case study of science

• Browse All Articles
• Newsletter Sign-Up

• 23 Apr 2024
• In Practice

Getting to Net Zero: The Climate Standards and Ecosystem the World Needs Now

What can companies and regulators do as climate predictions grow grimmer? They should measure impact, strengthen environmental institutions, and look to cities to lead, say Robert Kaplan, Shirley Lu, and Rosabeth Moss Kanter.

• 22 Apr 2024
• Research & Ideas

When Does Impact Investing Make the Biggest Impact?

More investors want to back businesses that contribute to social change, but are impact funds the only approach? Research by Shawn Cole, Leslie Jeng, Josh Lerner, Natalia Rigol, and Benjamin Roth challenges long-held assumptions about impact investing and reveals where such funds make the biggest difference.

• 18 Mar 2024

When It Comes to Climate Regulation, Energy Companies Take a More Nuanced View

Many assume that major oil and gas companies adamantly oppose climate-friendly regulation, but that's not true. A study of 30 years of corporate advocacy by Jonas Meckling finds that energy companies have backed clean-energy efforts when it aligns with their business interests.

• 12 Mar 2024

How Used Products Can Unlock New Markets: Lessons from Apple's Refurbished iPhones

The idea of reselling old smartphones might have seemed risky for a company known for high-end devices, but refurbished products have become a major profit stream for Apple and an environmental victory. George Serafeim examines Apple's circular model in a case study, and offers insights for other industries.

• 27 Feb 2024
• Cold Call Podcast

How Could Harvard Decarbonize Its Supply Chain?

Harvard University aims to be fossil-fuel neutral by 2026 and totally free of fossil fuels by 2050. As part of this goal, the university is trying to decarbonize its supply chain and considers replacing cement with a low-carbon substitute called Pozzotive®, made with post-consumer recycled glass. A successful pilot project could jump start Harvard’s initiative to reduce embodied carbon emissions, but it first needs credible information about the magnitude and validity of potential carbon reductions. Harvard Business School professor emeritus Robert Kaplan and assistant professor Shirley Lu discuss the flow of emissions along the supply chain of Harvard University’s construction projects, the different methods of measuring carbon emissions, including the E-liability approach, and the opportunity to leverage blockchain technology to facilitate the flow of comparable and reliable emissions information in the case, “Harvard University and Urban Mining Industries: Decarbonizing the Supply Chain.”

• 30 Jan 2024

Can Second-Generation Ethanol Production Help Decarbonize the World?

Raízen, a bioenergy company headquartered in São Paulo, is Brazil’s leader in sugar and ethanol production and the world’s leading ethanol trader. Since its creation in 2011, the company had primarily produced first-generation ethanol (E1G) from sugarcane, a crop that can also be used to produce sugar. In 2015, Raízen also started to produce second-generation ethanol (E2G), a biofuel derived from residual and waste materials, such as cane bagasse and straw – which don’t compete with food production. The company’s growth strategy focused on developing and boosting a low carbon portfolio that focused on E2G, based on the belief that Raízen—and Brazil—could help the world decarbonize and profit from the energy transition. Paula Kovarsky, Raízen’s chief strategy and sustainability officer, was confident the company could become a global green energy champion. But after the board’s approval for the first round of E2G investments, she faced a complex challenge: how to expand the market for second-generation ethanol and other sugar-cane waste biofuels, in order to ensure Raízen’s long-term growth? Harvard Business School professor Gunnar Trumbull and Kovarsky discuss the company’s strategy for bringing second-generation ethanol to the world in the case, “Raízen: Helping to Decarbonize the World?”

• 29 Jan 2024

Do Disasters Rally Support for Climate Action? It's Complicated.

Reactions to devastating wildfires in the Amazon show the contrasting realities for people living in areas vulnerable to climate change. Research by Paula Rettl illustrates the political ramifications that arise as people weigh the economic tradeoffs of natural disasters.

• 17 Jan 2024

Are Companies Getting Away with 'Cheap Talk' on Climate Goals?

Many companies set emissions targets with great fanfare—and never meet them, says research by Shirley Lu and colleagues. But what if investors held businesses accountable for achieving their climate plans?

• 09 Jan 2024

Could Clean Hydrogen Become Affordable at Scale by 2030?

The cost to produce hydrogen could approach the $1-per-kilogram target set by US regulators by 2030, helping this cleaner energy source compete with fossil fuels, says research by Gunther Glenk and colleagues. But planned global investments in hydrogen production would need to come to fruition to reach full potential.

• 02 Jan 2024

Should Businesses Take a Stand on Societal Issues?

Should businesses take a stand for or against particular societal issues? And how should leaders determine when and how to engage on these sensitive matters? Harvard Business School Senior Lecturer Hubert Joly, who led the electronics retailer Best Buy for almost a decade, discusses examples of corporate leaders who had to determine whether and how to engage with humanitarian crises, geopolitical conflict, racial justice, climate change, and more in the case, “Deciding When to Engage on Societal Issues.”

10 Trends to Watch in 2024

Employees may seek new approaches to balance, even as leaders consider whether to bring more teams back to offices or make hybrid work even more flexible. These are just a few trends that Harvard Business School faculty members will be following during a year when staffing, climate, and inclusion will likely remain top of mind.

• 19 Sep 2023

What Chandrayaan-3 Says About India's Entrepreneurial Approach to Space

India reached an unexplored part of the moon despite its limited R&D funding compared with NASA and SpaceX. Tarun Khanna discusses the significance of the landing, and the country's advancements in data and digital technology.

• 12 Sep 2023
• What Do You Think?

Who Gets the Loudest Voice in DEI Decisions?

Business leaders are wrestling with how to manage their organizations' commitment to diversity, equity, and inclusion. If you were a CEO, which constituency would you consider most: your employees, customers, or investors? asks James Heskett. Open for comment; 0 Comments.

• 26 Jul 2023

STEM Needs More Women. Recruiters Often Keep Them Out

Tech companies and programs turn to recruiters to find top-notch candidates, but gender bias can creep in long before women even apply, according to research by Jacqueline Ng Lane and colleagues. She highlights several tactics to make the process more equitable.

• 18 Jul 2023

Will Global Demand for Oil Peak This Decade?

The International Energy Agency expects the world's oil demand to start to ebb in the coming years. However, Joseph Lassiter and Lauren Cohen say the outlook will likely be more complex, especially as poor and fast-growing regions seek energy sources for their economies.

• 28 Apr 2023

Sweden’s Northvolt Electric Battery Maker: A Startup with a Mission

In Stockholm, Sweden an upstart battery maker, Northvolt, is trying to recreate the value chain for European car manufacturers making the switch to EVs. With two founders from Tesla and two experienced financiers at the helm, the company seems bound for success. But can they partner with government, scale fast enough, and truly be part of the climate solution? Harvard Business School professor George Serafeim discusses what it takes to scale a business—the right people, in the right place, at the right time—with the aim of providing a climate solution in the case, “Northvolt, Building Batteries to Fight Climate Change.” As part of a new first-year MBA course at Harvard Business School, this case examines the central question: what is the social purpose of the firm?

• 18 Apr 2023

What Happens When Banks Ditch Coal: The Impact Is 'More Than Anyone Thought'

Bank divestment policies that target coal reduced carbon dioxide emissions, says research by Boris Vallée and Daniel Green. Could the finance industry do even more to confront climate change?

• 11 Apr 2023

A Rose by Any Other Name: Supply Chains and Carbon Emissions in the Flower Industry

Headquartered in Kitengela, Kenya, Sian Flowers exports roses to Europe. Because cut flowers have a limited shelf life and consumers want them to retain their appearance for as long as possible, Sian and its distributors used international air cargo to transport them to Amsterdam, where they were sold at auction and trucked to markets across Europe. But when the Covid-19 pandemic caused huge increases in shipping costs, Sian launched experiments to ship roses by ocean using refrigerated containers. The company reduced its costs and cut its carbon emissions, but is a flower that travels halfway around the world truly a “low-carbon rose”? Harvard Business School professors Willy Shih and Mike Toffel debate these questions and more in their case, “Sian Flowers: Fresher by Sea?”

• 28 Mar 2023

BMW’s Decarbonization Strategy: Sustainable for the Environment and the Bottom Line

In mid-2022, automakers, consumers, regulators, and investors were focusing on the transition from internal combustion engine (ICE) vehicles to electric vehicles (EV). While this would reduce tail-pipe emissions, it ignored the fact that the production of EVs—and especially their batteries—increases emissions in the supply chain. Many automakers were announcing deadlines by which they would stop selling ICE vehicles altogether, buoyed by investment analysts and favorable press. But BMW decided to focus on lifecycle emissions and pursued a flexible powertrain strategy by offering vehicles with several options: gasoline and diesel-fueled ICE, plug-in hybrid electric vehicles, and battery electric vehicles. That approach received a frostier reception in the stock market. Assistant Professor Shirley Lu discusses how BMW plans to convince stakeholders that its strategy is good for both the environment and the company’s financial performance in the case, “Driving Decarbonization at BMW.”

• 23 Mar 2023

As Climate Fears Mount, More Investors Turn to 'ESG' Funds Despite Few Rules

Regulations and ratings remain murky, but that's not deterring climate-conscious investors from paying more for funds with an ESG label. Research by Mark Egan and Malcolm Baker sizes up the premium these funds command. Is it time for more standards in impact investing?

Center for Teaching

Case studies.

Print Version

Case studies are stories that are used as a teaching tool to show the application of a theory or concept to real situations. Dependent on the goal they are meant to fulfill, cases can be fact-driven and deductive where there is a correct answer, or they can be context driven where multiple solutions are possible. Various disciplines have employed case studies, including humanities, social sciences, sciences, engineering, law, business, and medicine. Good cases generally have the following features: they tell a good story, are recent, include dialogue, create empathy with the main characters, are relevant to the reader, serve a teaching function, require a dilemma to be solved, and have generality.

Instructors can create their own cases or can find cases that already exist. The following are some things to keep in mind when creating a case:

• What do you want students to learn from the discussion of the case?
• What do they already know that applies to the case?
• What are the issues that may be raised in discussion?
• How will the case and discussion be introduced?
• What preparation is expected of students? (Do they need to read the case ahead of time? Do research? Write anything?)
• What directions do you need to provide students regarding what they are supposed to do and accomplish?
• Do you need to divide students into groups or will they discuss as the whole class?
• Are you going to use role-playing or facilitators or record keepers? If so, how?
• What are the opening questions?
• How much time is needed for students to discuss the case?
• What concepts are to be applied/extracted during the discussion?
• How will you evaluate students?

To find other cases that already exist, try the following websites:

• The National Center for Case Study Teaching in Science , University of Buffalo. SUNY-Buffalo maintains this set of links to other case studies on the web in disciplines ranging from engineering and ethics to sociology and business
• A Journal of Teaching Cases in Public Administration and Public Policy , University of Washington

For more information:

• World Association for Case Method Research and Application

Book Review :  Teaching and the Case Method , 3rd ed., vols. 1 and 2, by Louis Barnes, C. Roland (Chris) Christensen, and Abby Hansen. Harvard Business School Press, 1994; 333 pp. (vol 1), 412 pp. (vol 2).

Teaching Guides

• Online Course Development Resources
• Principles & Frameworks
• Pedagogies & Strategies
• Reflecting & Assessing
• Challenges & Opportunities
• Populations & Contexts

Quick Links

• Services for Departments and Schools
• Examples of Online Instructional Modules

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

Search form

• About Faculty Development and Support
• Programs and Funding Opportunities

Consultations, Observations, and Services

• Strategic Resources & Digital Publications
• Canvas @ Yale Support
• Learning Environments @ Yale
• Teaching Workshops
• Teaching Consultations and Classroom Observations
• Teaching Programs
• Spring Teaching Forum
• Written and Oral Communication Workshops and Panels
• Writing Resources & Tutorials
• About the Graduate Writing Laboratory
• Writing and Public Speaking Consultations
• Writing Workshops and Panels
• Writing Peer-Review Groups
• Writing Retreats and All Writes
• Online Writing Resources for Graduate Students
• About Teaching Development for Graduate and Professional School Students
• Teaching Programs and Grants
• Teaching Forums
• Resources for Graduate Student Teachers
• About Undergraduate Writing and Tutoring
• Academic Strategies Program
• The Writing Center
• STEM Tutoring & Programs
• Humanities & Social Sciences
• Center for Language Study
• Online Course Catalog
• Antiracist Pedagogy
• NECQL 2019: NorthEast Consortium for Quantitative Literacy XXII Meeting
• STEMinar Series
• Teaching in Context: Troubling Times
• Helmsley Postdoctoral Teaching Scholars
• Pedagogical Partners
• Instructional Materials
• Evaluation & Research
• STEM Education Job Opportunities
• Yale Connect
• Online Education Legal Statements

You are here

Case-based learning.

Case-based learning (CBL) is an established approach used across disciplines where students apply their knowledge to real-world scenarios, promoting higher levels of cognition (see Bloom’s Taxonomy ). In CBL classrooms, students typically work in groups on case studies, stories involving one or more characters and/or scenarios.  The cases present a disciplinary problem or problems for which students devise solutions under the guidance of the instructor. CBL has a strong history of successful implementation in medical, law, and business schools, and is increasingly used within undergraduate education, particularly within pre-professional majors and the sciences (Herreid, 1994). This method involves guided inquiry and is grounded in constructivism whereby students form new meanings by interacting with their knowledge and the environment (Lee, 2012).

There are a number of benefits to using CBL in the classroom. In a review of the literature, Williams (2005) describes how CBL: utilizes collaborative learning, facilitates the integration of learning, develops students’ intrinsic and extrinsic motivation to learn, encourages learner self-reflection and critical reflection, allows for scientific inquiry, integrates knowledge and practice, and supports the development of a variety of learning skills.

CBL has several defining characteristics, including versatility, storytelling power, and efficient self-guided learning.  In a systematic analysis of 104 articles in health professions education, CBL was found to be utilized in courses with less than 50 to over 1000 students (Thistlethwaite et al., 2012). In these classrooms, group sizes ranged from 1 to 30, with most consisting of 2 to 15 students.  Instructors varied in the proportion of time they implemented CBL in the classroom, ranging from one case spanning two hours of classroom time, to year-long case-based courses. These findings demonstrate that instructors use CBL in a variety of ways in their classrooms.

The stories that comprise the framework of case studies are also a key component to CBL’s effectiveness. Jonassen and Hernandez-Serrano (2002, p.66) describe how storytelling:

Is a method of negotiating and renegotiating meanings that allows us to enter into other’s realms of meaning through messages they utter in their stories,

Helps us find our place in a culture,

Allows us to explicate and to interpret, and

Facilitates the attainment of vicarious experience by helping us to distinguish the positive models to emulate from the negative model.

Neurochemically, listening to stories can activate oxytocin, a hormone that increases one’s sensitivity to social cues, resulting in more empathy, generosity, compassion and trustworthiness (Zak, 2013; Kosfeld et al., 2005). The stories within case studies serve as a means by which learners form new understandings through characters and/or scenarios.

CBL is often described in conjunction or in comparison with problem-based learning (PBL). While the lines are often confusingly blurred within the literature, in the most conservative of definitions, the features distinguishing the two approaches include that PBL involves open rather than guided inquiry, is less structured, and the instructor plays a more passive role. In PBL multiple solutions to the problem may exit, but the problem is often initially not well-defined. PBL also has a stronger emphasis on developing self-directed learning. The choice between implementing CBL versus PBL is highly dependent on the goals and context of the instruction.  For example, in a comparison of PBL and CBL approaches during a curricular shift at two medical schools, students and faculty preferred CBL to PBL (Srinivasan et al., 2007). Students perceived CBL to be a more efficient process and more clinically applicable. However, in another context, PBL might be the favored approach.

In a review of the effectiveness of CBL in health profession education, Thistlethwaite et al. (2012), found several benefits:

Students enjoyed the method and thought it enhanced their learning,

Instructors liked how CBL engaged students in learning,

CBL seemed to facilitate small group learning, but the authors could not distinguish between whether it was the case itself or the small group learning that occurred as facilitated by the case.

Other studies have also reported on the effectiveness of CBL in achieving learning outcomes (Bonney, 2015; Breslin, 2008; Herreid, 2013; Krain, 2016). These findings suggest that CBL is a vehicle of engagement for instruction, and facilitates an environment whereby students can construct knowledge.

Science – Students are given a scenario to which they apply their basic science knowledge and problem-solving skills to help them solve the case. One example within the biological sciences is two brothers who have a family history of a genetic illness. They each have mutations within a particular sequence in their DNA. Students work through the case and draw conclusions about the biological impacts of these mutations using basic science. Sample cases: You are Not the Mother of Your Children ; Organic Chemisty and Your Cellphone: Organic Light-Emitting Diodes ;   A Light on Physics: F-Number and Exposure Time

Medicine – Medical or pre-health students read about a patient presenting with specific symptoms. Students decide which questions are important to ask the patient in their medical history, how long they have experienced such symptoms, etc. The case unfolds and students use clinical reasoning, propose relevant tests, develop a differential diagnoses and a plan of treatment. Sample cases: The Case of the Crying Baby: Surgical vs. Medical Management ; The Plan: Ethics and Physician Assisted Suicide ; The Haemophilus Vaccine: A Victory for Immunologic Engineering

Public Health – A case study describes a pandemic of a deadly infectious disease. Students work through the case to identify Patient Zero, the person who was the first to spread the disease, and how that individual became infected.  Sample cases: The Protective Parent ; The Elusive Tuberculosis Case: The CDC and Andrew Speaker ; Credible Voice: WHO-Beijing and the SARS Crisis

Law – A case study presents a legal dilemma for which students use problem solving to decide the best way to advise and defend a client. Students are presented information that changes during the case.  Sample cases: Mortgage Crisis Call (abstract) ; The Case of the Unpaid Interns (abstract) ; Police-Community Dialogue (abstract)

Business – Students work on a case study that presents the history of a business success or failure. They apply business principles learned in the classroom and assess why the venture was successful or not. Sample cases: SELCO-Determining a path forward ; Project Masiluleke: Texting and Testing to Fight HIV/AIDS in South Africa ; Mayo Clinic: Design Thinking in Healthcare

Humanities - Students consider a case that presents a theater facing financial and management difficulties. They apply business and theater principles learned in the classroom to the case, working together to create solutions for the theater. Sample cases: David Geffen School of Drama

Recommendations

Finding and Writing Cases

Consider utilizing or adapting open access cases - The availability of open resources and databases containing cases that instructors can download makes this approach even more accessible in the classroom. Two examples of open databases are the Case Center on Public Leadership and Harvard Kennedy School (HKS) Case Program , which focus on government, leadership and public policy case studies.

• Consider writing original cases - In the event that an instructor is unable to find open access cases relevant to their course learning objectives, they may choose to write their own. See the following resources on case writing: Cooking with Betty Crocker: A Recipe for Case Writing ; The Way of Flesch: The Art of Writing Readable Cases ;   Twixt Fact and Fiction: A Case Writer’s Dilemma ; And All That Jazz: An Essay Extolling the Virtues of Writing Case Teaching Notes .

Implementing Cases

Take baby steps if new to CBL - While entire courses and curricula may involve case-based learning, instructors who desire to implement on a smaller-scale can integrate a single case into their class, and increase the number of cases utilized over time as desired.

Use cases in classes that are small, medium or large - Cases can be scaled to any course size. In large classes with stadium seating, students can work with peers nearby, while in small classes with more flexible seating arrangements, teams can move their chairs closer together. CBL can introduce more noise (and energy) in the classroom to which an instructor often quickly becomes accustomed. Further, students can be asked to work on cases outside of class, and wrap up discussion during the next class meeting.

Encourage collaborative work - Cases present an opportunity for students to work together to solve cases which the historical literature supports as beneficial to student learning (Bruffee, 1993). Allow students to work in groups to answer case questions.

Form diverse teams as feasible - When students work within diverse teams they can be exposed to a variety of perspectives that can help them solve the case. Depending on the context of the course, priorities, and the background information gathered about the students enrolled in the class, instructors may choose to organize student groups to allow for diversity in factors such as current course grades, gender, race/ethnicity, personality, among other items.  

Use stable teams as appropriate - If CBL is a large component of the course, a research-supported practice is to keep teams together long enough to go through the stages of group development: forming, storming, norming, performing and adjourning (Tuckman, 1965).

Walk around to guide groups - In CBL instructors serve as facilitators of student learning. Walking around allows the instructor to monitor student progress as well as identify and support any groups that may be struggling. Teaching assistants can also play a valuable role in supporting groups.

Interrupt strategically - Only every so often, for conversation in large group discussion of the case, especially when students appear confused on key concepts. An effective practice to help students meet case learning goals is to guide them as a whole group when the class is ready. This may include selecting a few student groups to present answers to discussion questions to the entire class, asking the class a question relevant to the case using polling software, and/or performing a mini-lesson on an area that appears to be confusing among students.  

Assess student learning in multiple ways - Students can be assessed informally by asking groups to report back answers to various case questions. This practice also helps students stay on task, and keeps them accountable. Cases can also be included on exams using related scenarios where students are asked to apply their knowledge.

Barrows HS. (1996). Problem-based learning in medicine and beyond: a brief overview. New Directions for Teaching and Learning, 68, 3-12.  

Bonney KM. (2015). Case Study Teaching Method Improves Student Performance and Perceptions of Learning Gains. Journal of Microbiology and Biology Education, 16(1): 21-28.

Breslin M, Buchanan, R. (2008) On the Case Study Method of Research and Teaching in Design.  Design Issues, 24(1), 36-40.

Bruffee KS. (1993). Collaborative learning: Higher education, interdependence, and authority of knowledge. Johns Hopkins University Press, Baltimore, MD.

Herreid CF. (2013). Start with a Story: The Case Study Method of Teaching College Science, edited by Clyde Freeman Herreid. Originally published in 2006 by the National Science Teachers Association (NSTA); reprinted by the National Center for Case Study Teaching in Science (NCCSTS) in 2013.

Herreid CH. (1994). Case studies in science: A novel method of science education. Journal of Research in Science Teaching, 23(4), 221–229.

Jonassen DH and Hernandez-Serrano J. (2002). Case-based reasoning and instructional design: Using stories to support problem solving. Educational Technology, Research and Development, 50(2), 65-77.  

Kosfeld M, Heinrichs M, Zak PJ, Fischbacher U, Fehr E. (2005). Oxytocin increases trust in humans. Nature, 435, 673-676.

Krain M. (2016) Putting the learning in case learning? The effects of case-based approaches on student knowledge, attitudes, and engagement. Journal on Excellence in College Teaching, 27(2), 131-153.

Lee V. (2012). What is Inquiry-Guided Learning?  New Directions for Learning, 129:5-14.

Nkhoma M, Sriratanaviriyakul N. (2017). Using case method to enrich students’ learning outcomes. Active Learning in Higher Education, 18(1):37-50.

Srinivasan et al. (2007). Comparing problem-based learning with case-based learning: Effects of a major curricular shift at two institutions. Academic Medicine, 82(1): 74-82.

Thistlethwaite JE et al. (2012). The effectiveness of case-based learning in health professional education. A BEME systematic review: BEME Guide No. 23.  Medical Teacher, 34, e421-e444.

Tuckman B. (1965). Development sequence in small groups. Psychological Bulletin, 63(6), 384-99.

Williams B. (2005). Case-based learning - a review of the literature: is there scope for this educational paradigm in prehospital education? Emerg Med, 22, 577-581.

Zak, PJ (2013). How Stories Change the Brain. Retrieved from: https://greatergood.berkeley.edu/article/item/how_stories_change_brain

YOU MAY BE INTERESTED IN

Instructional Enhancement Fund

The Instructional Enhancement Fund (IEF) awards grants of up to $500 to support the timely integration of new learning activities into an existing undergraduate or graduate course. All Yale instructors of record, including tenured and tenure-track faculty, clinical instructional faculty, lecturers, lectors, and part-time acting instructors (PTAIs), are eligible to apply. Award decisions are typically provided within two weeks to help instructors implement ideas for the current semester.

Reserve a Room

The Poorvu Center for Teaching and Learning partners with departments and groups on-campus throughout the year to share its space. Please review the reservation form and submit a request.

The Poorvu Center for Teaching and Learning routinely supports members of the Yale community with individual instructional consultations and classroom observations.

Case Studies in Science Education

A video library for k-8 science teachers: 25 half-hour video programs and guides.

These video case studies take science education reform to a personal level, where individual teachers struggle to make changes that matter. Follow Donna, Mike, Audrey, and other science teachers as they work to adopt one or more research-based interventions to improve science teaching and learning. Each case follows a single teacher over the course of a year and is divided into three modules: the teacher's background and the problem he or she chooses to address, the chosen approach and implementation, and the outcome with assessment by the teacher and his or her advisor. Average running time: 1/2 hour. Program guides and supporting materials (PDF) Program guides and supporting materials (Link)

Log in using your username and password

• Search More Search for this keyword Advanced search
• Latest content
• Current issue
• Write for Us
• BMJ Journals More You are viewing from: Google Indexer

You are here

• Volume 21, Issue 1
• What is a case study?
• Article Text
• Article info
• Citation Tools
• Rapid Responses
• Article metrics

• Roberta Heale 1 ,
• Alison Twycross 2
• 1 School of Nursing , Laurentian University , Sudbury , Ontario , Canada
• 2 School of Health and Social Care , London South Bank University , London , UK
• Correspondence to Dr Roberta Heale, School of Nursing, Laurentian University, Sudbury, ON P3E2C6, Canada; rheale{at}laurentian.ca

https://doi.org/10.1136/eb-2017-102845

Statistics from Altmetric.com

Request permissions.

If you wish to reuse any or all of this article please use the link below which will take you to the Copyright Clearance Center’s RightsLink service. You will be able to get a quick price and instant permission to reuse the content in many different ways.

What is it?

Case study is a research methodology, typically seen in social and life sciences. There is no one definition of case study research. 1 However, very simply… ‘a case study can be defined as an intensive study about a person, a group of people or a unit, which is aimed to generalize over several units’. 1 A case study has also been described as an intensive, systematic investigation of a single individual, group, community or some other unit in which the researcher examines in-depth data relating to several variables. 2

Often there are several similar cases to consider such as educational or social service programmes that are delivered from a number of locations. Although similar, they are complex and have unique features. In these circumstances, the evaluation of several, similar cases will provide a better answer to a research question than if only one case is examined, hence the multiple-case study. Stake asserts that the cases are grouped and viewed as one entity, called the quintain . 6  ‘We study what is similar and different about the cases to understand the quintain better’. 6

The steps when using case study methodology are the same as for other types of research. 6 The first step is defining the single case or identifying a group of similar cases that can then be incorporated into a multiple-case study. A search to determine what is known about the case(s) is typically conducted. This may include a review of the literature, grey literature, media, reports and more, which serves to establish a basic understanding of the cases and informs the development of research questions. Data in case studies are often, but not exclusively, qualitative in nature. In multiple-case studies, analysis within cases and across cases is conducted. Themes arise from the analyses and assertions about the cases as a whole, or the quintain, emerge. 6

Benefits and limitations of case studies

If a researcher wants to study a specific phenomenon arising from a particular entity, then a single-case study is warranted and will allow for a in-depth understanding of the single phenomenon and, as discussed above, would involve collecting several different types of data. This is illustrated in example 1 below.

Using a multiple-case research study allows for a more in-depth understanding of the cases as a unit, through comparison of similarities and differences of the individual cases embedded within the quintain. Evidence arising from multiple-case studies is often stronger and more reliable than from single-case research. Multiple-case studies allow for more comprehensive exploration of research questions and theory development. 6

Despite the advantages of case studies, there are limitations. The sheer volume of data is difficult to organise and data analysis and integration strategies need to be carefully thought through. There is also sometimes a temptation to veer away from the research focus. 2 Reporting of findings from multiple-case research studies is also challenging at times, 1 particularly in relation to the word limits for some journal papers.

Examples of case studies

Example 1: nurses’ paediatric pain management practices.

One of the authors of this paper (AT) has used a case study approach to explore nurses’ paediatric pain management practices. This involved collecting several datasets:

Observational data to gain a picture about actual pain management practices.

Questionnaire data about nurses’ knowledge about paediatric pain management practices and how well they felt they managed pain in children.

Questionnaire data about how critical nurses perceived pain management tasks to be.

These datasets were analysed separately and then compared 7–9 and demonstrated that nurses’ level of theoretical did not impact on the quality of their pain management practices. 7 Nor did individual nurse’s perceptions of how critical a task was effect the likelihood of them carrying out this task in practice. 8 There was also a difference in self-reported and observed practices 9 ; actual (observed) practices did not confirm to best practice guidelines, whereas self-reported practices tended to.

Example 2: quality of care for complex patients at Nurse Practitioner-Led Clinics (NPLCs)

The other author of this paper (RH) has conducted a multiple-case study to determine the quality of care for patients with complex clinical presentations in NPLCs in Ontario, Canada. 10 Five NPLCs served as individual cases that, together, represented the quatrain. Three types of data were collected including:

Review of documentation related to the NPLC model (media, annual reports, research articles, grey literature and regulatory legislation).

Interviews with nurse practitioners (NPs) practising at the five NPLCs to determine their perceptions of the impact of the NPLC model on the quality of care provided to patients with multimorbidity.

Chart audits conducted at the five NPLCs to determine the extent to which evidence-based guidelines were followed for patients with diabetes and at least one other chronic condition.

The three sources of data collected from the five NPLCs were analysed and themes arose related to the quality of care for complex patients at NPLCs. The multiple-case study confirmed that nurse practitioners are the primary care providers at the NPLCs, and this positively impacts the quality of care for patients with multimorbidity. Healthcare policy, such as lack of an increase in salary for NPs for 10 years, has resulted in issues in recruitment and retention of NPs at NPLCs. This, along with insufficient resources in the communities where NPLCs are located and high patient vulnerability at NPLCs, have a negative impact on the quality of care. 10

These examples illustrate how collecting data about a single case or multiple cases helps us to better understand the phenomenon in question. Case study methodology serves to provide a framework for evaluation and analysis of complex issues. It shines a light on the holistic nature of nursing practice and offers a perspective that informs improved patient care.

• Gustafsson J
• Calanzaro M
• Sandelowski M

Competing interests None declared.

Provenance and peer review Commissioned; internally peer reviewed.

Read the full text or download the PDF:

An official website of the United States government

The .gov means it’s official. Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

The site is secure. The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

• Publications
• Account settings

Preview improvements coming to the PMC website in October 2024. Learn More or Try it out now .

• Advanced Search
• Journal List
• J Microbiol Biol Educ
• v.15(2); 2014 Dec

Cautionary Tales: Ethics and Case Studies in Science

Ethical concerns are normally avoided in science classrooms in spite of the fact that many of our discoveries impinge directly on personal and societal values. We should not leave the ethical problems for another day, but deal with them using realistic case studies that challenge students at their ethical core. In this article we illustrate how case studies can be used to teach STEM students principles of ethics.

INTRODUCTION

Americans consider morality the most essential part of self ( 11 ).

This may be true of other cultures as well. All societies have elaborate rules of conduct that are often codified into law. Some of these imperatives seem hardwired. Human infants younger than a year and a half will look longer at visual displays showing violations of social rules ( 2 ). It is part of our primate heritage; individuals are punished if they stray far from acceptable behavior. Capuchin monkeys will reject a reward if they think they are being treated unfairly; they have a clear sense of right and wrong which depends on the social situation ( 3 ). Aesop would agree—he penned many a story where animals behaved badly and paid the penalty.

If morality and ethics are so central to our beings, what are our responsibilities as STEM educators to pass along the standards of society? And if we accept this challenge, what is the best way to instruct our youthful comrades in their quest for knowledge? I argue in this article that we should accept this obligation and that case study teaching is an ideal way to deliver the message.

Case-study teaching has a long and honorable lineage ( 4 ). In academic circles we find it used 100 years ago in Harvard Law School. The instructor would bring in a true criminal or civil case that had been adjudicated and conduct a class discussion with future lawyers, asking them to justify the rationale for the final decision—challenging them every step of the way. This provided students a real-world problem as part of their training for a real world ahead. The method was soon adopted by the Harvard Business School and various schools across the country, where it is now the standard. Medical schools have their own version of the method called Problem-Based Learning. Again the idea was to use real world problems to train physicians, but in this case students work in small groups to analyze patient problems and provide diagnoses. The idea of using similar strategies to teach basic sciences to undergraduates is largely due to the efforts of faculty at the University of Delaware and the National Center for Case Study Teaching in Science, where there are hundreds of cases now published http://sciencecases.lib.buffalo.edu/cs/ .

Research has shown that minorities and women undergraduates respond well to cases ( 5 , 8 ). Among this group, cases have been shown to increase students’ understanding of science by encouraging them to make connections between science concepts and situations they may encounter in their lives ( 7 ). In addition, the case method promotes the internalization of learning and the development of analytical and decision-making skills, as well as proficiency in oral communication and teamwork ( 6 ). The method, moreover, is a flexible teaching tool. Cases can take many different forms and be taught in many different ways, ranging from the classical discussion method used in business and law schools, to the arguably strongest approaches, Problem-Based Learning and the Interrupted Case Method, with their emphasis on small-group, cooperative learning strategies ( 4 ).

The method seems ideal for teaching ethics to STEM students. We have plenty of precedents to guide us. We have legal ethics, business ethics, medical ethics, bioethics, geoethics, environmental ethics, teaching ethics, research ethics, engineering ethics, and so on. And, of course, there are religious ethics, with each faith describing canons of behavior not to be breached. Some of them are commonly held community values, such as “thou shalt not steal, lie, or cheat.” Others are more specific, such as the research tenet, “thou should replicate experiments.” While some of these “rules” are so entrenched that they are tantamount to absolutes, others are more fragile and malleable; they are subject to the changing moral landscape. Policies about smoking in public places have rapidly shifted ( 12 ). Decrees against interracial marriage, once laws of the land, are now anachronisms, as are statues against same-sex marriage ( 1 , 10 ). Such shifts in the moral topography offer wonderful opportunities for case studies as they challenge students at their central core of beliefs. There are hundreds of these case studies now available for teachers in repositories such as the National Center for Case Study Teaching in Science ( http://sciencecases.lib.buffalo.edu ), where you can find moral dilemmas depicted in cases on evolution, genetic engineering, nutrition, euthanasia, cloning, and organic farming.

Case studies can be used to show students acceptable standards of behavior within a given profession—the do’s and don’ts—and the disastrous consequences that can occur if the rules are not obeyed. We learn of breaches of research ethics such as fraud, plagiarism, and sloppy book-keeping that ruin careers. We come to know cautionary tales, like Dr. Andrew Wakefield, who misrepresented the medical histories of 12 patients and claimed that his research results showed that vaccinations caused autism. He was eventually discredited and Britain stripped him of his medical license. Unfortunately, this sensational allegation has resulted in thousands of people refusing to have their children vaccinated, with a subsequent striking rise in measles.

In the past, these stories were neglected in the STEM classroom. Questions of right or wrong belonged elsewhere—in the home, in a philosophy class, in a church or tabernacle. In the science classroom we learned how to make petroleum, shoot rockets, synthesize drugs, manipulate DNA, and clone animals, not whether we should do so. Then came the Second World War. The academic community ran squarely into two striking examples of the deep entanglement of science and ethics. Suddenly, there was a public debate about whether Truman’s decision to drop the atom bomb on Japan with the loss of millions of lives was ethical. The sensational trials of generals and scientists implicated in the atrocities at the Nazi concentration camps came to light during the Nuremberg Trials and patient bills of rights were drafted. Today our IRB committees and other ethical bodies monitor our experimental protocols involving research into issues of genetic engineering, stem cell research, three-parent embryos, etc. So my argument is that we should not ignore these disputes in the science classroom; this is where the technology is coming from—the STEM laboratories and the people in charge.

This is especially true as scientists have gained technological expertise; we see more clearly than ever how science and technological decisions can wreak havoc in our lives. Think about science in the courtroom, the public policy decisions on health and insurance, the intrusion of listening devices and the tracking of our e-mails and phone calls, the science of warfare and the use of chemical weapons and drones, the use of chemical fertilizers and organic farming, and possible designer babies. Very little that we humans do is not filled with moral or ethical conundrums. No more should we eschew these quandaries in our classrooms. When we discuss DNA genomes, we should not only speak of how the technology can be used to track potential criminals, but also how it can lead to social and personal dilemmas when we identify parentage, plot evolutionary lineages, discover genetically modified food, and detect mutations that might lead to lethal disease and the loss of insurance. How better to deal with such contentious matters than to use case studies? Case studies are stories with an educational message, and as such they are perfect vehicles to integrate science with societal and policy issues. They are ideal because of their interdisciplinary nature. They deal with real issues that students will face in the future. And people love stories.

RESOURCES FOR ETHICS CASES

There are several STEM case repositories in the world; arguably the largest is the National Center for Case Study Teaching in Science, with over 500 case studies published over the past 25 years. Its greatest strength is in the fields of biology and health-related professions. Over 100 cases are catalogued as having ethical issues, ranging in suitability from middle school student classes to faculty seminars.

We seldom find pure instances of ethical transgressions, where issues of fraud, fabrication, or plagiarism are discussed. Rather, ethical issues are more apt to be a sidebar to the main thrust of a case concentrated on a health or environmental problem. And even in these cases, an individual may not be wrestling with problems involving societal standards. Instead, they grapple with whether it is prudent to make one decision versus another. It may be as simple as whether or not to have an operation or whether it is healthy to use drugs to lose weight.

Let me give you a flavor of the kinds of issues and cases that are available:

Personal dilemma

Often such cases involve medical issues, as we see in “A Right to Her Genes” ( http://sciencecases.lib.buffalo.edu/cs/collection/detail.asp?case_id=316&id=316 ). In this true story, students examine the case of a woman, Michelle, with a family predisposition to cancer, who is considering genetic testing. The woman wishes to get some information to confirm this predisposition from a reluctant aunt so that she can better decide whether to remove her breasts and/or ovaries prophylactically. The aunt is illiterate and poor and had previously been estranged from the rest of the family. A genetic counselor is involved to help educate the aunt and hopefully obtain consent to get a DNA sample from her. Michelle must decide for herself what course of action she should take.

In “Spirituality and Health Care: A Request for Prayer” ( http://sciencecases.lib.buffalo.edu/cs/collection/detail.asp?case_id=434&id=434 ), a fourth-year medical student making hospital rounds with an attending physician is asked by a family member of a patient to pray with her. The case allows medical students to explore issues related to patients’ religious beliefs as they think through how they might respond to different expectations and requests they may receive from patients and their families in their professional career.

Social ethics

These are cases where protagonists must decide how they will respond to evolving social standards. “SNPs and Snails and Puppy Dog Tails, and That’s What People Are Made Of” ( http://sciencecases.lib.buffalo.edu/cs/collection/detail.asp?case_id=337&id=337 ) deals with questions of genome privacy. Students work together to research six lobbying groups’ views in this area and then present their insights before a mock meeting of a U.S. House of Representatives Subcommittee voting on the Genetic Information Nondiscrimination Act. In working through the case, students learn about single nucleotide polymorphisms, common molecular biology techniques, and current legislation governing genome privacy.

“A Case of Cheating?” ( http://sciencecases.lib.buffalo.edu/cs/collection/detail.asp?case_id=399&id=399 ) involves two international students who are accused of cheating at the end of the semester, and the teacher must decide how to handle the accusation so that all students see that justice is done. The case raises cultural questions in the context of the use of peer evaluation and cooperative learning strategies.

Medical ethics

Patient rights are a common concern in medical cases, whether they are the central issue of the case or a sidebar to teaching students about a particular disease syndrome. It is the central theme of the infamous “Bad Blood” case involving black men in Tuskegee, Alabama, in the 1920s ( http://sciencecases.lib.buffalo.edu/cs/collection/detail.asp?case_id=371&id=371 ). They had contracted syphilis, and public health officials studying the progress of the debilitating disease originally did not have an effective treatment. Twenty years later, the antibiotic penicillin was discovered, yet treatment was withheld to maintain the integrity of the study, whose purpose was to follow the progression of the disease. The study was immediately stopped when this transgression was made public.

Often there are competing concerns, as when a person is confronted with a decision where their personal morality may be at odds with the decrees of a society or institution. “The Plan: Ethics and Physician Assisted Suicide” ( http://sciencecases.lib.buffalo.edu/cs/collection/detail.asp?case_id=436&id=436 ) is based on an article published in 1991 in the New England Journal of Medicine in which Dr. Timothy E. Quill described his care for a patient suffering from acute leukemia, including how he prescribed a lethal dose of barbiturates knowing that the woman intended to commit suicide. As a consequence of the article’s publication, a grand jury was convened to consider a charge of manslaughter against Dr. Quill. Students read the case and then, as part of a classroom-simulated trial, discuss physician-assisted suicide in terms of fundamental medical ethics principles.

Research ethics

Courses in experimental design are frequently part of psychology curricula. They seldom are part of the typical undergraduate programs in other STEM fields, although there is an excellent resource in the text Research Ethics ( 9 ). Apparently, students in STEM disciplines are supposed to absorb the proper canons of behavior by observation and osmosis.

“A Rush to Judgment” ( http://sciencecases.lib.buffalo.edu/cs/collection/detail.asp?case_id=250&id=250 ) deals with a typical psychological experiment, where a faculty professor is inattentive to his student assistants, one of whom is misrepresenting the results of an experiment. Another student is confronted with a moral dilemma of whether to report this infraction at a potential cost to herself. Involved in the case is a consideration of proper research protocol when dealing with human participants: informed consent, freedom from harm, freedom from coercion, anonymity, and confidentiality. Students are referred to the American Psychological Association's Ethical Principles of Psychologists and Code of Conduct.

“How a Cancer Trial Ended in Betrayal” ( http://sciencecases.lib.buffalo.edu/cs/collection/detail.asp?case_id=233&id=233 ) begins with a quote from a news item.

Birmingham, Alabama —After Bob Lange spent 8 weeks rubbing an experimental cream, BCX-34, from a prominent biotech company BioCryst on the fiery patches on his body, researchers at the University of Alabama at Birmingham told him the drug was defeating the killer inside him. He felt grateful. “I believed it,” he recalls. “I actually thought I might be cured.” But it was a lie. The drug had no effect on Lange’s rare and potentially fatal skin cancer. And the two key people testing the drug knew it. Lange and 21 other patients were victims of fraud—a scheme made possible by the close tie between the university and the state’s most prominent biotech company. — The Baltimore Sun , June 24, 2001

The authors of this fascinating case state that the learning objectives are to learn the basics of scientific research in a clinical trial; to learn the principles of the scientific method; and to consider the ethical issues involved in clinical trials. Ethical potholes litter the road when universities travel with businesses, and millions of dollars and fame are at stake.

Socio-environmental ethics

Conflicting concerns are the norm when dealing with the environmental problems that beset our world. They not only involve scientific principles, but invariably policy and hurly burly politics as well.

“One Glass for Two People: A Case of Water Use Rights in the Eastern United States” ( http://sciencecases.lib.buffalo.edu/cs/collection/detail.asp?case_id=603&id=603 ) focuses on the growing issue of water use. Approximately 1.3 million people in North and South Carolina depend on the Catawba-Wateree River for water and electricity. The river is also important for recreation and real estate development. To meet growing water demands, elected officials in Concord and Kannapolis, NC, petitioned their state government to approve an inter-basin transfer of 25 million gallons of water a day from the Catawba River. Other towns in North Carolina and South Carolina that are part of the Catawba-Wateree watershed fought this request for water transfer. For this exercise, students are divided into teams that take the role of different stakeholders trying to negotiate a settlement to this lawsuit. In the course of the debate, students address fundamental legal, ethical, and environmental questions about water use.

“Ecotourism: Who Benefits?” ( http://sciencecases.lib.buffalo.edu/cs/collection/detail.asp?case_id=359&id=359 ) critically examines the costs and the benefits of visiting fragile, pristine, and relatively undisturbed natural areas. Although ecotourism has among its goals to provide funds for ecological conservation as well as economic benefit and empowerment to local communities, it can result in the exploitation of the natural resources (and communities) it seeks to protect. Students assess ecotourism in Costa Rica by considering the viewpoints of a displaced landowner, banana plantation worker, environmentalist, state official, U.S. trade representative, and national park employee.

Legal ethics

“The Slippery Slope of Litigating Geologic Hazards” ( http://sciencecases.lib.buffalo.edu/cs/collection/detail.asp?case_id=385&id=385 ) is based on a lawsuit brought against the County of Los Angeles by homeowners suing over damage to their homes in the wake of the Portuguese Bend Landslide. It teaches students principles of landslide movement while illustrating the difficulties involved with litigation resulting from natural hazards. Students first read a newspaper article based on the actual events and then receive details about the geologic setting and landslide characteristics. They are then asked to evaluate the possible causes of the disaster and the responsibilities involved.

“The Sad But True Case of Earl Washington: DNA Analysis and the Criminal Justice System” ( http://sciencecases.lib.buffalo.edu/cs/collection/detail.asp?case_id=725&id=725 ) recounts how, in 1983, Earl Washington “confessed” to a violent crime that he did not commit and was sentenced to death row. After spending 17 years in prison for something he did not do, Earl was released in 2001 after his innocence was proven through the use of modern DNA technology. The case guides students through the wrongful incarceration of Earl and explores the biological mechanisms behind DNA profiling and the ethical issues involved.

“Complexity in Conservation: The Legal and Ethical Case of a Bird-Eating Cat and its Human Killer” ( http://sciencecases.lib.buffalo.edu/cs/collection/detail.asp?case_id=664&id=664 ) presents the true story of a Texas man who killed a cat that was killing piping plovers, a type of endangered bird species, and was prosecuted for it. In Texas, it is a crime to kill an animal that “belongs to another,” and there was evidence that another person was feeding the cat, which otherwise appeared to be feral. Students engage in a role-playing activity as jurors; they discuss the case and collectively decide whether the cat killer should be acquitted or convicted. This role-playing coupled with follow-up discussions helps students examine and articulate their own views on a controversial environmental issue and gain a better understanding about the complex interdisciplinary nature of conservation science and practice.

There are plenty of ethical issues in every science classroom to discuss; they are not in short supply. They are hovering around every scientific study that reaches the public eye. Pick any news item with science as its theme and there will be the central question that is often not spoken: should we be doing this research at all, not only because of its economic cost, but because of the social, environmental, or health costs? Surely this should be always a pivotal question in the minds of all citizens. It is sometimes asserted that scientific discovery cannot or should not be stopped—that all knowledge is good. But even if we accept that premise, it seems worthwhile to consider the consequences of our actions. Where else to start than in our classrooms?

Acknowledgments

This material is based upon work supported by the National Science Foundation (NSF) under Grant Nos. DUE-0341279, DUE-0618570, DUE-0920264, and DUE-1323355. Any opinions, findings, conclusions, or recommendations expressed in this material are those of the author and do not necessarily reflect the views of the NSF. The author declares that there are no conflicts of interest.

• Our Mission

Making Learning Relevant With Case Studies

The open-ended problems presented in case studies give students work that feels connected to their lives.

To prepare students for jobs that haven’t been created yet, we need to teach them how to be great problem solvers so that they’ll be ready for anything. One way to do this is by teaching content and skills using real-world case studies, a learning model that’s focused on reflection during the problem-solving process. It’s similar to project-based learning, but PBL is more focused on students creating a product.

Case studies have been used for years by businesses, law and medical schools, physicians on rounds, and artists critiquing work. Like other forms of problem-based learning, case studies can be accessible for every age group, both in one subject and in interdisciplinary work.

You can get started with case studies by tackling relatable questions like these with your students:

• How can we limit food waste in the cafeteria?
• How can we get our school to recycle and compost waste? (Or, if you want to be more complex, how can our school reduce its carbon footprint?)
• How can we improve school attendance?
• How can we reduce the number of people who get sick at school during cold and flu season?

Addressing questions like these leads students to identify topics they need to learn more about. In researching the first question, for example, students may see that they need to research food chains and nutrition. Students often ask, reasonably, why they need to learn something, or when they’ll use their knowledge in the future. Learning is most successful for students when the content and skills they’re studying are relevant, and case studies offer one way to create that sense of relevance.

Teaching With Case Studies

Ultimately, a case study is simply an interesting problem with many correct answers. What does case study work look like in classrooms? Teachers generally start by having students read the case or watch a video that summarizes the case. Students then work in small groups or individually to solve the case study. Teachers set milestones defining what students should accomplish to help them manage their time.

During the case study learning process, student assessment of learning should be focused on reflection. Arthur L. Costa and Bena Kallick’s Learning and Leading With Habits of Mind gives several examples of what this reflection can look like in a classroom: 

Journaling: At the end of each work period, have students write an entry summarizing what they worked on, what worked well, what didn’t, and why. Sentence starters and clear rubrics or guidelines will help students be successful. At the end of a case study project, as Costa and Kallick write, it’s helpful to have students “select significant learnings, envision how they could apply these learnings to future situations, and commit to an action plan to consciously modify their behaviors.”

Interviews: While working on a case study, students can interview each other about their progress and learning. Teachers can interview students individually or in small groups to assess their learning process and their progress.

Student discussion: Discussions can be unstructured—students can talk about what they worked on that day in a think-pair-share or as a full class—or structured, using Socratic seminars or fishbowl discussions. If your class is tackling a case study in small groups, create a second set of small groups with a representative from each of the case study groups so that the groups can share their learning.

4 Tips for Setting Up a Case Study

1. Identify a problem to investigate: This should be something accessible and relevant to students’ lives. The problem should also be challenging and complex enough to yield multiple solutions with many layers.

2. Give context: Think of this step as a movie preview or book summary. Hook the learners to help them understand just enough about the problem to want to learn more.

3. Have a clear rubric: Giving structure to your definition of quality group work and products will lead to stronger end products. You may be able to have your learners help build these definitions.

4. Provide structures for presenting solutions: The amount of scaffolding you build in depends on your students’ skill level and development. A case study product can be something like several pieces of evidence of students collaborating to solve the case study, and ultimately presenting their solution with a detailed slide deck or an essay—you can scaffold this by providing specified headings for the sections of the essay.

Problem-Based Teaching Resources

There are many high-quality, peer-reviewed resources that are open source and easily accessible online.

• The National Center for Case Study Teaching in Science at the University at Buffalo built an online collection of more than 800 cases that cover topics ranging from biochemistry to economics. There are resources for middle and high school students.
• Models of Excellence , a project maintained by EL Education and the Harvard Graduate School of Education, has examples of great problem- and project-based tasks—and corresponding exemplary student work—for grades pre-K to 12.
• The Interdisciplinary Journal of Problem-Based Learning at Purdue University is an open-source journal that publishes examples of problem-based learning in K–12 and post-secondary classrooms.
• The Tech Edvocate has a list of websites and tools related to problem-based learning.

In their book Problems as Possibilities , Linda Torp and Sara Sage write that at the elementary school level, students particularly appreciate how they feel that they are taken seriously when solving case studies. At the middle school level, “researchers stress the importance of relating middle school curriculum to issues of student concern and interest.” And high schoolers, they write, find the case study method “beneficial in preparing them for their future.”

FOR EMPLOYERS

Top 10 real-world data science case studies.

Aditya Sharma

Aditya is a content writer with 5+ years of experience writing for various industries including Marketing, SaaS, B2B, IT, and Edtech among others. You can find him watching anime or playing games when he’s not writing.

Frequently Asked Questions

Real-world data science case studies differ significantly from academic examples. While academic exercises often feature clean, well-structured data and simplified scenarios, real-world projects tackle messy, diverse data sources with practical constraints and genuine business objectives. These case studies reflect the complexities data scientists face when translating data into actionable insights in the corporate world.

Real-world data science projects come with common challenges. Data quality issues, including missing or inaccurate data, can hinder analysis. Domain expertise gaps may result in misinterpretation of results. Resource constraints might limit project scope or access to necessary tools and talent. Ethical considerations, like privacy and bias, demand careful handling.

Lastly, as data and business needs evolve, data science projects must adapt and stay relevant, posing an ongoing challenge.

Real-world data science case studies play a crucial role in helping companies make informed decisions. By analyzing their own data, businesses gain valuable insights into customer behavior, market trends, and operational efficiencies.

These insights empower data-driven strategies, aiding in more effective resource allocation, product development, and marketing efforts. Ultimately, case studies bridge the gap between data science and business decision-making, enhancing a company's ability to thrive in a competitive landscape.

Key takeaways from these case studies for organizations include the importance of cultivating a data-driven culture that values evidence-based decision-making. Investing in robust data infrastructure is essential to support data initiatives. Collaborating closely between data scientists and domain experts ensures that insights align with business goals.

Finally, continuous monitoring and refinement of data solutions are critical for maintaining relevance and effectiveness in a dynamic business environment. Embracing these principles can lead to tangible benefits and sustainable success in real-world data science endeavors.

Data science is a powerful driver of innovation and problem-solving across diverse industries. By harnessing data, organizations can uncover hidden patterns, automate repetitive tasks, optimize operations, and make informed decisions.

In healthcare, for example, data-driven diagnostics and treatment plans improve patient outcomes. In finance, predictive analytics enhances risk management. In transportation, route optimization reduces costs and emissions. Data science empowers industries to innovate and solve complex challenges in ways that were previously unimaginable.

Hire remote developers

Tell us the skills you need and we'll find the best developer for you in days, not weeks.

• 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

424 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]

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

What Is a Case Study?

Weighing the pros and cons of this method of research

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

Cara Lustik is a fact-checker and copywriter.

Verywell / Colleen Tighe

• Pros and Cons

What Types of Case Studies Are Out There?

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

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

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

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

At a Glance

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

What Are the Benefits and Limitations of Case Studies?

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

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

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

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

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

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

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

Case Study Examples

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

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

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

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

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

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

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

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

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

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

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

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

Section 1: A Case History

This section will have the following structure and content:

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

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

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

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

Section 2: Treatment Plan

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

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

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

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

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

Need More Tips?

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

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

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

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

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

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

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

Help | Advanced Search

Computer Science > Cryptography and Security

Title: ransomware detection and classification using random forest: a case study with the ugransome2024 dataset.

Abstract: Cybersecurity faces challenges in identifying and mitigating ransomware, which is important for protecting critical infrastructures. The absence of datasets for distinguishing normal versus abnormal network behaviour hinders the development of proactive detection strategies against ransomware. An obstacle in proactive prevention methods is the absence of comprehensive datasets for contrasting normal versus abnormal network behaviours. The dataset enabling such contrasts would significantly expedite threat anomaly mitigation. In this study, we introduce UGRansome2024, an optimised dataset for ransomware detection in network traffic. This dataset is derived from the UGRansome data using an intuitionistic feature engineering approach that considers only relevant patterns in network behaviour analysis. The study presents an analysis of ransomware detection using the UGRansome2024 dataset and the Random Forest algorithm. Through encoding and feature relevance determination, the Random Forest achieved a classification accuracy of 96% and effectively identified unusual ransomware transactions. Findings indicate that certain ransomware variants, such as those utilising Encrypt Decrypt Algorithms (EDA) and Globe ransomware, have the highest financial impact. These insights have significant implications for real-world cybersecurity practices, highlighting the importance of machine learning in ransomware detection and mitigation. Further research is recommended to expand datasets, explore alternative detection methods, and address limitations in current approaches.

Submission history

Access paper:.

• 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 .

Advertisement

Supported by

Hot Oceans Worsened Dubai’s Dramatic Flooding, Scientists Say

An international team of researchers found that heavy rains had intensified in the region, though they couldn’t say for sure how much climate change was responsible.

• Share full article

By Raymond Zhong

Scenes of flood-ravaged neighborhoods in one of the planet’s driest regions stunned the world this month. Heavy rains in the United Arab Emirates and Oman submerged cars, clogged highways and killed at least 21 people. Flights out of Dubai’s airport, a major global hub, were severely disrupted.

The downpours weren’t a total surprise — forecasters had anticipated the storms several days earlier and issued warnings. But they were certainly unusual.

Here’s what to know.

Heavy rain there is rare, but not unheard-of.

On average, the Arabian Peninsula receives a scant few inches of rain a year, although scientists have found that a sizable chunk of that precipitation falls in infrequent but severe bursts, not as periodic showers. These rains often come during El Niño conditions like the ones the world is experiencing now.

U.A.E. officials said the 24-hour rain total on April 16 was the country’s largest since records there began in 1949 . And parts of the nation had already experienced an earlier round of thunderstorms in March.

Oman, with its coastline on the Arabian Sea, is also vulnerable to tropical cyclones. Past storms there have brought torrential rain, powerful winds and mudslides, causing extensive damage.

Global warming is projected to intensify downpours.

Stronger storms are a key consequence of human-caused global warming. As the atmosphere gets hotter, it can hold more moisture, which can eventually make its way down to the earth as rain or snow.

But that doesn’t mean rainfall patterns are changing in precisely the same way across every part of the globe.

In their latest assessment of climate research , scientists convened by the United Nations found there wasn’t enough data to have firm conclusions about rainfall trends in the Arabian Peninsula and how climate change was affecting them. The researchers said, however, that if global warming were to be allowed to continue worsening in the coming decades, extreme downpours in the region would quite likely become more intense and more frequent.

Hot oceans are a big factor.

An international team of scientists has made a first attempt at estimating the extent to which climate change may have contributed to April’s storms. The researchers didn’t manage to pin down the connection precisely, though in their analysis, they did highlight one known driver of heavy rain in the region: above-normal ocean temperatures.

Large parts of the Indian, Pacific and Atlantic Oceans have been hotter than usual recently, in part because of El Niño and other natural weather cycles, and in part because of human-induced warming .

When looking only at El Niño years, the scientists estimated that storm events as infrequent as this month’s delivered 10 percent to 40 percent more rain to the region than they would in a world that hadn’t been warmed by human activities. They cautioned, however, that these estimates were highly uncertain.

“Rainfall, in general, is getting more extreme,” said Mansour Almazroui, a climate scientist at King Abdulaziz University in Jeddah, Saudi Arabia, and one of the researchers who contributed to the analysis.

The analysis was conducted by scientists affiliated with World Weather Attribution, a research collaboration that studies extreme weather events shortly after they occur. Their findings about this month’s rains haven’t yet been peer reviewed, but are based on standardized methods .

The role of cloud seeding isn’t clear.

The U.A.E. has for decades worked to increase rainfall and boost water supplies by seeding clouds. Essentially, this involves shooting particles into clouds to encourage the moisture to gather into larger, heavier droplets, ones that are more likely to fall as rain or snow.

Cloud seeding and other rain-enhancement methods have been tried around the world, including in Australia, China, India, Israel, South Africa and the United States. Studies have found that these operations can, at best, affect precipitation modestly — enough to turn a downpour into a bigger downpour, but probably not a drizzle into a deluge.

Still, experts said pinning down how much seeding might have contributed to this month’s storms would require detailed study.

“In general, it is quite a challenge to assess the impact of seeding,” said Luca Delle Monache, a climate scientist at the Scripps Institution of Oceanography in La Jolla, Calif. Dr. Delle Monache has been leading efforts to use artificial intelligence to improve the U.A.E.’s rain-enhancement program.

An official with the U.A.E.’s National Center of Meteorology, Omar Al Yazeedi, told news outlets that the agency didn’t conduct any seeding during the latest storms. His statements didn’t make clear, however, whether that was also true in the hours or days before.

Mr. Al Yazeedi didn’t respond to emailed questions from The New York Times, and Adel Kamal, a spokesman for the center, didn’t have further comment.

Cities in dry places just aren’t designed for floods.

Wherever it happens, flooding isn’t just a matter of how much rain comes down. It’s also about what happens to all that water once it’s on the ground — most critically, in the places people live.

Cities in arid regions often aren’t designed to drain very effectively. In these areas, paved surfaces block rain from seeping into the earth below, forcing it into drainage systems that can easily become overwhelmed.

One recent study of Sharjah , the capital of the third-largest emirate in the U.A.E., found that the city’s rapid growth over the past half-century had made it vulnerable to flooding at far lower levels of rain than before.

Omnia Al Desoukie contributed reporting.

Raymond Zhong reports on climate and environmental issues for The Times. More about Raymond Zhong

Organizing Your Social Sciences Research Paper: Writing a Case Study

• Purpose of Guide
• Design Flaws to Avoid
• Independent and Dependent Variables
• Glossary of Research Terms
• Narrowing a Topic Idea
• Broadening a Topic Idea
• Extending the Timeliness of a Topic Idea
• Academic Writing Style
• Choosing a Title
• Making an Outline
• Paragraph Development
• Executive Summary
• The C.A.R.S. Model
• Background Information
• The Research Problem/Question
• Theoretical Framework
• Citation Tracking
• Content Alert Services
• Evaluating Sources
• Reading Research Effectively
• Primary Sources
• Secondary Sources
• Tiertiary Sources
• What Is Scholarly vs. Popular?
• Qualitative Methods
• Quantitative Methods
• Using Non-Textual Elements
• Limitations of the Study
• Common Grammar Mistakes
• Writing Concisely
• Avoiding Plagiarism
• Footnotes or Endnotes?
• Further Readings
• Annotated Bibliography
• Dealing with Nervousness
• Using Visual Aids
• Grading Someone Else's Paper
• Types of Structured Group Activities
• Group Project Survival Skills
• Multiple Book Review Essay
• Reviewing Collected Essays
• Writing a Case Study
• About Informed Consent
• Writing Field Notes
• Writing a Policy Memo
• Writing a Research Proposal
• Bibliography

The term case study refers to both a method of analysis and a specific research design for examining a problem, both of which are used in most circumstances to generalize across populations. This tab focuses on the latter--how to design and organize a research paper in the social sciences that analyzes a specific case.

A case study research paper examines a person, place, event, 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 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 among more than two 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 this writing guide. Review this page because it may help you identify a subject of analysis that can be investigated using a single 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:

• Does the case represent 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.
• Does the case provide 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.
• Does the case challenge and offer 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 practice. A case may offer you 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 the study a case in order 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.
• Does the case provide 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 in order to better warn drivers of an approaching train, particularly when visibility is hindered by heavy rain, fog, or at night.
• Does the case offer a new direction in future research? A case study can be used as a tool for exploratory research that points to a need for further examination of the research 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 Uganda. A case study of how women contribute to saving water in a particular village 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 throughout rural regions of east Africa. The case could also point to the need for scholars to apply 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 was I studying? Describe the research problem and describe the subject of analysis 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 was 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 research 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 include 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 study 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 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 the context of explaining the relevance of the case in addressing the research problem.

III.  Method

In this section, you explain why you selected a particular subject of analysis to study 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 frames 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; c) what were the consequences of the event.

If your subject of analysis is a person. Explain why you selected this particular individual to be studied and describe what experience he or she has had that provides 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 his/her 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 him or her 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.

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, cultural, economic, political, etc.], 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, why study 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 reveals 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? How might knowing the suppliers of these trucks from overseas 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 be linked to the findings from the literature review. Be sure to cite any prior studies that helped you determine that the case you chose was appropriate for investigating the research 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 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 more common to combine a description of the findings 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 to 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 It is important to 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 for 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.

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 needs for further research.

The function of your paper's conclusion is to: 1)  restate the main argument supported by the findings from the analysis of your case; 2) clearly state 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 for you 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 and your professor's preferences, the concluding paragraph may contain your final reflections on the evidence presented applied 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 on 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 differently 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.

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: Reviewing Collected Essays
• Next: Writing a Field Report >>
• Last Updated: Jan 17, 2023 10:50 AM
• URL: https://libguides.pointloma.edu/ResearchPaper

• Copy/Paste Link Link Copied

Science Update: Steroid treatment in late pregnancy does not appear to affect children’s neurodevelopment, NICHD-funded study suggests

Children who were exposed to a steroid at 34 to 36 weeks of pregnancy are no more likely to have cognitive effects than children whose mother did not receive a steroid, suggests a study funded by the Eunice Kennedy Shriver National Institute of Child Health and Human Development (NICHD). The findings help to allay concerns that fetal exposure to a steroid in the uterus—given to speed lung development in case of preterm birth—could affect a child’s neurodevelopment.

The study was conducted by Cynthia Gyamfi-Bannerman, M.D., M.S., and colleagues in the NICHD Maternal-Fetal Medicine Units Network. It appears in the Journal of the American Medical Association .

A previous study concluded that giving a single dose of the steroid betamethasone to pregnant people at risk of giving birth at 34 to 36 weeks of pregnancy significantly reduced the risk of respiratory complications in their newborns. However, the study also found that these infants were more likely to develop hypoglycemia (low blood sugar). Prolonged hypoglycemia in newborns is associated with brain injury . Other research suggests that multiple doses of steroids before birth could affect a child’s neurodevelopment.

For the current study, researchers evaluated children of the previous study’s participants when the children were six years old or older. A psychologist evaluated each child using a variety of tests that measured verbal and nonverbal reasoning and comprehension. A total of 949 children completed the testing (479 in the betamethasone group and 470 in the placebo group).

Both groups of children scored similarly across all measures of the test, called the Differential Ability Scales. A total of 17.1% in the betamethasone group received a score of less than 85, which did not differ significantly from the 18.5% of the placebo group. Similarly, the average score was 96.6 for both groups (compared to a national average of 100). Also similar between the groups were scores for verbal ability, nonverbal ability, spatial ability, social responsiveness, gross motor function, and behavior.

Significance

The authors conclude that giving a steroid to pregnant people at risk for late preterm birth to reduce potential respiratory complications in their infants is not associated with adverse neurodevelopmental outcomes at age 6 or older. The results help support the prescribing of corticosteroids to pregnant people at risk for late preterm birth.

Gyamfi-Bannerman, C, et al. Neurodevelopmental Outcomes After late preterm antenatal corticosteroids: The ALPS follow-up study. The Journal of the American Medical Association. 2024. doi:10.1001/jama.2024.4303

• Publications
• Conferences & Events
• Professional Learning
• Science Standards
• Awards & Competitions
• Daily Do Lesson Plans
• Free Resources
• American Rescue Plan
• For Preservice Teachers
• NCCSTS Case Collection
• Partner Jobs in Education
• Interactive eBooks+
• Digital Catalog
• Regional Product Representatives
• e-Newsletters
• Bestselling Books
• Latest Books
• Popular Book Series
• Prospective Authors
• Web Seminars
• Exhibits & Sponsorship
• Conference Reviewers
• National Conference • Denver 24
• Leaders Institute 2024
• National Conference • New Orleans 24
• Submit a Proposal
• Latest Resources
• Professional Learning Units & Courses
• For Districts
• Online Course Providers
• Schools & Districts
• College Professors & Students
• The Standards
• Teachers and Admin
• eCYBERMISSION
• Toshiba/NSTA ExploraVision
• Junior Science & Humanities Symposium
• Teaching Awards
• Climate Change
• Earth & Space Science
• New Science Teachers
• Early Childhood
• Middle School
• High School
• Postsecondary
• Informal Education
• Journal Articles
• Lesson Plans
• e-newsletters
• Science & Children
• Science Scope
• The Science Teacher
• Journal of College Sci. Teaching
• Connected Science Learning
• NSTA Reports
• Next-Gen Navigator
• Science Update
• Teacher Tip Tuesday
• Trans. Sci. Learning

MyNSTA Community

• My Collections

Case Studies: Forensic Science

All forensic science case studies.

Fatally Flawed?

By Amy C. Groth

Disaster at the Daisys’

By Kimberly S. Farah

Caught Red-Handed

By Mackenzie A. Hahn, Hannah C. Schake, Ryan T. Schalles, Sarah R. Shioji, Breanna N. Harris

The Boy in the Temple

By Cheryld L. Emmons

The Sad But True Case of Earl Washington

By Justin F. Shaffer

Thomas and Sally

By Eric Ribbens, Andrew C. Lydeard

King Tut's Family Secrets

By Kuei-Chiu Chen

Murder by HIV? Grades 5-8 Edition

By Michèle I. Shuster, Naowarat (Ann) Cheeptham, Laura B. Regassa

What Do We Tell the Sheriff?

By Phoebe R. Stubblefield, Elizabeth Scharf

The Case of the Druid Dracula: Clicker Case Version

By Norris Armstrong, Terry Platt, Peggy Brickman

• Skip to main content
• Keyboard shortcuts for audio player

• Your Health
• Treatments & Tests
• Health Inc.
• Public Health

Reproductive rights in America

What's at stake as the supreme court hears idaho case about abortion in emergencies.

Selena Simmons-Duffin

The Supreme Court will hear another case about abortion rights on Wednesday. Protestors gathered outside the court last month when the case before the justices involved abortion pills. Tom Brenner for The Washington Post/Getty Images hide caption

The Supreme Court will hear another case about abortion rights on Wednesday. Protestors gathered outside the court last month when the case before the justices involved abortion pills.

In Idaho, when a pregnant patient has complications, abortion is only legal to prevent the woman's death. But a federal law known as EMTALA requires doctors to provide "stabilizing treatment" to patients in the emergency department.

The Biden administration sees that as a direct conflict, which is why the abortion issue is back – yet again – before the Supreme Court on Wednesday.

The case began just a few weeks after the justices overturned Roe v. Wade in 2022, when the federal Justice Department sued Idaho , arguing that the court should declare that "Idaho's law is invalid" when it comes to emergency abortions because the federal emergency care law preempts the state's abortion ban. So far, a district court agreed with the Biden administration, an appeals court panel agreed with Idaho, and the Supreme Court allowed the strict ban to take effect in January when it agreed to hear the case.

Supreme Court allows Idaho abortion ban to be enacted, first such ruling since Dobbs

The case, known as Moyle v. United States (Mike Moyle is the speaker of the Idaho House), has major implications on everything from what emergency care is available in states with abortion bans to how hospitals operate in Idaho. Here's a summary of what's at stake.

1. Idaho physicians warn patients are being harmed

Under Idaho's abortion law , the medical exception only applies when a doctor judges that "the abortion was necessary to prevent the death of the pregnant woman." (There is also an exception to the Idaho abortion ban in cases of rape or incest, only in the first trimester of the pregnancy, if the person files a police report.)

In a filing with the court , a group of 678 physicians in Idaho described cases in which women facing serious pregnancy complications were either sent home from the hospital or had to be transferred out of state for care. "It's been just a few months now that Idaho's law has been in effect – six patients with medical emergencies have already been transferred out of state for [pregnancy] termination," Dr. Jim Souza, chief physician executive of St. Luke's Health System in Idaho, told reporters on a press call last week.

Those delays and transfers can have consequences. For example, Dr. Emily Corrigan described a patient in court filings whose water broke too early, which put her at risk of infection. After two weeks of being dismissed while trying to get care, the patient went to Corrigan's hospital – by that time, she showed signs of infection and had lost so much blood she needed a transfusion. Corrigan added that without receiving an abortion, the patient could have needed a limb amputation or a hysterectomy – in other words, even if she didn't die, she could have faced life-long consequences to her health.

Attorneys for Idaho defend its abortion law, arguing that "every circumstance described by the administration's declarations involved life-threatening circumstances under which Idaho law would allow an abortion."

Ryan Bangert, senior attorney for the Christian legal powerhouse Alliance Defending Freedom, which is providing pro-bono assistance to the state of Idaho, says that "Idaho law does allow for physicians to make those difficult decisions when it's necessary to perform an abortion to save the life of the mother," without waiting for patients to become sicker and sicker.

Still, Dr. Sara Thomson, an OB-GYN in Boise, says difficult calls in the hospital are not hypothetical or even rare. "In my group, we're seeing this happen about every month or every other month where this state law complicates our care," she says. Four patients have sued the state in a separate case arguing that the narrow medical exception harmed them.

"As far as we know, we haven't had a woman die as a consequence of this law, but that is really on the top of our worry list of things that could happen because we know that if we watch as death is approaching and we don't intervene quickly enough, when we decide finally that we're going to intervene to save her life, it may be too late," she says.

2. Hospitals are closing units and struggling to recruit doctors

Labor and delivery departments are expensive for hospitals to operate. Idaho already had a shortage of providers, including OB-GYNS. Hospital administrators now say the Idaho abortion law has led to an exodus of maternal care providers from the state, which has a population of 2 million people.

Three rural hospitals in Idaho have closed their labor-and-delivery units since the abortion law took effect. "We are seeing the expansion of what's called obstetrical deserts here in Idaho," said Brian Whitlock, president and CEO of the Idaho Hospital Association.

Since Idaho's abortion law took effect, nearly one in four OB-GYNs have left the state or retired, according to a report from the Idaho Physician Well-Being Action Collaborative. The report finds the loss of doctors who specialize in high-risk pregnancies is even more extreme – five of nine full time maternal-fetal medicine specialists have left Idaho.

Administrators say they aren't able to recruit new providers to fill those positions. "Since [the abortion law's] enactment, St. Luke's has had markedly fewer applicants for open physician positions, particularly in obstetrics. And several out-of-state candidates have withdrawn their applications upon learning of the challenges of practicing in Idaho, citing [the law's] enactment and fear of criminal penalties," reads an amicus brief from St. Luke's health system in support of the federal government.

"Prior to the abortion decision, we already ranked 50th in number of physicians per capita – we were already a strained state," says Thomson, the doctor in Boise. She's experienced the loss of OB-GYN colleagues first hand. "I had a partner retire right as the laws were changing and her position has remained open – unfilled now for almost two years – so my own personal group has been short-staffed," she says.

ADF's Bangert says he's skeptical of the assertion that the abortion law is responsible for this exodus of doctors from Idaho. "I would be very surprised if Idaho's abortion law is the sole or singular cause of any physician shortage," he says. "I'm very suspicious of any claims of causality."

3. Justices could weigh in on fetal "personhood"

The state of Idaho's brief argues that EMTALA actually requires hospitals "to protect and care for an 'unborn child,'" an argument echoed in friend-of-the-court briefs from the U.S. Conference of Catholic Bishops and a group of states from Indiana to Wyoming that also have restrictive abortion laws. They argue that abortion can't be seen as a stabilizing treatment if one patient dies as a result.

Thomson is also Catholic, and she says the idea that, in an emergency, she is treating two patients – the fetus and the mother – doesn't account for clinical reality. "Of course, as obstetricians we have a passion for caring for both the mother and the baby, but there are clinical situations where the mom's health or life is in jeopardy, and no matter what we do, the baby is going to be lost," she says.

The Idaho abortion law uses the term "unborn child" as opposed to the words "embryo" or "fetus" – language that implies the fetus has the same rights as other people.

Shots - Health News

The science of ivf: what to know about alabama's 'extrauterine children' ruling.

Mary Ziegler , a legal historian at University of California - Davis, who is writing a book on fetal personhood, describes it as the "North Star" of the anti-abortion rights movement. She says this case will be the first time the Supreme Court justices will be considering a statute that uses that language.

"I think we may get clues about the future of bigger conflicts about fetal personhood," she explains, depending on how the justices respond to this idea. "Not just in the context of this statute or emergency medical scenarios, but in the context of the Constitution."

ADF has dismissed the idea that this case is an attempt to expand fetal rights. "This case is, at root, a question about whether or not the federal government can affect a hostile takeover of the practice of medicine in all 50 states by misinterpreting a long-standing federal statute to contain a hidden nationwide abortion mandate," Bangert says.

4. The election looms large

Ziegler suspects the justices will allow Idaho's abortion law to remain as is. "The Supreme Court has let Idaho's law go into effect, which suggests that the court is not convinced by the Biden administration's arguments, at least at this point," she notes.

Trump backed a federal abortion ban as president. Now, he says he wouldn't sign one

Whatever the decision, it will put abortion squarely back in the national spotlight a few months before the November election. "It's a reminder on the political side of things, that Biden and Trump don't really control the terms of the debate on this very important issue," Zielger observes. "They're going to be things put on everybody's radar by other actors, including the Supreme Court."

The justices will hear arguments in the case on Wednesday morning. A decision is expected by late June or early July.

Correction April 23, 2024

An earlier version of this story did not mention the rape and incest exception to Idaho's abortion ban. A person who reports rape or incest to police can end a pregnancy in Idaho in the first trimester.

• Abortion rights
• Supreme Court