experiences across every channel. Once you’ve created your case studies, Experience Platform will help you deliver the right information to the right customer at the right time for maximum impact.

To learn more, watch the Adobe Experience Platform story .

Keep in mind that the best case studies are backed by data. That’s where Adobe Real-Time Customer Data Platform and Adobe Analytics come into play. With Real-Time CDP, you can gather the data you need to build a great case study and target specific customers to deliver the content to the right audience at the perfect moment.

Watch the Real-Time CDP overview video to learn more.

Finally, Adobe Analytics turns real-time data into real-time insights. It helps your business collect and synthesize data from multiple platforms to make more informed decisions and create the best case study possible.

Request a demo to learn more about Adobe Analytics.

https://business.adobe.com/blog/perspectives/b2b-ecommerce-10-case-studies-inspire-you

https://business.adobe.com/blog/basics/business-case

https://business.adobe.com/blog/basics/what-is-real-time-analytics

Case Study Analysis: Examples + How-to Guide & Writing Tips

A case study analysis is a typical assignment in business management courses. The task aims to show high school and college students how to analyze a current situation, determine what problems exist, and develop the best possible strategy to achieve the desired outcome.

Our specialists will write a custom essay specially for you!

Many students feel anxious about writing case analyses because being told to analyze a case study and provide a solution can seem like a big task. That is especially so when working with real-life scenarios. However, you can rest assured writing a case analysis paper is easier than you think. Just keep reading this article and you will find case study examples for students and the advice provided by Custom-writing experts!

• 👣 Main Steps
• 🕵 Preparing the Case

🔬 Analyzing the Case

• 📑 Format & Structure
• 🙅 Things to Avoid
• 🏁 Conclusion

🔗 References

👣 writing a case study analysis: main steps.

Business management is built on case analysis. Every single economic result shows that the methods and instruments employed were either well-timed and expedient, in the event of success, or not, in case of failure. These two options indicate whether the strategy is efficient (and should be followed) or requires corrections (or complete change). Such an approach to the case study will make your writing piece more proficient and valuable for the reader. The following steps will direct your plan for writing a case study analysis.

Step 1: Preliminary work

• Make notes and highlight the numbers and ideas that could be quoted.
• Single out as many problems as you can, and briefly mark their underlying issues. Then make a note of those responsible. In the report, you will use two to five of the problems, so you will have a selection to choose from.
• Outline a possible solution to each of the problems you found. Course readings and outside research shall be used here. Highlight your best and worst solution for further reference.

Step 2: Drafting the Case

• Provide a general description of the situation and its history.
• Name all the problems you are going to discuss.
• Specify the theory used for the analysis.
• Present the assumptions that emerged during the analysis, if any.
• Describe the detected problems in more detail.
• Indicate their link to, and effect on, the general situation.
• Explain why the problems emerged and persist.
• List realistic and feasible solutions to the problems you outlined, in the order of importance.
• Specify your predicted results of such changes.
• Support your choice with reliable evidence (i.e., textbook readings, the experience of famous companies, and other external research).
• Define the strategies required to fulfill your proposed solution.
• Indicate the responsible people and the realistic terms for its implementation.
• Recommend the issues for further analysis and supervision.

Step 3: Finalizing the Case

Like any other piece of writing, a case analysis requires post-editing. Carefully read it through, looking for inconsistencies and gaps in meaning. Your purpose is to make it look complete, precise, and convincing.

🕵 Preparing a Case for Analysis

Your professor might give you various case study examples from which to choose, or they may just assign you a particular case study. To conduct a thorough data analysis, you must first read the case study. This might appear to be obvious. However, you’d be surprised at how many students don’t take adequate time to complete this part.

Read the case study very thoroughly, preferably several times. Highlight, underline, flag key information, and make notes to refer to later when you are writing your analysis report.

Just in 1 hour! We will write you a plagiarism-free paper in hardly more than 1 hour

If you don’t have a complete knowledge of the case study your professor has assigned, you won’t conduct a proper analysis of it. Even if you make use of a business case study template or refer to a sample analysis, it won’t help if you aren’t intimately familiar with your case study.

You will also have to conduct research. When it comes to research, you will need to do the following:

• Gather hard, quantitative data (e.g. 67% of the staff participated in the meeting).
• Design research tools , such as questionnaires and surveys (this will aid in gathering data).
• Determine and suggest the best specific, workable solutions.

It would be best if you also learned how to analyze a case study. Once you have read through the case study, you need to determine the focus of your analysis. You can do this by doing the following:

Compare your chosen solutions to the solutions offered by the experts who analyzed the case study you were given or to online assignments for students who were dealing with a similar task. The experts’ solutions will probably be more advanced than yours simply because these people are more experienced. However, don’t let this discourage you; the whole point of doing this analysis is to learn. Use the opportunity to learn from others’ valuable experience, and your results will be better next time.

If you are still in doubt, the University of South Carolina offers a great guide on forming a case study analysis.

Receive a plagiarism-free paper tailored to your instructions. Cut 15% off your first order!

📑 Case Analysis Format & Structure

When you are learning how to write a case study analysis, it is important to get the format of your analysis right. Understanding the case study format is vital for both the professor and the student. The person planning and handing out such an assignment should ensure that the student doesn’t have to use any external sources .

In turn, students have to remember that a well-written case analysis provides all the data, making it unnecessary for the reader to go elsewhere for information.

Regardless of whether you use a case study template, you will need to follow a clear and concise format when writing your analysis report. There are some possible case study frameworks available. Still, a case study should contain eight sections laid out in the following format:

• Describe the purpose of the current case study;
• Provide a summary of the company;
• Briefly introduce the problems and issues found in the case study
• Discuss the theory you will be using in the analysis;
• Present the key points of the study and present any assumptions made during the analysis.
• Present each problem you have singled out;
• Justify your inclusion of each problem by providing supporting evidence from the case study and by discussing relevant theory and what you have learned from your course content;
• Divide the section (and following sections) into subsections, one for each of your selected problems.
• Present a summary of each problem you have identified;
• Present plausible solutions for each of the problems, keeping in mind that each problem will likely have more than one possible solution;
• Provide the pros and cons of each solution in a way that is practical.
• Conclusion . This is a summary of your findings and discussion.
• Decide which solution best fits each of the issues you identified;
• Explain why you chose this solution and how it will effectively solve the problem;
• Be persuasive when you write this section so that you can drive your point home;
• Be sure to bring together theory and what you have learned throughout your course to support your recommendations.
• Provide an explanation of what must be done, who should take action, and when the solution should be carried out;
• Where relevant, you should provide an estimate of the cost in implementing the solution, including both the financial investment and the cost in terms of time.
• References. While you generally do not need to refer to many external sources when writing a case study analysis, you might use a few. When you do, you will need to properly reference these sources, which is most often done in one of the main citation styles, including APA, MLA, or Harvard. There is plenty of help when citing references, and you can follow these APA guidelines , these MLA guidelines , or these Harvard guidelines .
• Appendices. This is the section you include after your case study analysis if you used any original data in the report. These data, presented as charts, graphs, and tables, are included here because to present them in the main body of the analysis would be disruptive to the reader. The University of Southern California provides a great description of appendices and when to make use of them.

When you’ve finished your first draft, be sure to proofread it. Look not only for potential grammar and spelling errors but also for discrepancies or holes in your argument.

You should also know what you need to avoid when writing your analysis.

Get an originally-written paper according to your instructions!

🙅 Things to Avoid in Case Analysis

Whenever you deal with a case study, remember that there are some pitfalls to avoid! Beware of the following mistakes:

• Excessive use of colloquial language . Even though it is a study of an actual case, it should sound formal.
• Lack of statistical data . Give all the important data, both in percentages and in numbers.
• Excessive details. State only the most significant facts, rather than drowning the reader in every fact you find.
• Inconsistency in the methods you have used . In a case study, theory plays a relatively small part, so you must develop a specific case study research methodology.
• Trivial means of research . It is critical that you design your own case study research method in whatever form best suits your analysis, such as questionnaires and surveys.

It is useful to see a few examples of case analysis papers. After all, a sample case study report can provide you with some context so you can see how to approach each aspect of your paper.

👀 Case Study Examples for Students

It might be easier to understand how a case study analysis works if you have an example to look at. Fortunately, examples of case studies are easy to come by. Take a look at this video for a sample case study analysis for the Coca-Cola Company.

If you want another example, then take a look at the one below!

Business Case Analysis: Example

CRM’s primary focus is customers and customer perception of the brand or the company. The focus may shift depending on customers’ needs. The main points that Center Parcs should consider are an increase in customer satisfaction and its market share. Both of these points will enhance customer perception of the product as a product of value. Increased customer satisfaction will indicate that the company provides quality services, and increased market share can reduce the number of switching (or leaving) customers, thus fostering customer loyalty.

Case Study Topics

• Equifax case study: the importance of cybersecurity measures . 
• Study a case illustrating ethical issues of medical research.  
• Examine the case describing the complications connected with nursing and residential care.  
• Analyze the competitive strategy of Delta Airlines . 
• Present a case study of an ethical dilemma showing the conflict between the spirit and the letter of the law.  
• Explore the aspects of Starbucks’ marketing strategyin a case study.  
• Research a case of community-based clinic organization and development.  
• Customer service of United Airlines: a case study . 
• Analyze a specific schizophrenia case and provide your recommendations.  
• Provide a case study of a patient with hyperglycemia.  
• Examine the growth strategy of United Healthcare. 
• Present a case study demonstrating ethical issues in business .  
• Study a case of the 5% shareholding rule application and its impact on the company.  
• Case study of post-traumatic stress disorder . 
• Analyze a case examining the issues of cross-cultural management .  
• Write a case study exploring the ethical issues the finance manager of a long-term care facility can face and the possible reaction to them.  
• Write a case study analyzing the aspects of a new president of a firm election. 
• Discuss the specifics of supply chain management in the case of Tehindo company. 
• Study a case of a life crisis in a family and the ways to cope with it.  
• Case study of Tea Leaves and More: supply chain issues .   
• Explore the case of ketogenic diet implementation among sportspeople.  
• Analyze the case of Webster Jewelry shop and suggest some changes.  
• Examine the unique aspects of Tea and More brand management .  
• Adidas case study: an ethical dilemma .  
• Research the challenges of Brazos Valley Food Bank and suggest possible solutions.  
• Describe the case of dark web monitoring for business.  
• Study a case of permissive parenting style .  
• Case study of Starbucks employees . 
• Analyze a case of workplace discrimination and suggest a strategy to avoid it.  
• Examine a case of the consumer decision-making process and define the factors that influence it.  
• Present a case study of Netflix illustrating the crucial role of management innovation for company development.  
• Discuss a case describing a workplace ethical issue and propose ways to resolve it.  
• Case study of the 2008 financial crisis: Graham’s value investing principles in the modern economic climate. 
• Write a case study analyzing the harmful consequences of communication issues in a virtual team .  
• Analyze a case that highlights the importance of a proper functional currency choice. 
• Examine the case of Hitachi Power Systems management.  
• Present a case study of medication research in a healthcare facility.  
• Study the case of Fiji Water and the challenges the brand faces.  
• Research a social problem case and suggest a solution.  
• Analyze a case that reveals the connection between alcohol use and borderline personality disorder .  
• Transglobal Airline case study: break-even analysis.   
• Examine the case of Chiquita Brands International from the moral and business ethics points of view.  
• Present a case study of applying for Social Security benefits. 
• Study the case of a mass hacker attack on Microsoft clients and suggest possible ways to prevent future attacks.  
• Case study of leadership effectiveness . 
• Analyze a case presenting a clinical moral dilemma and propose ways to resolve it. 
• Describe the case of Cowbell Brewing Company and discuss the strategy that made them successful.  
• Write a case study of WeWork company and analyze the strengths and weaknesses of its strategy.  
• Case study of medical ethical decision-making. 
• Study the case of The Georges hotel and suggest ways to overcome its managerial issues.  

🏁 Concluding Remarks

Writing a case study analysis can seem incredibly overwhelming, especially if you have never done it before. Just remember, you can do it provided you follow a plan, keep to the format described here, and study at least one case analysis example.

If you still need help analyzing a case study, your professor is always available to answer your questions and point you in the right direction. You can also get help with any aspect of the project from a custom writing company. Just tackle the research and hand over the writing, write a rough draft and have it checked by a professional, or completely hand the project off to an expert writer.

Regardless of the path you choose, you will turn in something of which you can be proud!

✏️ Case Study Analysis FAQ

Students (especially those who study business) often need to write a case study analysis. It is a kind of report that describes a business case. It includes multiple aspects, for example, the problems that exist, possible solutions, forecasts, etc.

There should be 3 main points covered in a case study analysis:

• The challenge(s) description,
• Possible solutions,
• Outcomes (real and/or foreseen).

Firstly, study some examples available online and in the library. Case study analysis should be a well-structured paper with all the integral components in place. Thus, you might want to use a template and/or an outline to start correctly.

A case study analysis is a popular task for business students. They typically hand it in the format of a paper with several integral components:

• Description of the problem
• Possible ways out
• Results and/or forecasts

Students sometimes tell about the outcome of their research within an oral presentation.

• Case Study: Academia
• Windows of vulnerability: a case study analysis (IEEE)
• A (Very) Brief Refresher on the Case Study Method: SAGE
• The case study approach: Medical Research Methodology
• Strengths and Limitations of Case Studies: Stanford University
• A Sample APA Paper: Radford University
• How to Write a Case Study APA Style: Seattle PI
• The Case Analysis: GVSU
• How to Outline: Purdue OWL
• Incorporating Interview Data: UW-Madison Writing Center
• Share to Facebook
• Share to Twitter
• Share to LinkedIn
• Share to email

If you are a student, you might need to learn how to write a literature review at some point. But don’t think it’s the same as the book review or other types of academic writing you had to do in high school! A literature review is a close examination of...

So, have you been recently assigned a research project? Or, even worse, is it already due soon? The following research paper hacks will help you do it in record time. In the article, you’ll see ten things you can do to conduct a study and compose a piece like a...

Eating a delicacy, watching a good movie, and proving a point to an audience are the three things that make life seem better. Today, you’ll deal with the last one. You’re about to become a professional at public speaking and attention grabbing. Here, you can learn how to write a...

What is a library research paper? It’s nothing more than an academic writing project that summarizes the information on a specific topic taken from primary and secondary sources. There are numerous library research examples you can find online. But to complete this assignment, you should simply follow these essential steps:...

Do you need to write a research analysis paper but have no idea how to do that? Then you’re in the right place. While completing this type of assignment, your key aim is to critically analyze a research article. An article from a serious scientific journal would be a good...

American Antiquity is a professional quarterly journal, which contains various papers on the American archeology. It is incredibly popular among archeologists and the students majoring in history. The organization adopted the rules of The Society for American Archaeology (SAA) citation style. As a result: The journal includes numerous references that...

The most tedious and time-consuming part of any school or college written assignment is the bibliography. Sometimes, it can even be challenging! For example, if you’re confused by the variety of citation styles. This is probably when the most students wonder “Is there someone who could complete my assignment?” That...

An appendix is the part of the paper that contains supplementary material. The information from an appendix in paper writing is not essential. If the readers ignore this part, they still have to get the paper’s idea. Appendices help the readers to understand the research better. They might be useful...

Writing an abstract is one of the skills you need to master to succeed in your studies. An abstract is a summary of an academic text. It contains information about the aims and the outcomes of the research. The primary purpose of an abstract is to help readers understand what...

So you have to write a literature review. You find your favorite novel and then start analyzing it. This is how it’s usually done, right? It’s not. You have to learn the elements of literature review and how to deal with them.

Only two words, but you already feel a chill down your spine. A research paper is no joke. It’s a super detailed piece of academic writing where you analyze a chosen issue in-depth. The main aim of such torture is to show how knowledgeable you are and that your opinion...

A research proposal is a text that suggests a topic or research problem, justifies the need to study it, and describes the ways and methods of conducting the study. Scholars usually write proposals to get funding for their research. In their turn, students might have to do that to get...

Quite an impressive piece The steps and procedures outlined here are well detailed and the examples facilitates understanding.

it was very helpful. I have an assessment to write where in I need to mention different effective components that are needed to compile a high quality case study assessment.

It is very important and helpful.

Thanks a lot. A knowledge shared with a structured template. Stay the course

Thanks for this valuable knowledge.I loved this. keep sharing. to know more about click Air India Case Study – Why Air India failed ?

This is going to be a great help in my monthly analysis requirements for my subject. Thank you so much.

Thank you very much for this insightful guidelines… It has really been a great tool for writing my project. Thanks once again.

This article was very helpful, even though I’ll have a clearer mind only after I do the case study myself but I felt very much motivated after reading this, as now I can at least have a plan of what to do compared to the clueless me I was before I read it. I hope if I have any questions or doubts about doing a case study I can clear it out here.

• 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]

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.

NTRS - NASA Technical Reports Server

Available downloads, related records.

Help | Advanced Search

Astrophysics > Instrumentation and Methods for Astrophysics

Title: milky way and nearby galaxies science with the single aperture large telescope for universe studies (\textit{saltus}) space observatory.

Abstract: This paper presents an overview of the Milky Way and nearby galaxies science case for the \textit{Single Aperture Large Telescope for Universe Studies} (SALTUS) far-infrared NASA probe-class mission concept. SALTUS offers enormous gains in spatial resolution and spectral sensitivity over previous far-IR missions, thanks to its cold ($<$40~K) 14-m primary mirror. Key Milky Way and nearby galaxies science goals for SALTUS focus on understanding the role of star formation in feedback in the Local Universe. In addition to this science case, SALTUS would open a new window to to of Galactic and extragalactic communities in the 2030s, enable fundamentally new questions to be answered, and be a far-IR analog to the near- and mid-IR capabilities of JWST. This paper summarizes the Milky Way and nearby galaxies science case and plans for notional observing programs in both guaranteed and guest (open) time.

Submission history

Access paper:.

• HTML (experimental)
• Other Formats

References & Citations

• Google Scholar
• Semantic Scholar

BibTeX formatted citation

Bibliographic and Citation Tools

Code, data and media associated with this article, recommenders and search tools.

• Institution

arXivLabs: experimental projects with community collaborators

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.

Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs .