ethnography case study differences

Case Study vs. Ethnography

What's the difference.

Case study and ethnography are both research methods used in social sciences to gain a deeper understanding of a particular phenomenon or group of people. However, they differ in their approach and focus. A case study typically involves an in-depth examination of a single individual, group, or event, aiming to provide a detailed analysis of a specific situation. On the other hand, ethnography involves immersing oneself in a particular culture or community over an extended period, observing and interacting with its members to understand their beliefs, behaviors, and social dynamics. While case studies provide detailed insights into specific cases, ethnography offers a broader understanding of the cultural context and social interactions within a community.

Further Detail

Introduction.

Case study and ethnography are two research methods commonly used in social sciences and other fields to gain a deeper understanding of a particular phenomenon or group of people. While both methods aim to provide rich and detailed insights, they differ in their approach, scope, and data collection techniques. In this article, we will explore the attributes of case study and ethnography, highlighting their similarities and differences.

Definition and Purpose

Case study is a research method that involves an in-depth examination of a specific individual, group, or event. It aims to provide a comprehensive analysis of a particular case, often focusing on a unique or rare occurrence. On the other hand, ethnography is a qualitative research method that involves immersing the researcher in the natural environment of a group or community to observe and understand their culture, behaviors, and social interactions.

Scope and Generalizability

One key difference between case study and ethnography lies in their scope and generalizability. Case studies are typically more focused and specific, aiming to provide detailed insights into a particular case or situation. The findings of a case study may not be easily generalized to a larger population due to the uniqueness of the case being studied.

On the other hand, ethnography aims to capture the broader cultural and social dynamics of a group or community. By immersing themselves in the natural setting, ethnographers can observe and document the behaviors, beliefs, and practices of the group. Ethnographic research often seeks to uncover patterns and themes that may be applicable to similar groups or communities, allowing for a higher level of generalizability.

Data Collection

Another important aspect to consider when comparing case study and ethnography is their data collection techniques. In case studies, researchers often rely on multiple sources of data, including interviews, surveys, observations, and document analysis. These various data sources help provide a comprehensive understanding of the case being studied.

On the other hand, ethnography primarily relies on participant observation, where the researcher actively engages with the group being studied, often for an extended period. This immersive approach allows the researcher to gain firsthand experience and insights into the culture, norms, and practices of the group. Ethnographers may also conduct interviews and collect artifacts or documents to supplement their observations.

Time and Resources

Case studies and ethnography also differ in terms of the time and resources required to conduct the research. Case studies are often more time-efficient, as they focus on a specific case or event. Researchers can collect data relatively quickly and analyze it in a shorter timeframe. However, the depth of analysis and the level of detail may vary depending on the complexity of the case.

On the other hand, ethnography is a time-consuming process that requires a significant investment of time and resources. Researchers need to spend an extended period in the field, building rapport with the community, and gaining their trust. The immersive nature of ethnography allows for a more comprehensive understanding of the group, but it also demands a longer-term commitment from the researcher.

Analysis and Interpretation

Both case study and ethnography involve a detailed analysis and interpretation of the collected data. In case studies, researchers often employ various analytical frameworks or theories to make sense of the data and draw conclusions. The analysis may involve identifying patterns, themes, or causal relationships within the case being studied.

Similarly, ethnographic research involves a rigorous analysis of the collected data. Ethnographers often engage in a process called coding, where they categorize and organize the observations, interviews, and other data sources. This coding process helps identify recurring themes, cultural practices, and social dynamics within the group. Ethnographers may also use theoretical frameworks to interpret their findings and provide a deeper understanding of the observed phenomena.

Applications

Both case study and ethnography have diverse applications across various disciplines. Case studies are commonly used in psychology, business, medicine, and law to examine individual cases, diagnose specific conditions, or understand unique situations. They provide valuable insights into complex phenomena that cannot be easily replicated or studied through other research methods.

On the other hand, ethnography finds its applications in anthropology, sociology, cultural studies, and other social sciences. Ethnographic research allows for a holistic understanding of different cultures, communities, and social groups. It helps uncover the underlying meanings, values, and practices that shape the lives of individuals within a specific cultural context.

In conclusion, case study and ethnography are two distinct research methods that offer valuable insights into specific cases or cultural contexts. While case studies provide a detailed analysis of a particular case, ethnography allows for a broader understanding of social and cultural dynamics. Both methods have their strengths and limitations, and the choice between them depends on the research objectives, scope, and available resources. By employing these research methods appropriately, researchers can gain a deeper understanding of the complexities of human behavior, culture, and society.

Comparisons may contain inaccurate information about people, places, or facts. Please report any issues.

Home » Education » Difference Between Case Study and Ethnography

Difference Between Case Study and Ethnography

Main difference – case study vs ethnography.

Case studies and ethnographies are two popular detailed, qualitative studies used in the field of social science . Although there are certain similarities between these two methods such as their holistic nature, and the extended time period, there are also some differences between the two. The main difference between case study and ethnography is their focus; ethnography aims to explore cultural phenomenon whereas case studies aim to describe the nature of phenomena through a detailed investigation of individual cases.

What is a Case Study

A case study is a detailed investigation of a single event, situation or an individual in order to explore and unearth complex issues. Yin (1984) defines case study as “an empirical inquiry that investigates a contemporary phenomenon within its real-life context; when the boundaries between phenomenon and context are not clearly evident; and in which multiple sources of evidence are used.” Although case studies are always associated with qualitative research, they can also be quantitative in nature. They are often used to explore community-based issued such as poverty, illiteracy, unemployment, prostitution, and drug addiction.

A successful case study is context-sensitive, holistic, systematic, layered and comprehensive. The process of a case study involves,

• Identifying and defining the research questions
• Selecting the cases and deciding techniques for data collection and analysis
• Collecting data in the field
• Evaluating and analysing the data
• Preparing the report

Data collection methods in a case study may involve interviews, observations, questionnaires, checklists, analysis of recorded data and opinionnaires. Case studies can also be divided into different categories. Exploratory, descriptive and explanatory case studies are three such categories.

Case studies are preferred by many researchers in the field of social sciences since they offer detailed and in-depth information about a particular phenomenon. However, it is difficult to use the data obtained from a case study to form generalisation since it only focuses on a single event or phenomenon.

Figure 1: Questionnaires are one method of data collection in a case study.

What is an Ethnography

Ethnography is a detailed and in-depth study of everyday life and practice. In other words, it is the systematic study of people and cultures. A researcher who is engaged in ethnography is known as an ethnographer . Ethnographers explore and study culture from an insider’s point of view (emic perspective).

Ethnography traditionally involved focusing on a bounded and a definable race, ethnicity or group of people; for example, study of a particular African tribe. However, modern ethnography also focus on different aspects of the contemporary social life.

Ethnographic research mainly involves field observations, i.e., observations of behaviour in a natural setting. The researchers have to spend a considerable amount of time inside a community in order to make such observations. Information about particular socio-cultural phenomena in a community is typically obtained from the members of that particular community. Participant observation and interviews are two of the main data collection methods in this type of studies. Ethnographic studies take a longer period of time than other types of research since it takes long-term involvement and observation to understand the attitudes, beliefs, and behaviours of a community.

Figure 2: Observation and participant interviews are main data collection methods in ethnography.

Definition 

Case Study: A case study is a detailed investigation of a single event, situation or an individual in order to explore and unearth complex issues.

Ethnography: An ethnography is the detailed and systematic study of people and cultures.

Case Study: Case studies focus on a single event, incident or individual.

Ethnography: Ethnography observes cultural phenomenon.

Case study: Case study intends to uncover the tacit knowledge of culture participants.

Ethnography: Ethnography aims to describe the nature of phenomena through detailed investigations of individual cases.

Data Collection Methods

Case Study: Case studies may use interviews, observations, questionnaires, checklists, analysis of recorded data and opinionnaires.

Ethnography: Ethnographic studies use participant observations and interviews.

Special Requirements

Case Study: The researcher does not have to live in a particular community.

Ethnography: The researcher has to spend a considerable amount time inside that particular community.

Conclusion 

Case study and ethnography may have some similarities; however, there is a considerable difference between case study and ethnography as explained above. The main difference between case study and ethnography lies in their intent and focus; case studies intend to uncover the tacit knowledge of culture participants whereas ethnographic studies intend to describe the nature of phenomena through detailed investigations of individual cases. There are also differences between them in terms of data collection and analyis. 

• Cohen, Arie. “Ethnography and case study: a comparative analysis.”  Academic Exchange Quarterly  7.3 (2003): 283-288.
• Yin, Robert. “Case study research. Beverly Hills.” (1984).

Image Courtesy:

• “plings_005” by  Plings   (CC BY 2.0)  via Flickr
• “Bronisław Malinowski among Trobriand tribe 3”  By Unknown (maybe Stanisław Ignacy Witkiewicz, 1885-1939) (Public Domain) via Commons Wikimedia

About the Author: Hasa

Hasanthi is a seasoned content writer and editor with over 8 years of experience. Armed with a BA degree in English and a knack for digital marketing, she explores her passions for literature, history, culture, and food through her engaging and informative writing.

​You May Also Like These

Leave a reply cancel reply.

Extract insights from Customer & Employee Interviews. At Scale.

Ethnography vs. case study: choosing the right approach.

Home » Ethnography vs. Case Study: Choosing the Right Approach

Research methodology selection is a critical step in any academic or professional study. When delving into human behavior and social phenomena, two popular approaches often come to the forefront: ethnography and case study research. Each method offers unique insights and perspectives, making the choice between them a pivotal decision for researchers.

Ethnography immerses the researcher in the daily lives of participants, providing a rich, contextual understanding of cultural dynamics. On the other hand, case studies offer an in-depth exploration of specific instances or situations, allowing for detailed analysis of complex issues. The selection between these methodologies depends on various factors, including research objectives, time constraints, and the nature of the subject matter. By carefully considering these elements, researchers can ensure their chosen approach aligns with their goals and yields meaningful results.

Understanding the Foundations of Research Methodology Selection

Selecting the appropriate research methodology is crucial for the success of any study. When it comes to ethnography and case studies, researchers must carefully consider their research objectives and the nature of their inquiry. Ethnography offers a deep dive into cultural contexts, allowing researchers to immerse themselves in the daily lives of their subjects. This approach is particularly valuable for understanding complex social dynamics and cultural nuances.

On the other hand, case studies provide a focused examination of specific instances or phenomena. They are ideal for exploring unique situations or testing theoretical propositions in real-world settings. The choice between ethnography and case study often depends on the research questions, available resources, and the desired depth of analysis. Researchers must weigh the benefits of broad cultural insights against the detailed exploration of particular cases to determine which methodology aligns best with their research goals.

What is Ethnography?

Ethnography is a qualitative research method that involves immersing oneself in a particular social setting to observe and understand its culture, behaviors, and interactions. This approach allows researchers to gain deep insights into the lived experiences of individuals or groups within their natural environment. Unlike case studies, which focus on specific instances or phenomena, ethnography aims to capture the broader context and cultural nuances of a community or organization.

Researchers conducting ethnographic studies typically spend extended periods in the field, participating in daily activities and engaging with community members. This prolonged engagement enables them to develop a comprehensive understanding of the social dynamics, beliefs, and practices that shape the group's identity. By employing various data collection techniques, such as participant observation, interviews, and artifact analysis, ethnographers can uncover hidden patterns and meanings that might not be apparent through other research methodologies.

What is a Case Study?

A case study is a research method that involves an in-depth examination of a specific subject, such as an individual, group, or event. This approach allows researchers to gather detailed information about a particular phenomenon within its real-world context. Case studies are particularly useful when investigating complex issues that require a holistic understanding of the subject matter.

Researchers employing case studies typically collect data from multiple sources, including interviews, observations, and document analysis. This comprehensive approach enables them to capture nuanced insights and explore the intricate relationships between various factors influencing the subject under investigation. By focusing on a single case or a small number of cases, researchers can delve deep into the underlying mechanisms and processes, uncovering valuable insights that might be overlooked in broader, more generalized studies.

Key Differences in Research Methodology Selection: Ethnography vs. Case Study

When selecting a research methodology, understanding the nuances between ethnography and case study approaches is crucial. Ethnography immerses researchers in the daily lives of participants, offering rich cultural insights over extended periods. This method excels at uncovering hidden social dynamics and cultural patterns within communities or organizations.

In contrast, case studies focus on specific instances or phenomena, providing in-depth analysis of particular situations or events. They are ideal for examining complex issues within real-world contexts, often combining multiple data sources to build a comprehensive picture. While ethnography seeks broad cultural understanding, case studies aim to explore specific scenarios in detail. The choice between these methodologies depends on research goals, time constraints, and the nature of the inquiry at hand.

When to Choose Ethnography

Ethnography and case studies are both valuable research methodologies, but choosing the right approach depends on your specific research goals. Ethnography shines when you need to immerse yourself in a culture or community to gain deep, contextual insights. This method is particularly effective when studying complex social phenomena or trying to understand the nuances of human behavior within a specific group.

Consider ethnography when your research requires a holistic view of a culture or community. It's ideal for uncovering hidden patterns, unspoken rules, and subtle interactions that might be missed with other methods. For instance, if you're exploring how a particular subculture uses technology in their daily lives, ethnography allows you to observe and participate in their routines, providing rich, firsthand data. However, keep in mind that ethnography is time-intensive and requires significant commitment from both researchers and participants.

When to Choose a Case Study

Case studies prove invaluable when researchers seek to explore complex phenomena within specific contexts. This approach shines when investigating real-world situations that require in-depth analysis of a particular instance or event. Researchers often opt for case studies when they aim to understand the intricacies of a unique scenario or when they need to examine a subject holistically.

Choosing a case study becomes particularly appropriate when the research question demands a detailed exploration of "how" or "why" certain outcomes occur. This method excels in situations where the boundaries between the phenomenon and its context are not clearly defined. Additionally, case studies offer an excellent choice for researchers who wish to generate hypotheses for future studies or when the subject matter is too complex for experimental or survey research methodologies.

Conclusion: Making the Right Choice in Research Methodology Selection

Selecting the right research methodology is crucial for the success of any study. As we've explored the strengths and limitations of ethnography and case studies, it's clear that both approaches offer unique insights. The choice between them depends on your research goals, available resources, and the nature of your subject matter.

Consider your research questions carefully when making your decision. If you aim to understand cultural nuances or social behaviors in depth, ethnography might be the better choice. On the other hand, if you're focusing on a specific phenomenon or seeking to analyze complex real-world situations, a case study approach could yield more relevant results. Remember, the key to effective research lies in aligning your methodology with your objectives and the context of your study.

Turn interviews into actionable insights

On this Page

Explain Ethnography: A Beginner’s Guide

You may also like, top behavioural research agency for consumer insights.

Top full service research agency for 2024 projects

Top market insight companies for strategic planning in 2024.

Unlock Insights from Interviews 10x faster

• Request demo
• Get started for free

Comparing Case Study and Ethnography as Qualitative Research Approaches

• December 2013
• Jurnal ILMU KOMUNIKASI 5(1)

• Monash University (Australia)

Discover the world's research

• 25+ million members
• 160+ million publication pages
• 2.3+ billion citations

• F Chasanatun
• H. E. Rudyanto

• Mellese Madda Gatisso

• QUAL HEALTH RES

• Marcia Finlayson

• Mohamed M. Elnakib
• Monique Turner

• Amy Zaharlick
• Robert K. Yin

• James H. McMillan
• Recruit researchers
• Join for free
• Login Email Tip: Most researchers use their institutional email address as their ResearchGate login Password Forgot password? Keep me logged in Log in or Continue with Google Welcome back! Please log in. Email · Hint Tip: Most researchers use their institutional email address as their ResearchGate login Password Forgot password? Keep me logged in Log in or Continue with Google No account? Sign up

Case Study vs. Ethnography: What's the Difference?

Key Differences

Comparison chart, data collection, generalization, case study and ethnography definitions, ethnography, are case studies generalizable, how is ethnography conducted, can a case study be quantitative, what is a case study, how long does a case study take, what is the main purpose of ethnography, what makes ethnography unique in research, what skills are needed for ethnography, can case studies be used for hypothesis testing, are case studies suitable for all fields of study, what is a limitation of a case study, can ethnography be done remotely, how does a case study differ from a survey, what role does language play in ethnography, what ethical considerations are involved in ethnography, can multiple cases be included in a case study, how does ethnography benefit sociology, how does technology impact ethnography, is ethnography considered a scientific method, what types of subjects are suitable for case studies.

Trending Comparisons

Popular Comparisons

New Comparisons

• DOI: 10.24002/jik.v5i1.221
• Corpus ID: 15484022

Comparing Case Study and Ethnography as Qualitative Research Approaches

• Published 4 December 2013
• Jurnal ilmu Komunikasi

46 Citations

Ethnographic and case study approaches: philosophical and methodological analysis, digitally-mediated mothering: an ethnography of health and parenting groups on facebook.

• Highly Influenced

Negotiating pedagogical positions in higher education during COVID-19 pandemic: teacher's narratives

Organizational culture and masculinities in a startup company in finland, parents' perception of their involvement in schooling activities: a case study from rural secondary schools in bangladesh, evidence of spiritual capital in the schooling of second-generation ghanaians in amsterdam, the spirits and transition: the second generation and the church of pentecost-uk, investigating the status of women engineers in education and employment during the covid-19 pandemic, 'youth amplified': using critical pedagogy to stimulate learning through dialogue at a youth radio show, artisans regeneration model: culture sustainability effort for creativity and indigenous skill, 19 references, an introduction to qualitative research, qualitative research methods, ethnography: problems and prospects.

• Highly Influential

Social Research Methods: Qualitative and Quantitative Approaches

Ethnography in action. how ethnography was established in swedish educational research, hypermedia ethnography in educational settings: possibilities and challenges, applications of case study research, a companion to qualitative research, educational research: fundamentals for the consumer. second edition., related papers.

Showing 1 through 3 of 0 Related Papers

Difference between case study & ethnography

Introduction

In the social sciences, case study and ethnography are two popular research methodologies. While there are similarities between the two, there are also differences in data collection and the overall purpose of the study. This article aims to clarify these differences.

A case study is an in-depth study of a particular instance, event, individual, or group. It can be explanatory or descriptive in nature, but its focus is on understanding the why’s and implications of the subject of study. Case studies draw conclusions based on prior research and systematic analysis of data.

Ethnography

Ethnography is the art and science of describing a group or culture. It is an investigative approach that requires the ethnographer to behave like a neutral observer, without imposing personal viewpoints or making subjective judgments. Participant observation is often used as a method of data collection in ethnography, where the ethnographer becomes a part of the group being studied and records observations without analysis.

Differences

– Ethnography focuses on describing a group or culture, while a case study focuses on a particular instance, event, individual, or group. – Ethnography requires participant observation as a data collection method, while it is not necessary for a case study. – A case study is more outward looking, focusing on the why’s and implications, whereas ethnography is more inward looking. – Ethnography takes a longer time to conduct than a case study.

In summary, a case study is an in-depth analysis of a specific subject, while ethnography is an in-depth study of a group or culture. The methods of data collection and the perspectives of analysis differ between the two methodologies.

Key Takeaways

1. The difference between a case study and ethnography is that ethnography is a study of a culture or ethnic group, while a case study investigates a particular instance, event, or individual. 2. Ethnography requires participant observation as a data collection method, while it is not necessary in a case study. 3. A case study is more outward-looking, focusing on the why’s and implications of an event, while ethnography is more inward-looking and focused on describing a group or culture.

LEAVE A REPLY Cancel reply

Save my name, email, and website in this browser for the next time I comment.

Related Articles

Difference between power & authority, distinguishing could of & could have, distinguishing pixie & bob haircuts, distinguishing between debate & discussion, distinguishing between dialogue & conversation, distinguishing between a present & a gift, distinguishing between will & can, distinguishing between up & upon.

Want to create or adapt books like this? Learn more about how Pressbooks supports open publishing practices.

Research Guides

Ethnographic Case Studies

Jeannette Armstrong; Laura Boyle; Lindsay Herron; Brandon Locke; and Leslie Smith

Description

This research guide discusses ethnographic case study. While there is much debate over what, precisely, delimits a case study , the general consensus seems to be that ethnographic case studies differ from other types of case studies primarily in their focus, methodology, and duration. In essence, ethnographic case studies are case studies “employing ethnographic methods and focused on building arguments about cultural, group, or community formation or examining other sociocultural phenomena” (Schwandt & Gates, 2018, p. 344), typically with a long duration, per the demands of ethnographic work. In essence, ethnographic case studies are case studies “employing ethnographic methods and focused on building arguments about cultural, group, or community formation or examining other sociocultural phenomena” (Schwandt & Gates, 2018, p. 344), typically with a long duration, per the demands of ethnographic work. Indeed, in its very situatedness, ethnography has a “case study character” and is “intimately related” to case studies (Ó Rian, 2009, p. 291); though there is currently a move to extract ethnographic work from overly situated contexts and use extended case methods, “[e]thnographic research has long been synonymous with case studies, typically conceived of as grounded in the local and situated in specific, well-defined and self-contained social contexts” (Ó Rian, 2009, p. 290). Because ethnography, in practice, is often a kind of case study, it’s useful to consider ethnography and case studies each in their own right for a fuller picture of what ethnographic case study entails.

Ethnographic research is one approach under the larger umbrella of qualitative research. Methodologically, it is, “a theoretical, ethical, political, and at times moral orientation to research, which guides the decisions one makes, including choices about research methods” (Harrison, 2014, p. 225), that is at its crux “based upon sharing the time and space of those who one is studying” (Ó Rian, 2009, p. 291)–a situated, nuanced exploration seeking a thick description and drawing on methods such as observation and field notes. According to …an ethnography focuses on an entire culture-sharing group and attempts to develop a complex, complete description of the culture of the group. Creswell and Poth (2018), an ethnography focuses on an entire culture-sharing group and attempts to develop a complex, complete description of the culture of the group. In doing so, ethnographers look for patterns of behavior such as rituals or social behaviors, as well as how their ideas and beliefs are expressed through language, material activities, and actions (Creswell & Poth, 2018). Yin (2016)  suggests that ethnographies seek “to promote embedded research that fuses close-up observation, rigorous theory, and social critique. [Ethnographies foster] work that pays equal attention to the minutiae of experience, the cultural texture of social relations, and to the remote structural forces and power vectors that bear on them” (p. 69).

Case study research, meanwhile, is characterized as an approach “that facilitates exploration of a phenomenon within its context using a variety of data sources” (Baxter & Jack, 2008, p. 544). The aim of case studies is precise description of reconstruction of cases (Flick, 2015). The philosophical background is a qualitative, constructivist paradigm based on the claim that reality is socially constructed and can best be understood by exploring the tacit, i.e., experience-based, knowledge of individuals. There is some debate about how to define a The philosophical background is a qualitative, constructivist paradigm based on the claim that reality is socially constructed and can best be understood by exploring the tacit, i.e., experience-based, knowledge of individuals. “case” (e.g., Ó Rian, 2009), however. As Schwandt and Gates (2018) write, “[A] case is an instance, incident, or unit of something and can be anything–a person, an organization, an event, a decision, an action, a location”; it can be at the micro, meso, or macro level; it can be an empirical unit or a theoretical construct, specific or general; and in fact, “what the research or case object is a case of may not be known until most of the empirical research is completed” (p. 341). The two authors conclude that given the multifarious interpretations of what case study is, “[b]eyond positing that case study methodology has something to do with ‘in-depth’ investigation of a phenomenon . . . , it is a fool’s errand to pursue what is (or should be) truly called ‘case study’” (p. 343, 344).

Baxter, P., & Jack, S. (2008). Qualitative case study methodology: Study design and implementation for novice researchers. The Qualitative Report, 13 (4), 544-559.

Creswell, J. W., & Poth, C. N. (2018). Qualitative inquiry & research design: Choosing among five approaches (4th ed.). Los Angeles, CA: SAGE.

Flick, U. (2015). Introducing research methodology . Los Angeles, CA: SAGE.

Rian, S. (2009). Extending the ethnographic case study. In D. Byrne & C. C. Ragin (Eds.), The SAGE handbook of case-based methods (pp. 289–306). Thousand Oaks, CA: SAGE.

Schwandt, T. A., & Gates, E. F. (2018). Case study methodology. In N. K. Dezin & Y. S. Lincoln (Eds.), The SAGE handbook of qualitative research (5th ed.; pp. 341-358). Thousand Oaks, CA: SAGE.

Yin, R. K. (2016). Qualitative research from start to finish (2nd ed.). New York, NY: The Guilford Press.

Key Research Books and Articles on Ethnographic Case Study Methodology

Fusch, G. E., & Ness, L. R. (2017). How to conduct a mini-ethnographic case study: A guide for novice researchers. The Qualitative Report , 22 (3), 923-941.  Retrieved from https://nsuworks.nova.edu/tqr/vol22/iss3/16

In this how-to article, the authors present an argument for the use of a blended research design, namely the Ethnographic Case Study, for student researchers. To establish their point of view, the authors reiterate recognized research protocols, such as choosing a design that suits the research question to ensure data saturation. Additionally, they remind their reader that one must also consider the feasibility of the project in terms of time, energy, and financial constraints.

Before outlining the benefits and components of the Ethnographic Case Study approach, the authors provide detailed narratives of ethnographic, mini-ethnographic (sometimes referred to as a focused ethnography ), and case study research designs to orient the reader. Next, we are introduced to the term mini-ethnographic case-study design, which is defined as a blended design that is bound in time and space and uses qualitative ethnographic and case study collection methods. The benefits of such an approach permit simultaneous generation of theory and the study of that theory in practice, as it allows for the exploration of causality.

Ethnographic Case Study research shares many characteristics with its parent approaches.  For example, subjectivity and bias are present and must be addressed. Next, data triangulation is necessary to ensure the collected qualitative data and subsequent findings are valid and reliable. Data collection methods include direct observation, fieldwork, reflective journaling, informal or unstructured interviews, and focus groups. Finally, the authors discuss three limitations to the ethnographic case study. First, this design requires the researcher to be embedded, yet the duration of time may not be for as long when compared to full-scale ethnographic studies.  Second, since there are fewer participants, there should be a larger focus on rich data as opposed to thick data, or said differently, quality is valued over quantity. Third, the researcher must be aware that the end-goal is not transferability, but rather the objective is to gain a greater understanding of the culture of a particular group that is bound by space and time.

Gregory, E. & Ruby, M. (2010) The ‘insider/outsider’ dilemma of ethnography: Working with young children and their families in cross-cultural contexts. Journal of Early Childhood Research, 9 (2), 1-13. https://doi.org/10.1177/1476718X10387899

This article focuses on the dilemma of insider and outsider roles in ethnographic work. It challenges the notion that a researcher can be both an insider and an outsider at the same time. There is no insider/outsider status; it is one or the other–not both.

It is easy to make assumptions about one’s status as an insider. It is not uncommon for a researcher to assume that because one is working amongst his/her “own” people sharing a similar background, culture, or faith that she/he is an insider. Likewise, a researcher may assume that it will be easy to build rapport with a community with which he/she has commonalities; however, it is important to keep in mind that the person may be an insider but the researcher may not have this same status. When the person enters into the protective space of family or community as a researcher, it is similar to being an outsider. Being a researcher makes one different, regardless of the commonalities that are shared. It is not the researcher’s presumed status of “insider” or “outsider” that makes the difference; rather, researcher status is determined by the participants or community that is being studied. It is wise for researchers to understand that they are distinctively one of “them” as opposed to one of “us”. This is not to say that researchers cannot become an “insider” to some degree. But to assume insider status, regardless of the rationale, is wrong. Assuming common beliefs across cultures or insider status can lead to difficulties that could impact the scope or nature of the study.

In conclusion, regardless of the ethnographic design (e.g., realist ethnography, ethnographic case study, critical ethnography), it is important for the researcher to approach the study as an “outsider”. Although the outsider status may change over time, it essential to understand that when one enters a community as a researcher or becomes a researcher within a community, insider status must be earned and awarded according to the participants in the community.

Ó Rian, S. (2009). Extending the ethnographic case study. In D. Byrne & C. C. Ragin (Eds.), The SAGE handbook of case-based methods (pp. 289–306). Thousand Oaks, CA: SAGE.

In this chapter, Ó Rian valorizes the problems and potential hiding within the vagaries of ethnographic “case” boundaries, arguing that “whereas the fluid and multi-faceted aspects of the ethnographic case pose dilemmas for ethnographers, they can also become resources for ethnographers in exploring theoretical and empirical questions” (p. 292). Indeed, he views the idea of firm case boundaries as a weakness, as “definitions of the case will rule in and out certain social processes,” and suggests ethnography’s flexibility can deal with this problem well because it permits researchers to “question the boundaries of the case as the study proceeds,” leading to a “de- and re-construction of the case that . . . places ethnography at the centre of a resurgent contextualist paradigm of social inquiry . . . that is increasingly self-consciously exploring its own theoretical and methodological foundations” (p. 304). Most of the chapter delves into these possibilities for exploration, offering an insightful (if occasionally difficult to follow) perspective on how they have been proceeding.

The chapter offers considerations that might be particularly helpful to researchers undertaking ethnographic case studies who are struggling to connect their cases, so firmly rooted in a particular context and their own personal experiences and observations, to a bigger picture. Ó Rian elucidates the reflexive strategies various ethnographers have adopted as they’ve sought “[t]o achieve a link between context-specific data and meso- or macro-level generalizations,” categorizing these strategies into three “interlocking extensions of case study research” (p. 292): personal extensions (related to “the shaping of the boundaries of the case by the ethnographer’s location within the field and . . . how ethnographers can convey their personalized experiences and tacit learning to readers” [p. 292]), theoretical extensions (which bridge the gap between the situated worlds being explored and “the larger structures and processes that produced and shaped them” [p. 292]), and empirical extensions (“creative efforts to experiment with the empirical boundaries of the ethnographic case” [p. 292] by bringing in, for example, historical context, social networks, etc.). The crux of his argument is that ethnographic researchers have a prime opportunity to push against the boundaries of their context and “extend their cases across space, time and institutional structures and practices” so that the ethnographer is “multiply, if perhaps a bit uncomfortably, situated” (p. 304), and also to include an “emphasis on the ongoing process of theoretical sampling within the process of the ethnographic study, with close attention to be paid to the paths chosen and rejected, and the reasons for these decisions” (p. 304). These kinds of extensions offer an opportunity for theories to “be refined or reconstructed” as the researcher attempts to locate their personal experience within a broader framework, allowing “[t]he case study . . . to challenge and reconstruct the preferred theory” while also connecting the case to a larger body of work, particularly because theory “carries the accumulated knowledge of previous studies” (p. 296).

Ó Rian’s in-depth descriptions of how other researchers have varyingly handled these personal, theoretical, and empirical extensions might be a bit overwhelming to novice researchers but overall can offer a way to “locate their cases within broader social processes and not solely within their own personal trajectories” (p. 294)–while also helping to situate their reflections and extensions within a larger body of literature replete with researchers struggling with similar questions and concerns.

This chapter offers an  in-depth, generally accessible (but occasionally overwhelming) overview of case studies of all sorts and integrates an extensive review of relevant literature. The authors provide an informed perspective on various considerations and debates in the case study field (e.g., varying definitions of what a “case” is construed to be; interpretive vs. critical realist orientations; the relative benefits of and techniques involved in different types of approaches), helping novice researchers locate and better describe their own approach within the context of the field. The information is quite detailed and delves into a wide variety of case study types, suggesting this chapter might best be first skimmed as an initial introduction, followed by more careful readings of relevant sections and perusal of the key texts cited in the chapter. The breadth of this chapter makes it a helpful resource for anyone interested in case-study methodology.

The authors do not specifically explore ethnographic case studies as a separate type of case study. They do, however, briefly touch on this idea, locating ethnography within the interpretive orientation (comprising constructivist approaches offering “phenomenological attention to lived experience” [p. 344]). The authors also cite researchers who distinguish it due to its “[employing] ethnographic methods and focus on building arguments about cultural, group, or community formation or examining other sociocultural phenomena” (p. 344). Ethnographic case study is placed in contrast to case studies that use non-ethnographic methods (e.g., studies “relying perhaps on survey data and document analysis”) or that “are focused on ‘writing culture’” (p. 344).

Two aspects of this chapter are particularly useful for novice researchers. First, it is worth highlighting the authors’ discussion of varying definitions of what a “case” is, as it can provide an interesting reconceptualization of the purpose of the research and the reason for conducting it. The second noteworthy aspect is the authors’ detailed descriptions of the four main case study uses/designs ( descriptive, hypothesis generation or theory development, hypothesis and theory testing , and contributing to normative theory ), which the authors beautifully align with the respective purposes and methods of each type while also offering insight into relevant conversations in the field.

Further Readings

Moss, P. A., & Haertel, E. H. (2016). Engaging methodological pluralism. In D. H. Gitomer & C. A. Bell (Eds.), Handbook of Research on Teaching (pp. 127–247). Washington, DC: American Educational Research Association.

Simons, H. (2014). Case study research: In-depth understanding in context. In P. Leavy (Ed.), The Oxford handbook of qualitative research (pp. 455–470). Oxford, UK: Oxford University Press.

Recent Dissertations Using Ethnographic Case Study Methodology

Cozzolino, M. (2014). Global education, accountability, and 21st century skills: A case of curriculum innovation . Retrieved from ProQuest Dissertations & Theses Global. (Order Number 3648007)

This dissertation is self-described as an ethnographic case study of a small, public, suburban high school in Pennsylvania. In this study, the researcher investigates the school’s process of integrating global education into its curriculum by implementing a school-wide initiative (Global Studies Initiative or GSI) as well as a program of study (Global Studies Credential or GSC). Cozzolino asserts that her framework has been shaped by both social constructivism and critical/Freirean pedagogy. From the constructivist view, she views knowledge as constructed through social interaction, and thus she sought to understand the world in which the research participants work, learn, and experience large parts of their lives. It is here that she situates the first three research questions that entail looking at the the GSI and the GSC in terms of their features, rationales, and implementations. The fourth question involves understanding the students’ views and perceptions of the GSC and here the author takes up a critical and Freirean pedagogy to honor and hear the voices of the students themselves.

The study design is therefore an embedded single-case study in that it is bound by the place (Olympus High School) and by its population. Furthermore, it is also a case within a case, as it seeks to understand the students’ perspectives of the global programming. The case study is ethnographically rooted through the multiple ethnographic data sources such as participant-observations and a prolonged engagement at the research site. Cozzolino embedded herself in the research site over a five-year period and became an active and invested member of the school community, thereby establishing a sound rationale for an ethnographic case-study approach.

The author concludes that there were some competing priorities about the overall initiative from stakeholders inside and outside the school district. This resulted in a less than ideal implementation of the program of study across the curriculum. Nonetheless, the students who were enrolled in these courses reported it to be a worthwhile experience. While Cozzolino presents specific recommendations for the improvements at Olympus High, she also offers implications for several other groups. First, she provides advice for implementation to other educational institutions that aim to integrate a global focus into their curriculum. Next, she gives recommendations for local, state, and national policy changes. Finally, she gives suggestions for engaging all parties in fruitful discourse to achieve their ultimate goal of implementing a meaningful and valuable global education curriculum.

Hamman, L. (2018). Reframing the language separation debate: Language, identity, and  ideology in two-way immersion . Retrieved from ProQuest Dissertations & Theses Global. (Order Number 2089463322)

This study explored the issues of surrounding language separation in two-way immersion (TWI) classrooms. The author looked at how classroom language practices and teacher ideologies influenced the student experience and how the students’ understanding of what it means to be bilingual is influenced in a classroom that purports to be equitable in terms of language use.

The study is theoretically grounded in sociocultural, critical, and postcultural theories and adapted Lemke’s ecosocial system to conceptualize TWI classroom. Hamman also drew upon translanguaging theory and dynamic bilingualism to provide a framework for a more modern and nuanced perspective of bilingualism, bilingual learning, and bilingual students.

The author combined a single-case study approach with ethnographic methods to “engage in close analysis of classroom language use and the discursive negotiation of identities and ideologies, while situating these analyses within a rich understanding of the sociolinguistic context of this TWI classroom” (p. 78-79). She employed various ethnographic methods such as taking fieldnotes, conducting participant observations, interviewing, and memoing. The study is “bound” in that it takes place in one 2nd-grade classroom with one teacher and 18 students over the course of one year.

Hamman concludes that student perspectives on language separation should be considered, since this forced separation of language influenced how they thought of their developing bilingualism and identity as bilinguals. Furthermore, the study envisages a linguistic “middle ground” to strict separation that allows for appropriate and meaningful spaces for linguistic negotiation. Finally, this dissertation asserts that the strict separation of languages codifies a monoglossic ideology mindset and limits learners’ possibilities for learning and making connections across languages.

Kim, S. (2015). Korean migrant youth identity work in the transnational social field: A link between identity, transnationalism, and new media literacy . Retrieved from University of Missouri-St. Louis Institutional Repository Library. https://irl.umsl.edu/dissertation/158/

This doctoral dissertation takes an ethnographic case study approach to explore the identity formation of transnational Korean youth. The researcher, herself a Korean immigrant to the U.S. navigating complex identity processes, focuses on these research questions: “1) what are the contexts in which migrant youth negotiate their identities? 2) how do youth understand and negotiate their sense of belonging? 3) how do youth’s [sic] cultural and literacy practices inform and shape their identities? 3i) how do youth make use of transnational new media for their identity work? 3ii) how do literacy practices potentially shape their identities?” (p. 7).

Drawing on Leander and McKim (2013), the author conceptualizes her study as a “connective ethnography” (p. 36) encompassing multiple spaces, both digital and physical, in which “space” comprises a variety of relationships, instead of a more traditional ethnography bounded by physical space. The “case study” aspect, meanwhile, refers to the four specific participants in which she chose to focus. She chose Korean immigrants in St. Louis, in general, due to their mobility between the U.S. and Korea, their high use of digital communication and information technology, and their limited access to the cultural resources of Korea in a Midwestern city. From an initial 32 possible participants purposively selected, the researcher chose four focal participants based on their Korean ethnicity, biliteracy in Korean and English, age (between 11 and 19 years old), residence in the U.S. (for at least 2 years), and their use of digital communication technologies. Data sources included an initial screening survey, an identity map each participant created, informal recorded conversations, recorded interviews in either English or Korean, field notes from the researcher’s interactions with the youth in various settings (home, school, community centers), and “literacy documents” (evidence of literacy practices from participants’ school and home, emails to the researcher, or activities in digital spaces). She used social semiotic multimodal discourse analysis and what she describes as “grounded theory thematic analysis” to analyze the data.

This is a reflective, thoughtful, and interesting dissertation. The author carefully notes the relationship between the data sources and her research questions, specifically addresses steps she took to ensure the validity of the data (e.g., triangulation via multiple data sources and theoretical frameworks, member checks, and feedback from her professors and other researchers), and discloses her own positionalities and biases. Her discussion includes not only a clear thematic exploration of her findings but also offers specific practical suggestions for how her findings can be applied and extended in the classroom.

Internet Resources

Abalos-Gerard Gonzalez , L. (2011). Ethnographic research . Retrieved from https://www.slideshare.net/lanceabalos/ethnographic-research-2?from_action=save

Created by Lance Gerard G. Abalos, teacher at the Department of Education-Philippines, this SlideShare, Ethnographic Research , explains that, regardless of specific design, ethnographic research should be undertaken “without any priori hypothesis to avoid predetermining what is observed or that information is elicited from informants . . .hypotheses evolve out of the fieldwork itself” (slide 4). It is also suggested that researchers refer to individuals from whom information is gathered as ‘informants’ is preferred over the term ‘participants’ (slide 4).

According to Abalos, “It is not the data collection techniques that determine whether the study is ethnographic, but rather the ‘socio-cultural interpretation’ that sets it apart from other forms of qualitative inquiry” (slide 6). A social situation always has three components: a place, actors, and activities (slide 8) and it is the socio-cultural interpretation of the interactions of these three that is the focus of the ethnographic research.

Ethnographic questions should guide what the researcher sees, hears, and collects as data (slide 9). When writing the ethnography, it is essential to ‘bring the culture or group to life’ through the words and descriptions used to describe the place, actors, and activities.

Abalos describes three types of ethnographic designs:

• Realist Ethnographies : an objective account of the situation, written dispassionately from third-person point of view, reporting objectively on information learned from informants, containing closely edited quotations (slide 11-12).
• Ethnographic Case Studies : researchers focus on a program, event, or activity involving individuals rather than a group, looking for shared patterns that develop as a group as a result of the program, event, or activity (slide 13).
• Critical Ethnographies: incorporating a ‘critical’ approach that includes an advocacy perspective, researchers are interested in advocating against inequality and domination (slide 14).

As ethnographic data is analyzed, in any design (e.g., realist, case study, critical), there is a shift away from reporting the facts to making an interpretation of people and activities, determining how things work, and identifying the essential features in themes of the cultural setting (slide 22). “The ethnographer must present the description, themes, and interpretation within the context or setting of the culture-sharing group (slide 23).

Brehm, W. (2016, July 21). FreshEd #13 – Jane Kenway . Retrieved from http://www.freshedpodcast.com/tag/ethnography/ (EDXSymposium: New Frontiers in Comparative Education).

Jane Kenway is with the Australian Research Council and is an emeritus professor at Monash University in Melbourne, Australia. In this podcast, she explains “traditional’ forms of ethnography and multi-sited global ethnography, which are her area of specialization. She considers “traditional” ethnography to have three components: space, time, and mobility.

Insider/outsider stance is explained within the context of spatiality, community, and culture of space specific to ‘traditional” ethnography. Researchers are outsiders who are attempting to enter a space and become insiders, then leave the space once the research is completed. Research is conducted over an extended period of time in one place/space. As a result, researchers will get to know in an extremely intimate manner the ways of life of the community or group. “Work is supposed to be a temporality of slowness. In other words, you don’t rush around like a mad thing in a field, you just quietly and slowly immerse yourself in the field over this extended period of time and get to understand it, get to appreciate it bit by bit.” (minute 7:56).

“Traditional” ethnographers are not necessarily interested in mobility over time or exploring who enters and exits the site. Most ethnographers are only interested in the movement that occurs in the space that is being studied during the time that they are in the field. It is about looking at the roots of the space, not necessarily about looking at the movements into and out of the space.

Multi-sited global ethnography tries to look at the way bounded sites can be studied as unbounded and on the move, as opposed to staying still. It considers how certain things (e.g., things, ideas, people) are  followed as they move. The researcher moves between sites, studying change that is encountered in different sites. From this perspective, the interested lies in the connections between sites. Multiple sites with commonalities can also be studied at the onset, without the need to physically follow.

Paulus, T. M., Lester, J. N., & Dempster, P. G. (2014). Digital Tools for Qualitative Research. Los Angeles, CA: SAGE.

While this text is not solely about ethnographic case studies, it is rich with countless ideas for utilizing digital tools to aid in the multiple facets of qualitative research. In Chapter 5 of their text, entitled Generating Data, the authors dedicate a section to exploring Internet archives and multimedia data. They state that, “in addition to online communities, the Internet is rich with multimedia data such as professionally curated archives, ameteur-created YouTube and Vimeo videos and photo-sharing sites” (p. 81). They provide three specific examples, each explained below: The Internet Archive, CADENSA, and Britain’s BBC Archives.

The Internet Archive ( https://archive.org ) is a non-profit library of millions of free books, movies, software, music, websites, and more. The site also contains a variety of cultural artifacts that are easily available and downloadable. CADENSA ( http://cadensa.bl.uk ) is an online archive of the British Library Sound and Moving Image Catalogue. And finally, the BBC Archives ( http://www.bbc.co.uk/archive/ ) is a particularly useful site for researchers interested in reviewing documentary film and political speeches.

Wang, T. (2016, September). Tricia Wang: The human insights missing from big data. [Video file]. Retrieved from  https://www.ted.com/talks/tricia_wang_the_human_insights_missing_from_big_data

In this TED Talk, Tricia Wang discusses her ethnographic work with technology and advocates for the need to save a place for thick data as opposed to relying only on big data. She argues that while companies invest millions of dollars in generating big data because they assume it will efficiently provide all the answers, it routinely does not provide a good return on investment. Instead, companies are left without answers to the questions about consumer preferences and behaviors, which leaves them unprepared for market changes.

In turn, Wang coins the term thick data, which is described as “precious data from humans, like stories, emotions, and interactions that cannot be quantified” (Minute 11:50). Wang suggests that this thick data may only come from a small group of individuals, but it is an essential component that can provide insights that are different and valuable. As an example, while working for Nokia, her ethnographic experiences in China provided her with new understandings on the future demand for smartphones. However, her employer did not take her findings seriously, and as a result, they lost their foothold in the technology market. She posits that a blended approach to collecting and analyzing data (i.e. combining or integrating thick data analysis with big data analysis) allows for a better grasp on the whole picture and making informed decisions.

Her conclusions for a blended approach to data collection also have implications for blending ethnographic and case-study approaches. While Wang took more of an ethnographic approach to her research, one could envision what her work might have looked like if she had used an Ethnographic Case Study approach. Wang could have clearly defined the time and space boundaries of her various ethnographic experiences (e.g. as a street vendor, living in the slums, hanging out in internet cafés). This would have allowed her to infer causality through the generation of thick data with a small sample size for each location and bound by each group.

Ethnographic Case Studies Copyright © 2019 by Jeannette Armstrong; Laura Boyle; Lindsay Herron; Brandon Locke; and Leslie Smith is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License , except where otherwise noted.

Share This Book

• Title & authors

Suryani, Anne. "Comparing Case Study and Ethnography as Qualitative Research Approaches." Jurnal Ilmu Komunikasi , vol. 5, no. 1, pp. 117-127.

Download citation file:

This article reviews several differences between case study and ethnography in terms of definitions, characteristics, strengths and limitations. It provides current information by comparing these approaches from various social researchers’ perspectives. Although each method has strong points, they both have differences in conducting observation and interview as data collection techniques; choosing the length of time of data gathering and reporting details of a particular reality.

Table of contents

Case Study vs. Ethnography — What's the Difference?

Difference Between Case Study and Ethnography

Table of contents, key differences, comparison chart, methodology, application areas, compare with definitions, ethnography, common curiosities, how long does an ethnography study typically last, what is the primary focus of a case study, are case studies subjective, what does ethnography emphasize in its study, can a case study be based on fictional events, can a case study be applied to organizations, is a case study quantitative or qualitative, are ethnographers detached observers in their studies, what's a common method used in ethnography, what disciplines commonly use case studies, what's a key outcome of ethnography, why is immersion important in ethnography, can the findings from one case study be generalized, can a case study cover multiple subjects, is ethnography limited to traditional cultures, share your discovery.

Author Spotlight

Popular Comparisons

Trending Comparisons

New Comparisons

Trending Terms

Have a language expert improve your writing

Run a free plagiarism check in 10 minutes, generate accurate citations for free.

• Knowledge Base

Methodology

• What Is Ethnography? | Definition, Guide & Examples

What Is Ethnography? | Definition, Guide & Examples

Published on March 13, 2020 by Jack Caulfield . Revised on June 22, 2023.

Ethnography is a type of qualitative research that involves immersing yourself in a particular community or organization to observe their behavior and interactions up close. The word “ethnography” also refers to the written report of the research that the ethnographer produces afterwards.

Ethnography is a flexible research method that allows you to gain a deep understanding of a group’s shared culture, conventions, and social dynamics. However, it also involves some practical and ethical challenges.

Table of contents

What is ethnography used for, different approaches to ethnographic research, gaining access to a community, working with informants, observing the group and taking field notes, writing up an ethnography, other interesting articles.

Ethnographic research originated in the field of anthropology, and it often involved an anthropologist living with an isolated tribal community for an extended period of time in order to understand their culture.

This type of research could sometimes last for years. For example, Colin M. Turnbull lived with the Mbuti people for three years in order to write the classic ethnography The Forest People .

Today, ethnography is a common approach in various social science fields, not just anthropology. It is used not only to study distant or unfamiliar cultures, but also to study specific communities within the researcher’s own society.

For example, ethnographic research (sometimes called participant observation ) has been used to investigate  football fans , call center workers , and police officers .

Advantages of ethnography

The main advantage of ethnography is that it gives the researcher direct access to the culture and practices of a group. It is a useful approach for learning first-hand about the behavior and interactions of people within a particular context.

By becoming immersed in a social environment, you may have access to more authentic information and spontaneously observe dynamics that you could not have found out about simply by asking.

Ethnography is also an open and flexible method. Rather than aiming to verify a general theory or test a hypothesis , it aims to offer a rich narrative account of a specific culture, allowing you to explore many different aspects of the group and setting.

Disadvantages of ethnography

Ethnography is a time-consuming method. In order to embed yourself in the setting and gather enough observations to build up a representative picture, you can expect to spend at least a few weeks, but more likely several months. This long-term immersion can be challenging, and requires careful planning.

Ethnographic research can run the risk of observer bias . Writing an ethnography involves subjective interpretation, and it can be difficult to maintain the necessary distance to analyze a group that you are embedded in.

There are often also ethical considerations to take into account: for example, about how your role is disclosed to members of the group, or about observing and reporting sensitive information.

Should you use ethnography in your research?

If you’re a student who wants to use ethnographic research in your thesis or dissertation , it’s worth asking yourself whether it’s the right approach:

• Could the information you need be collected in another way (e.g. a survey , interviews)?
• How difficult will it be to gain access to the community you want to study?
• How exactly will you conduct your research, and over what timespan?
• What ethical issues might arise?

If you do decide to do ethnography, it’s generally best to choose a relatively small and easily accessible group, to ensure that the research is feasible within a limited timeframe.

Here's why students love Scribbr's proofreading services

Discover proofreading & editing

There are a few key distinctions in ethnography which help to inform the researcher’s approach: open vs. closed settings, overt vs. covert ethnography, and active vs. passive observation. Each approach has its own advantages and disadvantages.

Open vs. closed settings

The setting of your ethnography—the environment in which you will observe your chosen community in action—may be open or closed.

An open or public setting is one with no formal barriers to entry. For example, you might consider a community of people living in a certain neighborhood, or the fans of a particular baseball team.

• Gaining initial access to open groups is not too difficult…
• …but it may be harder to become immersed in a less clearly defined group.

A closed or private setting is harder to access. This may be for example a business, a school, or a cult.

• A closed group’s boundaries are clearly defined and the ethnographer can become fully immersed in the setting…
• …but gaining access is tougher; the ethnographer may have to negotiate their way in or acquire some role in the organization.

Overt vs. covert ethnography

Most ethnography is overt . In an overt approach, the ethnographer openly states their intentions and acknowledges their role as a researcher to the members of the group being studied.

• Overt ethnography is typically preferred for ethical reasons, as participants can provide informed consent…
• …but people may behave differently with the awareness that they are being studied.

Sometimes ethnography can be covert . This means that the researcher does not tell participants about their research, and comes up with some other pretense for being there.

• Covert ethnography allows access to environments where the group would not welcome a researcher…
• …but hiding the researcher’s role can be considered deceptive and thus unethical.

Active vs. passive observation

Different levels of immersion in the community may be appropriate in different contexts. The ethnographer may be a more active or passive participant depending on the demands of their research and the nature of the setting.

An active role involves trying to fully integrate, carrying out tasks and participating in activities like any other member of the community.

• Active participation may encourage the group to feel more comfortable with the ethnographer’s presence…
• …but runs the risk of disrupting the regular functioning of the community.

A passive role is one in which the ethnographer stands back from the activities of others, behaving as a more distant observer and not involving themselves in the community’s activities.

• Passive observation allows more space for careful observation and note-taking…
• …but group members may behave unnaturally due to feeling they are being observed by an outsider.

While ethnographers usually have a preference, they also have to be flexible about their level of participation. For example, access to the community might depend upon engaging in certain activities, or there might be certain practices in which outsiders cannot participate.

An important consideration for ethnographers is the question of access. The difficulty of gaining access to the setting of a particular ethnography varies greatly:

• To gain access to the fans of a particular sports team, you might start by simply attending the team’s games and speaking with the fans.
• To access the employees of a particular business, you might contact the management and ask for permission to perform a study there.
• Alternatively, you might perform a covert ethnography of a community or organization you are already personally involved in or employed by.

Flexibility is important here too: where it’s impossible to access the desired setting, the ethnographer must consider alternatives that could provide comparable information.

For example, if you had the idea of observing the staff within a particular finance company but could not get permission, you might look into other companies of the same kind as alternatives. Ethnography is a sensitive research method, and it may take multiple attempts to find a feasible approach.

All ethnographies involve the use of informants . These are people involved in the group in question who function as the researcher’s primary points of contact, facilitating access and assisting their understanding of the group.

This might be someone in a high position at an organization allowing you access to their employees, or a member of a community sponsoring your entry into that community and giving advice on how to fit in.

However,  i f you come to rely too much on a single informant, you may be influenced by their perspective on the community, which might be unrepresentative of the group as a whole.

In addition, an informant may not provide the kind of spontaneous information which is most useful to ethnographers, instead trying to show what they believe you want to see. For this reason, it’s good to have a variety of contacts within the group.

Receive feedback on language, structure, and formatting

Professional editors proofread and edit your paper by focusing on:

• Academic style
• Vague sentences
• Style consistency

See an example

The core of ethnography is observation of the group from the inside. Field notes are taken to record these observations while immersed in the setting; they form the basis of the final written ethnography. They are usually written by hand, but other solutions such as voice recordings can be useful alternatives.

Field notes record any and all important data: phenomena observed, conversations had, preliminary analysis. For example, if you’re researching how service staff interact with customers, you should write down anything you notice about these interactions—body language, phrases used repeatedly, differences and similarities between staff, customer reactions.

Don’t be afraid to also note down things you notice that fall outside the pre-formulated scope of your research; anything may prove relevant, and it’s better to have extra notes you might discard later than to end up with missing data.

Field notes should be as detailed and clear as possible. It’s important to take time to go over your notes, expand on them with further detail, and keep them organized (including information such as dates and locations).

After observations are concluded, there’s still the task of writing them up into an ethnography. This entails going through the field notes and formulating a convincing account of the behaviors and dynamics observed.

The structure of an ethnography

An ethnography can take many different forms: It may be an article, a thesis, or an entire book, for example.

Ethnographies often do not follow the standard structure of a scientific paper, though like most academic texts, they should have an introduction and conclusion. For example, this paper begins by describing the historical background of the research, then focuses on various themes in turn before concluding.

An ethnography may still use a more traditional structure, however, especially when used in combination with other research methods. For example, this paper follows the standard structure for empirical research: introduction, methods, results, discussion, and conclusion.

The content of an ethnography

The goal of a written ethnography is to provide a rich, authoritative account of the social setting in which you were embedded—to convince the reader that your observations and interpretations are representative of reality.

Ethnography tends to take a less impersonal approach than other research methods. Due to the embedded nature of the work, an ethnography often necessarily involves discussion of your personal experiences and feelings during the research.

Ethnography is not limited to making observations; it also attempts to explain the phenomena observed in a structured, narrative way. For this, you may draw on theory, but also on your direct experience and intuitions, which may well contradict the assumptions that you brought into the research.

If you want to know more about statistics , methodology , or research bias , make sure to check out some of our other articles with explanations and examples.

• Normal distribution
• Degrees of freedom
• Null hypothesis
• Discourse analysis
• Control groups
• Mixed methods research
• Non-probability sampling
• Quantitative research
• Ecological validity

Research bias

• Rosenthal effect
• Implicit bias
• Cognitive bias
• Selection bias
• Negativity bias
• Status quo bias

Cite this Scribbr article

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

Caulfield, J. (2023, June 22). What Is Ethnography? | Definition, Guide & Examples. Scribbr. Retrieved August 26, 2024, from https://www.scribbr.com/methodology/ethnography/

Is this article helpful?

Jack Caulfield

Other students also liked, what is qualitative research | methods & examples, what is a case study | definition, examples & methods, critical discourse analysis | definition, guide & examples, what is your plagiarism score.

To read this content please select one of the options below:

Please note you do not have access to teaching notes, ethnography versus case study ‐ positioning research and researchers.

Qualitative Research Journal

ISSN : 1443-9883

Article publication date: 6 April 2009

In this paper we narrate a story of working on a large project funded by an Australian Research Council Linkage grant the ‘Keeping Connected: Young People, Identity and Schooling’ project. The purpose of the study is to consider the social connection and schooling of young people who have experienced long‐term chronic illness. While the research involves both quantitative and qualitative elements, the qualitative component is the largest and involves the most researcher time and diversity. At an early stage of the project, three of the researchers working on the qualitative team consider why the study was framed as a series of case studies rather than as ethnography. The second issue considered in this paper is the different approaches to data collection, data analysis and truth claims we might take.

• Ethnography
• Funded research
• Methodology

White, J. , Drew, S. and Hay, T. (2009), "Ethnography Versus Case Study ‐ Positioning Research and Researchers", Qualitative Research Journal , Vol. 9 No. 1, pp. 18-27. https://doi.org/10.3316/QRJ0901018

Emerald Group Publishing Limited

Copyright © 2009, Emerald Group Publishing Limited

Related articles

All feedback is valuable.

Please share your general feedback

Report an issue or find answers to frequently asked questions

Contact Customer Support

What's the difference between case study ethnography?  

Insight from top 5 papers.

Case study and ethnography are two different qualitative research approaches used to answer social questions. Case study involves an in-depth analysis of a specific case or cases, often focusing on a particular phenomenon or situation [??] [??] . It typically uses multiple data collection methods, such as interviews, observations, and document analysis, to gather rich and detailed information about the case(s) being studied [??] . On the other hand, ethnography is a research method that involves immersing oneself in a particular cultural context to understand the social interactions and behaviors of the people within that context [??] [??] . Ethnography often relies on participant observation, where the researcher actively participates in the daily activities of the community being studied, and interviews to gather data [??] [??] . While both approaches have their own strengths and limitations, they differ in terms of their focus, data collection techniques, and the level of immersion in the research setting [??] .

Source Papers (5)

Related Questions

Ethnographic research involves active immersion in a specific setting to understand practices deeply, focusing on relationships, emotions, and lived experiences . It emphasizes the importance of establishing trust and adapting to emergent ethical challenges in the field . On the other hand, participant research, as highlighted in the context of volunteering, delves into the voluntariness of participants, ethical responsibilities of researchers, and self-care considerations, particularly in volunteer-related contexts . While ethnography aims for a comprehensive understanding of a culture or community through immersive engagement, participant research may involve a narrower focus on specific aspects of participation and ethical considerations within the research process, especially in volunteer settings. Both approaches prioritize ethical considerations and the quality of relationships established during the research process, albeit with different emphases and scopes.

Ethnography is crucial due to its ability to capture social forms effectively . It offers a detailed understanding of implementation processes by focusing on the social milieu of change . Despite its strengths, ethnography may not always be the recommended approach due to contextual weaknesses . This method examines routine interactions, providing rich descriptions and interpretations of social activities . Ethnography involves immersive fieldwork and detailed writing, making it both a method and an approach to understanding human behavior . Through participant observation and reflexivity, ethnographers can delve into the symbolism of cultures, organizations, and interactions, offering unique insights into various societal aspects.

Ethnography is preferred over phenomenology for observations in nursing and other fields due to its focus on cultural contexts and social dynamics, emphasizing the role of culture in shaping experiences . On the other hand, phenomenology delves into individuals' subjective experiences of reality, aiming to describe different conceptions of the world . In radiology, enactive phenomenology is utilized to analyze radiologists' diagnostic intentions and interactions with imaging technology, highlighting the importance of shared intentions and expert performance . Additionally, a novel approach combining phenomenological ethnography with artificial intelligence has been developed to understand human social interactions and culture as experience . This showcases the diverse applications of both ethnography and phenomenology in various research fields, each offering unique insights into different aspects of human experiences and behaviors.

An ethnographic approach in qualitative research distinguishes itself through its emphasis on participant observation, cultural relativism, and the integration of insider and outsider perspectives . This method, rooted in cultural anthropology, involves in-depth immersion in the studied group's environment to understand their behaviors and beliefs. Unlike other qualitative methods, ethnography prioritizes contextualized descriptions and analyses of specific groups at particular times and places, along with the process of data collection for such reports . Additionally, ethnography often involves techniques like ethnographic interviews and digital ethnography to explore communicative competence in language learners . Furthermore, cross-cultural ethnographic research allows for the comparison of data from multiple sites to identify cultural patterns and test global phenomena theories .

An ethnographic research design can be used to study a particular phenomenon by immersing the researcher in the natural setting of the study population and understanding how the event is perceived and interpreted by the people in the community . This qualitative research method allows for in-depth knowledge about the socio-technological realities surrounding the phenomenon, uncovering not only what practitioners do but also why they do it . Ethnography involves active participation in the routines of the subjects and recording observations to gain an insider view of the world . It can be applied to various contexts, such as cross-cultural research, human-computer interaction, and translation and interpreting research . Ethnographic research involves selecting appropriate methodology, conducting study in a naturalistic setting, and presenting findings with cultural meaning . It provides a unique strength in understanding complex activities and contexts, making it an ideal method for in-depth understanding of the phenomenon .

Trending Questions

Pigafetta's observations of the indigenous peoples of the Philippines reveal a rich tapestry of cultural practices and traditions that reflect their deep-rooted beliefs and social structures. His accounts highlight various aspects of their daily lives, rituals, and healing practices, which continue to evolve yet retain their significance. ## Cultural Rituals and Practices - **Rituals and Ceremonies**: Indigenous groups, such as the Ati, perform healing rituals led by traditional healers (Sorhana), which include practices like Pagbagting (beating of the agong) and Pagtabog (expelling evil spirits). - **Syncretism**: Many indigenous rituals have integrated elements from other religions, showcasing a blend of traditional and contemporary practices, particularly in the Ibaloi community. ## Beliefs and Healing - **Magico-Spiritual Influences**: Indigenous beliefs often attribute mental health issues to spiritual factors, leading to culturally specific healing practices. - **Cultural Preservation**: Despite modernization, communities like the Aetas strive to maintain their traditional practices related to significant life events such as childbirth and marriage. In summary, Pigafetta's observations underscore the resilience of indigenous cultural practices amidst external influences, highlighting their importance in identity and community cohesion. However, the ongoing challenges of modernization and syncretism may threaten the preservation of these traditions.

The effect of occupational regulation on the craft beer market is significant, influencing both market entry and competition. Regulations often create barriers that hinder innovation and limit consumer choice, particularly for smaller breweries. ## Barriers to Entry - Craft breweries face substantial regulatory hurdles at federal, state, and local levels, which can stifle competition and innovation. - In North Carolina, restrictive laws on production and distribution have inhibited growth, demonstrating how legislative frameworks can limit entrepreneurial opportunities. ## Market Dynamics - A 2019 law in Colorado allowing full-strength beer sales in grocery stores favored larger breweries, highlighting how regulatory changes can disproportionately benefit established firms over smaller competitors. - The outdated three-tier system, designed to prevent large brewery abuses, continues to disadvantage small craft breweries by consolidating distributor power. ## Recommendations for Improvement - Modernizing regulations, such as providing exemptions for craft breweries from certain distributor protections, could enhance competition and consumer choice. While regulations aim to protect consumers and ensure fair practices, they often inadvertently favor established players, suggesting a need for reform to support the burgeoning craft beer sector.

Children's literature plays a significant role in enhancing literacy rates and academic achievement among elementary school students. It serves as a foundational tool for developing essential literacy skills, fostering a love for reading, and promoting critical thinking and creativity. The impact of children's literature is multifaceted, influencing not only academic success but also personal and cultural development. Below, we explore the various dimensions of this impact. ## Literacy Skill Development - Early exposure to children's literature is crucial for developing emergent literacy skills such as vocabulary, phonological awareness, and narrative understanding. These skills are foundational for reading and writing proficiency, which are critical for academic success . - Children's literature encourages reading habits and literacy development, which are essential for the formation of proficient readers. Teachers play a vital role in integrating literature into the curriculum to enhance these skills . ## Academic Achievement - The use of children's literature in educational settings has been shown to improve academic outcomes by fostering a deeper engagement with reading materials. This engagement is linked to better performance in school subjects that require strong reading and comprehension skills . - Literature also supports the development of critical thinking and creativity, which are important competencies for academic success. These skills are nurtured through exposure to diverse themes and narratives found in children's literature . ## Cultural and Character Development - Children's literature, including folklore, helps preserve cultural heritage and instills values and identity in young readers. It serves as a medium for character education, promoting good values and cultural awareness . - The creative and imaginative aspects of children's literature allow children to explore different perspectives and develop a sense of self and the world around them, contributing to their intellectual and personal growth . While children's literature has a profound impact on literacy and academic achievement, challenges remain in its effective implementation. Teachers often lack the training to utilize literature effectively in the classroom, and there is a need for pedagogical strategies that maximize its benefits. Additionally, some children's literature may inadvertently convey negative attitudes or be more suitable for adults, highlighting the importance of careful selection and guidance by educators and parents .

Language barriers can significantly hinder children's understanding of physics concepts, particularly when the language of instruction differs from their home language. This challenge is compounded by the abstract nature of physics, which requires a strong grasp of specific terminologies and the ability to engage in complex discussions. The following sections explore how language barriers impact physics learning and suggest strategies to mitigate these challenges. ## Impact of Language Barriers on Physics Learning - **Complexity of Physics Language**: Physics is often described as a language in itself, with its own set of terminologies and symbols. For children who are not proficient in the language of instruction, this complexity can be overwhelming, leading to poor comprehension and performance in physics. - **Correlation with Language Proficiency**: Studies have shown a positive correlation between proficiency in the language of instruction and performance in physics. Learners who struggle with the language often find it difficult to understand physics concepts and perform poorly in assessments. - **Cognitive Load**: The additional cognitive load of translating concepts from one language to another can detract from the learning process, making it harder for children to grasp and retain physics concepts. ## Strategies to Overcome Language Barriers - **Simplification and Early Introduction**: Introducing physics concepts in simpler terms and at an early age can help children become more familiar with the subject. This approach emphasizes understanding over memorization of complex formulas. - **Use of Code-Switching**: Teachers can employ code-switching, using both the home language and the language of instruction, to help students better understand physics concepts. This strategy has been shown to improve comprehension and engagement in the classroom. - **Supportive Learning Materials**: Providing additional learning materials that cater to different language proficiencies can facilitate better understanding and retention of physics concepts. While language barriers pose significant challenges, they are not insurmountable. By employing strategies such as simplifying content, using code-switching, and providing supportive materials, educators can help bridge the gap and enhance children's understanding of physics. However, it is crucial to recognize that these strategies require careful implementation and support from educational policies to be effective.

Teamwork skills significantly influence academic performance and overall student success by enhancing interpersonal abilities, self-esteem, and integration into the academic environment. Research indicates that effective teamwork fosters essential competencies that are crucial for both academic and professional achievements. ## Impact on Academic Performance - Students with developed teamwork skills tend to perform better academically, as evidenced by significant correlations between teamwork efficiency and academic grades. - Action research interventions have shown that structured teamwork projects improve planning, time management, and team cohesion, leading to enhanced perceived performance. ## Enhancement of Self-Esteem - Teamwork skills are linked to improved self-esteem, which is vital for academic success. Skills such as decision-making and leadership contribute positively to students' self-worth. - The integration of teamwork training in curricula can foster self-esteem, thereby enhancing students' overall academic experience. ## Social Integration and Future Readiness - Developing teamwork skills helps students integrate into peer groups and prepares them for the labor market, where such skills are increasingly demanded. - Universities are encouraged to embed teamwork training in their syllabuses to ensure students are equipped with these essential skills for future challenges. While the benefits of teamwork skills are clear, some studies highlight that many students still struggle with these competencies, indicating a need for targeted training programs to bridge this gap.

This paper is in the following e-collection/theme issue:

Published on 26.8.2024 in Vol 26 (2024)

Evaluation of a Natural Language Processing Approach to Identify Diagnostic Errors and Analysis of Safety Learning System Case Review Data: Retrospective Cohort Study

Authors of this article:

Original Paper

• Azade Tabaie 1, 2 , PhD   ; 
• Alberta Tran 3 , RN, CCRN, PhD   ; 
• Tony Calabria 3 , MA, CPHQ, CSSBB   ; 
• Sonita S Bennett 1 , MSc   ; 
• Arianna Milicia 4 , BSc   ; 
• William Weintraub 5, 6 , MACC, MD   ; 
• William James Gallagher 6, 7 , MD   ; 
• John Yosaitis 6, 8 , MD   ; 
• Laura C Schubel 4 , MPH   ; 
• Mary A Hill 9, 10 , MS   ; 
• Kelly Michelle Smith 9, 10 , PhD   ; 
• Kristen Miller 4, 6 , MSPH, MSL, CPPS, DrPH  

1 Center for Biostatistics, Informatics, and Data Science, MedStar Health Research Institute, Washington, DC, United States

2 Department of Emergency Medicine, Georgetown University School of Medicine, Washington, DC, United States

3 Department of Quality and Safety, MedStar Health Research Institute, Washington, DC, United States

4 National Center for Human Factors in Healthcare, MedStar Health Research Institute, Washington, DC, United States

5 Population Health, MedStar Health Research Institute, Washington, DC, United States

6 Georgetown University School of Medicine, Washington, DC, United States

7 Family Medicine Residency Program, MedStar Health Georgetown-Washington Hospital Center, Washington, DC, United States

8 MedStar Simulation Training & Education Lab (SiTEL), MedStar Institute for Innovation, Washington, DC, United States

9 Institute of Health Policy, Management & Evaluation, University of Toronto, Toronto, ON, Canada

10 Michael Garron Hospital, Toronto, ON, Canada

Corresponding Author:

Azade Tabaie, PhD

Center for Biostatistics, Informatics, and Data Science

MedStar Health Research Institute

3007 Tilden Street NW

Washington, DC, 20008

United States

Phone: 1 202 244 9810

Email: [email protected]

Background: Diagnostic errors are an underappreciated cause of preventable mortality in hospitals and pose a risk for severe patient harm and increase hospital length of stay.

Objective: This study aims to explore the potential of machine learning and natural language processing techniques in improving diagnostic safety surveillance. We conducted a rigorous evaluation of the feasibility and potential to use electronic health records clinical notes and existing case review data.

Methods: Safety Learning System case review data from 1 large health system composed of 10 hospitals in the mid-Atlantic region of the United States from February 2016 to September 2021 were analyzed. The case review outcome included opportunities for improvement including diagnostic opportunities for improvement. To supplement case review data, electronic health record clinical notes were extracted and analyzed. A simple logistic regression model along with 3 forms of logistic regression models (ie, Least Absolute Shrinkage and Selection Operator, Ridge, and Elastic Net) with regularization functions was trained on this data to compare classification performances in classifying patients who experienced diagnostic errors during hospitalization. Further, statistical tests were conducted to find significant differences between female and male patients who experienced diagnostic errors.

Results: In total, 126 (7.4%) patients (of 1704) had been identified by case reviewers as having experienced at least 1 diagnostic error. Patients who had experienced diagnostic error were grouped by sex: 59 (7.1%) of the 830 women and 67 (7.7%) of the 874 men. Among the patients who experienced a diagnostic error, female patients were older (median 72, IQR 66-80 vs median 67, IQR 57-76; P =.02), had higher rates of being admitted through general or internal medicine (69.5% vs 47.8%; P =.01), lower rates of cardiovascular-related admitted diagnosis (11.9% vs 28.4%; P =.02), and lower rates of being admitted through neurology department (2.3% vs 13.4%; P =.04). The Ridge model achieved the highest area under the receiver operating characteristic curve (0.885), specificity (0.797), positive predictive value (PPV; 0.24), and F 1 -score (0.369) in classifying patients who were at higher risk of diagnostic errors among hospitalized patients.

Conclusions: Our findings demonstrate that natural language processing can be a potential solution to more effectively identifying and selecting potential diagnostic error cases for review and therefore reducing the case review burden.

Introduction

Diagnostic errors are an underappreciated cause of preventable mortality in hospitals, estimated to affect a quarter million hospital inpatients, and account for an estimated 40,000-80,000 deaths annually in the United States [ 1 ]. These errors pose a risk for severe patient harm [ 2 , 3 ], increase hospital length of stay [ 4 ], and made up 22% and accounted for US $5.7 billion of paid malpractice claims in hospitalized patients throughout a nearly 13-year period [ 5 ]. In their analysis of malpractice claims occurring in the US National Practitioner Database from 1999 to 2011, Gupta et al [ 5 ] found that diagnosis-related paid claims were most likely to be associated with death and cost (following surgery); among diagnosis-related paid claims, failure to diagnose was the most common subtype and was more likely than other types to be associated with mortality. Several factors have been proposed as contributors to inpatient diagnostic errors including time constraints related to the concurrent care of multiple patients, unpredictable workflows, distractions, and competing priorities for trainees. From their systematic review and meta-analysis, Gunderson et al [ 2 ] estimate that 250,000 diagnostic adverse events occur annually among hospitalized patients in the United States, and this is likely an underestimation of the problem due to several challenges in diagnostic error measurement [ 6 ].

Challenges in identifying and measuring diagnostic errors occur due to the evolving and iterative nature of the diagnostic process, making it difficult to determine when, if at all, a correct or more specific diagnosis could have been established by clinicians to start the appropriate treatment [ 6 ]. Since its landmark report, Improving Diagnosis in Health Care , the National Academies of Science, Engineering, and Medicine (NASEM) has produced a common understanding of diagnostic error that includes accuracy, timeliness, and communication of the explanation to the patient or patient’s family member [ 3 ]. Diagnostic errors often involve missed opportunities related to various aspects of the diagnostic process [ 7 - 9 ] and diagnostic adverse events resulting in harm [ 10 ]. However, many hospitals currently do not capture or include surveillance for diagnostic errors, despite having robust systems in place to report and analyze patient safety issues [ 6 , 11 , 12 ].

A crucial first step to improving diagnosis in hospitals is the creation of programs to identify, analyze, and learn from diagnostic errors. Ongoing efforts by the Agency for Health Care Research and Quality have supported pragmatic measurement approaches for health organizations to build a diagnostic safety program and identify and learn from diagnostic errors such as those described in the Measure Dx resource [ 9 ]. One proposed and promising solution for hospitals to improve diagnostic surveillance is to build on existing efforts to collect patient safety data, root cause analyses, or other forms of case reviews for quality improvement purposes. Cases that have already been reviewed or investigated in the organization for general patient safety and quality purposes may be able to inform or be rereviewed for information and learning opportunities specific to diagnostic safety. Widely used case-based learning methodologies in particular, such as the “Learning From Every Death” initiative developed at Mayo Clinic [ 13 ] used both nationally and worldwide, offer an excellent opportunity for hospitals to augment their existing quality and safety efforts and support diagnostic safety.

Clinical notes in electronic health records (EHRs) written by health providers in free-text format are rich sources of a patient’s diagnoses and care trajectory through hospitalization time. Approaches to processing free text, such as through natural language processing (NLP) and machine learning (ML), have demonstrated significant opportunities to improve quality and safety within health care organizations in diverse applications [ 14 - 16 ] such as cancer research [ 17 , 18 ] and infection prediction [ 19 ] to sleep issues [ 20 ] and neurological outcome prediction [ 21 ]. Besides its use in the diagnostic process, ML models proved to have added benefits when used in diagnostic error identification [ 22 , 23 ]. However, despite significant progress and evidence about the use of these ML and NLP approaches to improve patient safety, the use of ML and NLP approaches to diagnostic safety and surveillance has largely remained untapped. A 2022 study demonstrates how an academic medical center’s implementation of an NLP-based algorithm to flag safety event reports for manual review enabled early detection of emerging diagnostic risks from large volumes of safety reports, and was among the first to apply an NLP approach to safety event reports to facilitate identification of COVID-19 related diagnostic errors [ 24 ]. Meanwhile, progress in the use of data mining approaches to develop electronic trigger tools offers promising methods to detect potential diagnostic events, promote organizational learning, and support the monitoring of data prospectively to identify patients at high risk for future adverse events [ 25 ]. To our knowledge, however, NLP has not yet been applied to case review data to facilitate the identification of diagnostic errors and understand its features and sources.

While free-text formatted clinical notes provide unique opportunities to incorporate ML models, the lack of reliable labels to represent diagnostic errors often limits the use of clinical notes for diagnostic safety surveillance efforts. The opportunity to train ML and NLP algorithms to identify diagnostic errors and opportunities depends on the collation of EHR data with existing efforts to identify diagnostic errors such as through case review findings from the Safety Learning System (SLS). To further explore the potential for this approach to be used to improve diagnostic safety surveillance, a rigorous evaluation of the feasibility and potential of using EHR and existing case review data is needed.

We hypothesized that ML and NLP methods can be applied to train models based on available case review data to examine content potentially related to diagnostic errors within EHR clinical notes. These approaches automatically identify features or information from free text using controlled vocabularies, rule sets, reference dictionaries, or lexicons.

Data Sets and Case Review Approach

We analyzed SLS data from 1 large health system comprised of 10 hospitals in the mid-Atlantic region of the United States. The SLS is one example of a holistic case review methodology delivered by health care organizations in the United States and globally. Established in 2015, the SLS builds upon the Mayo Clinic Mortality Review System of Huddleston et al [ 13 ] to review and analyze EHR data from patient mortality cases to find safety issues that could be found and mitigated. This approach was designed to enhance current quality improvement projects done within health organizations, providing a perspective and strategy based on the Safety II lens and rooted in the belief that every death provides an opportunity to improve care. With a Safety II lens, participating organizations use a holistic case review methodology designed to identify vulnerabilities in systems and processes of care delivery. Reviewers identify and translate these into different categories and labels to (1) define and quantify types of process of care and system failures contributing to adverse outcomes (errors) and (2) identify the components of the process of care and system failures that when fixed will improve performance (opportunities for improvement [OFIs]).

To ensure a sufficient cross-sampling of patients across different specialties and areas, patients are selected for case reviews at this health system based on their primary provider service line category (eg, medicine, surgery, etc) and hospital length of stay; patients in primary and ambulatory care settings are not included for case review selection. The case review process occurs according to the standardized SLS methodology and recommendations [ 13 , 26 ], and between at least 1 physician and 1 nurse within the health system who have both received training in the SLS approach. The case review outcome and identification of OFIs, including diagnostic OFIs, relies on the reviewer’s consensus of any findings and through multiple multidisciplinary and multispecialty meetings that may involve a committee Chair member, clinical department leader, or escalation to other leadership.

We obtained SLS data from February 2016 to September 2021; data in later years were available but not included because of key changes to the case selection process made during and in response to the COVID-19 pandemic. All hospitalized adult patients older than 18 years were included for analysis, regardless of their hospitalization outcome (eg, mortality or discharge location). Pediatric and neonatal patients were excluded.

Ethical Considerations

The original data collection and study protocol was approved by the institutional review board (00001245) at MedStar Health Research Institute on August 26, 2019.

Data Extraction

Medical record number, encounter number, length of stay, age, date of birth, sex, diagnosis at the time of admission (ie, ICD-10 [ International Statistical Classification of Diseases, Tenth Revision ] diagnosis codes), mortality, OFI categories (eg, delayed or missed diagnosis and diagnostic opportunities), number of identified OFIs and diagnosis issues (eg, the accuracy of diagnosis and confirmation or fixation bias) were the features and patient identifiers which were extracted from SLS data [ 13 , 26 ].

Because chart reviews generally occur at a single point in time within the patient’s care trajectory, they often do not contain information or details of the patient’s full hospital course. However, clinical notes written by health care providers are rich sources of patient’s health status throughout their hospitalization period [ 27 - 29 ]. Therefore, to supplement these chart review data, we additionally extracted and included all clinical notes from the EHR for patients who could be matched by patient identifiers (eg, encounter number and date of birth).

Coding Diagnostic Errors

Case reviewers can select any number of labels to describe a diagnosis issue or an OFI identified and agreed upon by consensus. For this study, diagnostic errors were defined by the available features from chart review pertaining to diagnosis and impacting the timeliness, accuracy, or communication of a diagnosis. Our definition of diagnostic errors was limited to the categories identified during chart reviews and recorded within the SLS data set; therefore, our diagnostic error definition does not include all aspects of the definition developed by the NASEM report [ 3 ]. Table 1 describes the SLS categories and values that were labeled as diagnostic errors and used to train our classification models. Patients were coded as having experienced a diagnostic error if one or more of the conditions listed in Table 1 were identified in their SLS case review.

a OFI: opportunity for improvement.

NLP Approach

We used an NLP approach on critical incident reporting system data to explore the features and risk of diagnostic error among hospitalized patients.

Features From Free-Text Data

Descriptive statistical analyses were performed to identify any differences among age, length of stay, and mortality between the female and male patients who had experienced diagnostic errors.

All EHR clinical notes were transformed to lowercase. Extra white spaces, numbers, punctuations, and stop words were removed and words were stemmed. The term frequency-inverse document frequency (TF-IDF) matrix was calculated for each clinical note using the bag-of-words from the preprocessed EHR clinical notes [ 30 ]. TF-IDF is a statistical measure that evaluates how relevant a word is to a document in a collection of documents and is a popular method to translate free text to numerical features in training ML models. The TF-IDF of a word in a document is calculated by multiplying 2 metrics: the number of times a word appeared in a document and the inverse document frequency of the word across a set of documents. TF-IDF is computationally efficient and easy to interpret. We excluded the most frequent words that had appeared in more than 95% of the EHR clinical notes, as these frequent words do not provide information to help with the classification. Moreover, we excluded the rare words that appeared in less than 5% of the EHR clinical notes [ 31 ].

In a TF-IDF matrix, the number of rows corresponds to the unique patients, and the number of columns represents the unique words found in EHR clinical notes. There are numerous unique words used in EHR clinical notes; therefore, the TF-IDF approach provides a high-dimensional input matrix for the classification task. The high-dimensional input matrix can lead to training inaccurate classifiers. To overcome that issue, we used the chi-square statistical test to select the most relevant words to identify diagnostic errors; therefore, if P values associated with a word (also called a feature) are less than .05, that word is selected and included in the feature matrix to train ML classification models.

Classification Models

In lieu of an existing model with the same objective in the literature, a simple logistic regression model was trained as the baseline classifier to identify patients within SLS data who were at higher risk of diagnostic error. Moreover, 3 forms of logistic regression models with regularization functions were trained on this data to compare classification performances and identify the best-performing model [ 32 ]: Least Absolute Shrinkage and Selection Operator (LASSO), Ridge, and Elastic Net.

• LASSO: for a more accurate prediction, LASSO regularization is used with a logistic regression model. The LASSO procedure encourages simple, sparse models which has fewer parameters in a way that the estimated coefficient of features with less effect will be set to zero. This characteristic makes LASSO well-suited for models showing high levels of multicollinearity or variable selection and parameter elimination is needed. LASSO is also called L1 regularization.
• Ridge: also called L2 regularization, Ridge is a regularization method used for models suffering from multicollinearity or high-dimensional feature space. Ridge regularization keeps all the features regardless of their effect on the model. However, it pushes the estimated coefficient of features with less effect toward zero to minimize their effect on the classification outcome. This characteristic of Ridge makes it well-suited when most features impact the outcome variable.
• Elastic Net: a logistic regression model with Elastic Net regularization is a weighted combination of LASSO (L1) and Ridge (L2) regularizations [ 33 ]. Elastic Net can remove the effect of the insignificant features by setting their estimated coefficient to zero and lower the effect of the less significant features by pushing their estimated coefficient toward zero while adding more weights to the more important features. From implementation and interpretation aspects, the Elastic Net model is simple to use. Such characteristics make this model an accepted baseline in ML-based studies [ 34 ].

The hyperparameters of the 3 classification models were optimized through cross-validation. All the analyses were conducted using Python 3 (Python Software Foundation).

Classification Performance Metrics

We calculated 7 common performance metrics reported for binary classifiers to compare the performance of the 4 classification models: area under receiver operating characteristics curve (AUROC), sensitivity or recall or true positive rate, specificity or true negative rate, positive predictive value (PPV) or precision, negative predictive value (NPV), F 1 -score, and area under precision-recall curve (AUPRC). The 7 metrics take values between 0 and 1. Values closer to 1 indicate a well-performing classifier. Multimedia Appendix 1 presents the definition of the performance metrics used in this study. Figure 1 presents the summary of the methods used in this analysis.

Descriptive Summary

In total, there were 2184 unique patient records within SLS data from February 2016 to September 2021. EHR clinical notes were cross-matched, extracted, and included in analyses for 1704 (78%) of these SLS patient records. Of those patients with cross-matched EHR data, 126 (7.4%) patients had been identified by case reviewers as having experienced at least 1 diagnostic error. A total number of 20,848 EHR clinical notes associated with the 1704 unique patients were used in this study.

Patients who had experienced diagnostic errors were grouped by sex: 59 (7.1%) of the 830 women and 67 (7.7%) of the 874 men in the larger cross-matched sample had been found to have a diagnostic error. Table 2 presents the descriptive statistics between female and male patient groups. We applied the Wilcoxon rank sum test for numerical features (ie, age and length of stay), and the chi-square test for mortality rate, admission diagnosis, and admission department or specialty. Patients in the female group were older than the male group by a median of 72 (IQR 66-80) versus a median of 67 (IQR 57-76; P =.02). Compared to the male group, female patients who experienced diagnostic error had higher rates of being admitted through general or internal medicine (69.5% vs 47.8%; P =.01), lower rates of cardiovascular-related admitted diagnosis (11.9% vs 28.4%; P =.02), and lower rates of being admitted through neurology department (2.3% vs 13.4%; P =.04). We observed no differences between groups in mortality rates and length of stay.

Classification Models’ Performance

Clinical notes were preprocessed for TF-IDF feature calculation. The bag-of-words included 2227 words, and each word was considered a feature (see Table S1 in Multimedia Appendix 2 for the top 100 words). We found that abscess, ascend, abnormality, scant, pair, and prefer were the top 5 features with the highest positive estimated coefficient (0.42 to 0.28); post, select, gave, muscl, hours, and unrespons were the top 5 features with the highest negative coefficients (–0.35 to –0.26). After applying the chi-square test, 250 features with a P value less than .05 were selected for the modeling process. All 4 ML classifiers were trained using the 250 selected features.

Table 3 presents the performances of the simple logistic regression and 3 regularized logistic regression models (LASSO, Ridge, and Elastic Net). The Ridge model achieved the highest AUROC (0.885), specificity (0.797), PPV (0.24), NPV (0.981), and F 1 -score (0.369) in classifying patients who were at higher risk of diagnostic errors among hospitalized patients in SLS system. The simple logistic regression model obtained the highest AUPRC (0.537). The simple logistic regression model classified all patients as the ones with diagnostic errors; therefore, it achieved a sensitivity of 1, and specificity and NPV of 0.

Figures 2 and 3 present the receiver operating characteristics curves and precision-recall curves for the 4 classifiers in this study. Models that give ROC curves closer to the top-left corner indicate a better performance. The AUROC values represent the probability that a patient who experienced a diagnostic error, chosen at random, is ranked higher by the Ridge model than a randomly chosen patient who did not experience a diagnostic error. The higher value of AUPRC indicates that the Ridge model can identify patients who experienced diagnostic errors more precisely with fewer false positives compared to LASSO and Elastic Net models.

a LASSO: Least Absolute Shrinkage and Selection Operator.

b AUROC: area under receiver operating characteristics curve.

c AUPRC: area under precision-recall curve.

Principal Findings

Our contribution is 2-fold; first, we integrated 2 data sources that are currently used by and available to many organizations across the United States, SLS and EHR data, to explore the use of ML and NLP algorithms to help identify diagnostic errors among hospitalized patients. Although case review methodologies offer rich insights into systems errors and OFIs, the predefined pull-down menus and structured data labels typically do not capture all the necessary clinical and contextual details that are considered by reviewers. Therefore, a large portion of these case review data are stored in free-text narratives that typically record key information and judgments decided upon by the multidisciplinary reviewers. However, given persistent issues of staff shortage and lack of time in health care settings, it is becoming increasingly important to lower the burden of systematic EHR data reviews for health care providers while maintaining the review systems in place. Second, any developed ML and NLP approaches can potentially be incorporated to generate a diagnostic error risk score for each patient. The predicted risk score can be used in identifying and prioritizing patients for focused chart reviews, thus lowering the burden of systematic EHR data reviews for health care providers while maintaining the review systems in place.

To our knowledge, this study is the first attempt to apply and test several different ML classification models to identify diagnostic errors within routinely collected organizational case review data. Despite a substantial body of literature about the prevalence of diagnostic errors in hospital settings, current efforts to identify diagnostic errors generally rely on reviews of patient cases and data by clinical or quality teams that often are resource-intensive. ML classification models and NLP techniques offer an opportunity to generate diagnostic error risk scores to sort through large data sets and identify signals of potential diagnostic errors that can be flagged for further review. However, these classification models require a high number of observations (and identified diagnostic errors) to perform well, which might not be feasible for health organizations that are just beginning to identify diagnostic errors or may have limited personnel and efforts to perform high numbers of case reviews. In this study, we accessed nearly 2000 patient records (and of those, only 126 cases of diagnostic errors), which is considered to be a limited data sample size in the field of ML. However, techniques, such as feature selection and n-fold cross-validations, can potentially be approaches to address small sample size challenges [ 35 ].

Using the results of the simple logistic regression model as the baseline performance, we found that 3 regularization functions, namely LASSO, Ridge, and Elastic Net, boosted the performance of the baseline model. The Ridge model outperformed the rest of the models in terms of multiple performance metrics: AUROC of 0.885, specificity of 0.797, PPV of 0.24, NPV of 0.981, and F 1 -score of 0.369. The Ridge algorithm tries to keep all features in the model even the features with a slight effect on the classification outcome. Since the patterns pointing at a diagnostic error were subtle in the clinical notes, even a small effect of a feature on the model’s classification outcome could be important for the classification model to learn. On the other hand, the LASSO algorithm rigorously removes features that have a small effect on the classification outcome. The Elastic Net model is a weighted combination of LASSO and Ridge. The performance results presented in Table 3 show that the values achieved by the Elastic Net model lie between those of the LASSO and Ridge models.

Insights From Diagnostic Errors Within Free-Text Clinical Notes

We did not find the free text formatted clinical notes in the EHR to reflect any sort of direct language around diagnostic errors. Our analysis identified no use of the terms misdiagnosis, missed diagnosis, or diagnostic error within clinical notes, finding instead more subtle signals pointing at diagnostic errors such as “there may be a chance of misreading the test,” or “insufficient data to make a diagnosis.” Our findings demonstrate that NLP algorithms can be used to identify such patterns and find the associations between diagnostic errors and the subtle signals in the clinical notes. A natural extension of this work can focus on using other feature extraction methods, such as Bidirectional Encoder Representations from Transformers contextualized word embeddings, and explore the use of the pretrained language models for this objective.

We found that the presence of terms, such as abscess, abnormality, “cp” (chest pain) , and dialysis in a patient’s EHR clinical note were associated with reviewer-identified diagnostic errors ( Multimedia Appendix 2 ). Misinterpretation of chest pain, specifically among female patients, has the potential to cause a cardiovascular-related diagnosis error [ 36 ]. Patients with chronic kidney disease are at higher risk of cardiovascular complications [ 37 ]. Missing such risk for a patient who is on dialysis, adds to the risk of diagnostic error.

Clinical and System Implications Around Diagnostic Inequity

Diagnostic inequity is defined as “the presence of preventable unwarranted variations in diagnostic process among population groups that are socially, economically, demographically, or geographically disadvantaged” [ 38 ]. Despite persistent and well-documented disparities in health care access and outcomes across different population groups, few studies have examined the association between diagnostic errors and health care disparities [ 39 ]. Recent evidence supports the notion that variation in diagnostic error rates across demographic groups may exist, particularly across sex. A systematic review of diagnostic errors in the emergency department, for example, found that female sex and non-White race were often associated with increased risk for diagnostic errors across several clinical conditions in emergency settings [ 40 ]. In cardiovascular medicine, a national cohort study of acute myocardial infarctions found that women were nearly twice as likely as men to receive the wrong initial diagnosis following signs of a heart attack [ 41 ]. Despite efforts to understand and reduce disparities in diagnosis and treatment, women not only continue to be understudied, underdiagnosed, and undertreated in cardiovascular medicine [ 42 ] but also may experience longer lengths of time to diagnosis than men in most patterns of disease diagnosis [ 43 ].

The analysis of case review data and other system-based data (eg, patient safety events or incident reporting) by subsets offer an opportunity to identify events in vulnerable patient populations and help sensitize clinicians to potential biases within the diagnostic process. To explore sex differences in diagnostic errors within our case review data, we statistically compared demographic and clinical differences between female and male patients who had been identified in case reviews as having experienced diagnostic error or errors. We found that of those patients who had experienced diagnostic error or errors, the female group of patients were older, had higher rates of being admitted through general or internal medicine or hospitalist (vs specialty) departments, and had lower rates of having a cardiovascular diagnosis on admission. These preliminary results of this study revealed unexpected differences between male and female diagnostic error groups, offering novel insights that warrant further investigation to fully understand the mechanisms underlying these relationships and their implications for clinical decision-making and practice. Future uses of NLP can potentially support clinical and system-based approaches to capture and increase the evidence around structural biases or disparities in diagnoses. Individual cases from these types of data sources could be used as example narratives to engage clinicians and improve clinician learning, contributing to the development of tailored clinician and systemic interventions that can improve quality and equity throughout the diagnostic process.

Limitations

This study has several limitations. Our definition of diagnostic errors was limited to the categories and labels used within the SLS data set, reviewer interpretations of cases (subject to reviewer bias), and does not include all aspects of the definition developed by the NASEM report [ 3 ]. Despite several continued differences in definitions of diagnostic error in the peer-reviewed literature [ 8 ], we recommend that quality and safety teams within health systems use the NASEM definition for diagnostic error—including errors in communicating the diagnosis to the patient—to develop any definitions, categories, or labels used in their case review and surveillance initiatives. Although a time-consuming task, future studies could consider EHR data chart reviews to have the ground truth for the diagnostic error cases and add to the accuracy of the data set used for training the ML classifiers. Additionally, due to staffing challenges and shifting organizational priorities, case review selection varies by hospital and has changed over time, resulting in a relatively small sample size and also introducing the potential for bias. Our data came from a single health system and may reflect the specific language, culture, and practices occurring within the system and therefore may not be similar to that of other health systems. To enhance the external validity and generalizability of results, future efforts and research studies should consider the random selection of cases to evaluate both diagnostic and general quality issues within the organization; studies with larger sample sizes can build on our preliminary findings and test differences between clinical subgroups. Finally, our classification models were developed and evaluated based on a retrospective cohort from EHR; therefore, the performance may deteriorate when the method is applied to real-time data. Further work or future studies should be conducted to prospectively validate the models.

Conclusions

We performed an NLP approach and compared 4 techniques to classify patients who were at a higher risk of experiencing diagnostic error during hospitalization. Our findings demonstrate that NLP can be a potential solution to more effectively identifying and selecting potential diagnostic error cases for review, and therefore, reducing the case review burden.

Acknowledgments

This work was supported by the Agency for Health Care Research and Quality (grant 5R18HS027280-02).

Conflicts of Interest

None declared.

Binary classification performance metrics.

The Estimated Coefficient from the Ridge Model.

• Newman-Toker DE, Wang Z, Zhu Y, Nassery N, Saber Tehrani AS, Schaffer AC, et al. Rate of diagnostic errors and serious misdiagnosis-related harms for major vascular events, infections, and cancers: toward a national incidence estimate using the "Big Three". Diagnosis (Berl). Feb 23, 2021;8(1):67-84. [ FREE Full text ] [ CrossRef ] [ Medline ]
• Gunderson CG, Bilan VP, Holleck JL, Nickerson P, Cherry BM, Chui P, et al. Prevalence of harmful diagnostic errors in hospitalised adults: a systematic review and meta-analysis. BMJ Qual Saf. Dec 2020;29(12):1008-1018. [ CrossRef ] [ Medline ]
• Ball JR, Miller BT, Balogh EP. Improving Diagnosis in Health Care. Washington, DC. National Academies Press; 2015:472.
• Hautz WE, Kämmer JE, Hautz SC, Sauter TC, Zwaan L, Exadaktylos AK, et al. Diagnostic error increases mortality and length of hospital stay in patients presenting through the emergency room. Scand J Trauma Resusc Emerg Med. May 08, 2019;27(1):54. [ FREE Full text ] [ CrossRef ] [ Medline ]
• Gupta A, Snyder A, Kachalia A, Flanders S, Saint S, Chopra V. Malpractice claims related to diagnostic errors in the hospital. BMJ Qual Saf. Aug 09, 2017;27(1):53-60. [ CrossRef ] [ Medline ]
• Zwaan L, Singh H. Diagnostic error in hospitals: finding forests not just the big trees. BMJ Qual Saf. 2020;29(12):961-964. [ CrossRef ] [ Medline ]
• Singh H. Editorial: helping health care organizations to define diagnostic errors as missed opportunities in diagnosis. Jt Comm J Qual Patient Saf. 2014;40(3):99-101. [ CrossRef ] [ Medline ]
• Giardina TD, Hunte H, Hill MA, Heimlich SL, Singh H, Smith KM. Defining diagnostic error: a scoping review to assess the impact of the national academies' report improving diagnosis in health care. J Patient Saf. 2022;18(8):770-778. [ FREE Full text ] [ CrossRef ] [ Medline ]
• Measure Dx: a resource to identify, analyze, and learn from diagnostic safety events. AHRQ: Agency for Healthcare Research and Quality. URL: https://www.ahrq.gov/patient-safety/settings/multiple/measure-dx.html [accessed 2023-06-22]
• Zwaan L, de Bruijne M, Wagner C, Thijs A, Smits M, van der Wal G, et al. Patient record review of the incidence, consequences, and causes of diagnostic adverse events. Arch Intern Med. 2010;170(12):1015-1021. [ CrossRef ] [ Medline ]
• Singh H. Diagnostic errors: moving beyond 'no respect' and getting ready for prime time. BMJ Qual Saf. 2013;22(10):789-792. [ FREE Full text ] [ CrossRef ] [ Medline ]
• Zwaan L, El-Kareh R, Meyer AND, Hooftman J, Singh H. Advancing diagnostic safety research: results of a systematic research priority setting exercise. J Gen Intern Med. 2021;36(10):2943-2951. [ FREE Full text ] [ CrossRef ] [ Medline ]
• Huddleston JM, Diedrich DA, Kinsey GC, Enzler MJ, Manning DM. Learning from every death. J Patient Saf. 2014;10(1):6-12. [ CrossRef ] [ Medline ]
• Arnaud E, Elbattah M, Gignon M, Dequen G. NLP-based prediction of medical specialties at hospital admission using triage notes. 2021. Presented at: IEEE 9th International Conference on Healthcare Informatics (ICHI); August 09-12, 2021; Victoria, British Columbia, Canada. [ CrossRef ]
• Bansal A, Saraswat B, Sharma B, Nayan S, Kathuria K. Data extraction and integration from unstructured electronic health records. 2023. Presented at: 2023 3rd International Conference on Technological Advancements in Computational Sciences (ICTACS); November 01-03, 2023; Tashkent, Uzbekistan. [ CrossRef ]
• Sezgin E, Hussain S, Rust S, Huang Y. Extracting medical information from free-text and unstructured patient-generated health data using natural language processing methods: feasibility study with real-world data. JMIR Form Res. 2023;7:e43014. [ FREE Full text ] [ CrossRef ] [ Medline ]
• Asri H, Mousannif H, Moatassime HA, Noel T. Using machine learning algorithms for breast cancer risk prediction and diagnosis. Procedia Comput Sci. 2016;83:1064-1069. [ CrossRef ]
• Goldenberg SL, Nir G, Salcudean SE. A new era: artificial intelligence and machine learning in prostate cancer. Nat Rev Urol. 2019;16(7):391-403. [ CrossRef ] [ Medline ]
• Henry KE, Adams R, Parent C, Soleimani H, Sridharan A, Johnson L, et al. Factors driving provider adoption of the TREWS machine learning-based early warning system and its effects on sepsis treatment timing. Nat Med. 2022;28(7):1447-1454. [ CrossRef ] [ Medline ]
• Nasiri S, Gari D. Attentive adversarial network for large-scale sleep staging. 2020. Presented at: Proceedings of the 5th Machine Learning for Healthcare Conference, PMLR; September, 2020:457-478; Atlanta, GA, USA. URL: https://proceedings.mlr.press/v126/nasiri20a.html
• Tabaie A, Nemati S, Allen JW, Chung C, Queiroga F, Kuk W, et al. Assessing contribution of higher order clinical risk factors to prediction of outcome in aneurysmal subarachnoid hemorrhage patients. AMIA Annu Symp Proc. 2019;2019:848-856. [ FREE Full text ] [ Medline ]
• Cheheltani R, King N, Lee S, North B, Kovarik D, Evans-Molina C, et al. Predicting misdiagnosed adult-onset type 1 diabetes using machine learning. Diabetes Res Clin Pract. 2022;191:110029. [ FREE Full text ] [ CrossRef ] [ Medline ]
• Hercus C, Hudaib A. Delirium misdiagnosis risk in psychiatry: a machine learning-logistic regression predictive algorithm. BMC Health Serv Res. 2020;20(1):151. [ FREE Full text ] [ CrossRef ] [ Medline ]
• Shen L, Levie A, Singh H, Murray K, Desai S. Harnessing event report data to identify diagnostic error during the COVID-19 pandemic. Jt Comm J Qual Patient Saf. 2022;48(2):71-80. [ FREE Full text ] [ CrossRef ] [ Medline ]
• Murphy DR, Meyer AN, Sittig DF, Meeks DW, Thomas EJ, Singh H. Application of electronic trigger tools to identify targets for improving diagnostic safety. BMJ Qual Saf. 2019;28(2):151-159. [ FREE Full text ] [ CrossRef ] [ Medline ]
• The safety learning system®. Discover the Hidden Causes of Patient Harm. URL: http://hbhealthcaresafety.org/safety-learning-system/ [accessed 2023-06-22]
• Alsentzer E, Murphy J, Boag W, Weng W, Jindi D, Naumann T, et al. Publicly available clinical BERT embeddings. 2019. Presented at: Proceedings of the 2nd Clinical Natural Language Processing Workshop; June, 2019; Minneapolis, Minnesota, USA. [ CrossRef ]
• Huang K, Altosaar A, Ranganath R. ClinicalBERT: modeling clinical notes and predicting hospital readmission. ArXiv. Preprint posted online on April 10, 2019. 2019:190405342. [ CrossRef ]
• Zhang D, Thadajarassiri J, Sen C, Rundensteiner E. Time-aware transformer-based network for clinical notes series prediction. 2020. Presented at: Proceedings of the 5th Machine Learning for Healthcare Conference; September, 2020; Worcester, MA, USA. URL: https://proceedings.mlr.press/v126/zhang20c/zhang20c.pdf
• Jones KS. A statistical interpretation of term specificity and its application in retrieval. J Doc. 1972;28(1):11-21. [ CrossRef ]
• Tabaie A, Sengupta S, Pruitt ZM, Fong A. A natural language processing approach to categorise contributing factors from patient safety event reports. BMJ Health Care Inform. 2023;30(1):e100731. [ FREE Full text ] [ CrossRef ] [ Medline ]
• Aheto JMK, Duah HO, Agbadi P, Nakua EK. A predictive model, and predictors of under-five child malaria prevalence in Ghana: how do LASSO, Ridge and Elastic Net regression approaches compare? Prev Med Rep. 2021;23:101475. [ FREE Full text ] [ CrossRef ] [ Medline ]
• Zou H, Trevor H. Regularization and variable selection via the Elastic Net. J R Stat Soc Series B Stat Methodol. 2005;67(2):301-320. [ CrossRef ]
• Lee SJ, Weinberg BD, Gore A, Banerjee I. A scalable natural language processing for inferring BT-RADS categorization from unstructured brain magnetic resonance reports. J Digit Imaging. 2020;33(6):1393-1400. [ FREE Full text ] [ CrossRef ] [ Medline ]
• Masino AJ, Harris MC, Forsyth D, Ostapenko S, Srinivasan L, Bonafide CP, et al. Machine learning models for early sepsis recognition in the neonatal intensive care unit using readily available electronic health record data. PLoS One. 2019;14(2):e0212665. [ FREE Full text ] [ CrossRef ] [ Medline ]
• Mehta PK, Bess C, Elias-Smale S, Vaccarino V, Quyyumi A, Pepine CJ, et al. Gender in cardiovascular medicine: chest pain and coronary artery disease. Eur Heart J. 2019;40(47):3819-3826. [ FREE Full text ] [ CrossRef ] [ Medline ]
• Jankowski J, Floege J, Fliser D, Böhm M, Marx N. Cardiovascular disease in chronic kidney disease: pathophysiological insights and therapeutic options. Circulation. 2021;143(11):1157-1172. [ FREE Full text ] [ CrossRef ] [ Medline ]
• Giardina TD, Woodard LD, Singh H. Advancing diagnostic equity through clinician engagement, community partnerships, and connected care. J Gen Intern Med. 2023;38(5):1293-1295. [ FREE Full text ] [ CrossRef ] [ Medline ]
• Ibrahim SA, Pronovost PJ. Diagnostic errors, health disparities, and artificial intelligence: a combination for health or harm? JAMA Health Forum. 2021;2(9):e212430. [ FREE Full text ] [ CrossRef ] [ Medline ]
• Newman-Toker DE, Peterson SM, Badihian S, Hassoon A, Nassery N, Parizadeh D, et al. Diagnostic Errors in the Emergency Department: A Systematic Review [internet]. Rockville (MD). Agency for Healthcare Research and Quality; 2022.
• Wu J, Gale CP, Hall M, Dondo TB, Metcalfe E, Oliver G, et al. Editor's choice—impact of initial hospital diagnosis on mortality for acute myocardial infarction: a national cohort study. Eur Heart J Acute Cardiovasc Care. 2018;7(2):139-148. [ FREE Full text ] [ CrossRef ] [ Medline ]
• Burgess S. Understudied, under-recognized, underdiagnosed, and undertreated: sex-based disparities in cardiovascular medicine. Circ Cardiovasc Interv. 2022;15(2):e011714. [ CrossRef ] [ Medline ]
• Sun TY, Hardin J, Nieva HR, Natarajan K, Cheng R, Ryan P, et al. Large-scale characterization of gender differences in diagnosis prevalence and time to diagnosis. MedRxiv. Preprint posted online on October 16, 2023. 2023. [ FREE Full text ] [ CrossRef ] [ Medline ]

Abbreviations

Edited by S Ma, T Leung; submitted 17.07.23; peer-reviewed by D Chrimes, M Elbattah; comments to author 18.01.24; revised version received 21.03.24; accepted 20.06.24; published 26.08.24.

©Azade Tabaie, Alberta Tran, Tony Calabria, Sonita S Bennett, Arianna Milicia, William Weintraub, William James Gallagher, John Yosaitis, Laura C Schubel, Mary A Hill, Kelly Michelle Smith, Kristen Miller. Originally published in the Journal of Medical Internet Research (https://www.jmir.org), 26.08.2024.

This is an open-access article distributed under the terms of the Creative Commons Attribution License (https://creativecommons.org/licenses/by/4.0/), which permits unrestricted use, distribution, and reproduction in any medium, provided the original work, first published in the Journal of Medical Internet Research (ISSN 1438-8871), is properly cited. The complete bibliographic information, a link to the original publication on https://www.jmir.org/, as well as this copyright and license information must be included.