questions longitudinal case study

Have a language expert improve your writing

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

• Knowledge Base
• Methodology
• Longitudinal Study | Definition, Approaches & Examples

Longitudinal Study | Definition, Approaches & Examples

Published on 5 May 2022 by Lauren Thomas . Revised on 24 October 2022.

In a longitudinal study, researchers repeatedly examine the same individuals to detect any changes that might occur over a period of time.

Longitudinal studies are a type of correlational research in which researchers observe and collect data on a number of variables without trying to influence those variables.

While they are most commonly used in medicine, economics, and epidemiology, longitudinal studies can also be found in the other social or medical sciences.

Table of contents

How long is a longitudinal study, longitudinal vs cross-sectional studies, how to perform a longitudinal study, advantages and disadvantages of longitudinal studies, frequently asked questions about longitudinal studies.

No set amount of time is required for a longitudinal study, so long as the participants are repeatedly observed. They can range from as short as a few weeks to as long as several decades. However, they usually last at least a year, oftentimes several.

One of the longest longitudinal studies, the Harvard Study of Adult Development , has been collecting data on the physical and mental health of a group of men in Boston, in the US, for over 80 years.

Prevent plagiarism, run a free check.

The opposite of a longitudinal study is a cross-sectional study. While longitudinal studies repeatedly observe the same participants over a period of time, cross-sectional studies examine different samples (or a ‘cross-section’) of the population at one point in time. They can be used to provide a snapshot of a group or society at a specific moment.

Both types of study can prove useful in research. Because cross-sectional studies are shorter and therefore cheaper to carry out, they can be used to discover correlations that can then be investigated in a longitudinal study.

If you want to implement a longitudinal study, you have two choices: collecting your own data or using data already gathered by somebody else.

Using data from other sources

Many governments or research centres carry out longitudinal studies and make the data freely available to the general public. For example, anyone can access data from the 1970 British Cohort Study, which has followed the lives of 17,000 Brits since their births in a single week in 1970, through the UK Data Service website .

These statistics are generally very trustworthy and allow you to investigate changes over a long period of time. However, they are more restrictive than data you collect yourself. To preserve the anonymity of the participants, the data collected is often aggregated so that it can only be analysed on a regional level. You will also be restricted to whichever variables the original researchers decided to investigate.

If you choose to go down this route, you should carefully examine the source of the dataset as well as what data are available to you.

Collecting your own data

If you choose to collect your own data, the way you go about it will be determined by the type of longitudinal study you choose to perform. You can choose to conduct a retrospective or a prospective study.

• In a retrospective study , you collect data on events that have already happened.
• In a prospective study , you choose a group of subjects and follow them over time, collecting data in real time.

Retrospective studies are generally less expensive and take less time than prospective studies, but they are more prone to measurement error.

Like any other research design , longitudinal studies have their trade-offs: they provide a unique set of benefits, but also come with some downsides.

Longitudinal studies allow researchers to follow their subjects in real time. This means you can better establish the real sequence of events, allowing you insight into cause-and-effect relationships.

Longitudinal studies also allow repeated observations of the same individual over time. This means any changes in the outcome variable cannot be attributed to differences between individuals.

Prospective longitudinal studies eliminate the risk of recall bias , or the inability to correctly recall past events.

Disadvantages

Longitudinal studies are time-consuming and often more expensive than other types of studies, so they require significant commitment and resources to be effective.

Since longitudinal studies repeatedly observe subjects over a period of time, any potential insights from the study can take a while to be discovered.

Attrition, which occurs when participants drop out of a study, is common in longitudinal studies and may result in invalid conclusions.

Longitudinal studies and cross-sectional studies are two different types of research design . In a cross-sectional study you collect data from a population at a specific point in time; in a longitudinal study you repeatedly collect data from the same sample over an extended period of time.

Longitudinal studies can last anywhere from weeks to decades, although they tend to be at least a year long.

The 1970 British Cohort Study , which has collected data on the lives of 17,000 Brits since their births in 1970, is one well-known example of a longitudinal study .

Longitudinal studies are better to establish the correct sequence of events, identify changes over time, and provide insight into cause-and-effect relationships, but they also tend to be more expensive and time-consuming than other types of studies.

Cite this Scribbr article

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

Thomas, L. (2022, October 24). Longitudinal Study | Definition, Approaches & Examples. Scribbr. Retrieved 22 April 2024, from https://www.scribbr.co.uk/research-methods/longitudinal-study-design/

Is this article helpful?

Lauren Thomas

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

Longitudinal Study Design

Julia Simkus

Editor at Simply Psychology

BA (Hons) Psychology, Princeton University

Julia Simkus is a graduate of Princeton University with a Bachelor of Arts in Psychology. She is currently studying for a Master's Degree in Counseling for Mental Health and Wellness in September 2023. Julia's research has been published in peer reviewed journals.

Learn about our Editorial Process

Saul Mcleod, PhD

Editor-in-Chief for Simply Psychology

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

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

Olivia Guy-Evans, MSc

Associate Editor for Simply Psychology

BSc (Hons) Psychology, MSc Psychology of Education

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

A longitudinal study is a type of observational and correlational study that involves monitoring a population over an extended period of time. It allows researchers to track changes and developments in the subjects over time.

What is a Longitudinal Study?

In longitudinal studies, researchers do not manipulate any variables or interfere with the environment. Instead, they simply conduct observations on the same group of subjects over a period of time.

These research studies can last as short as a week or as long as multiple years or even decades. Unlike cross-sectional studies that measure a moment in time, longitudinal studies last beyond a single moment, enabling researchers to discover cause-and-effect relationships between variables.

They are beneficial for recognizing any changes, developments, or patterns in the characteristics of a target population. Longitudinal studies are often used in clinical and developmental psychology to study shifts in behaviors, thoughts, emotions, and trends throughout a lifetime.

For example, a longitudinal study could be used to examine the progress and well-being of children at critical age periods from birth to adulthood.

The Harvard Study of Adult Development is one of the longest longitudinal studies to date. Researchers in this study have followed the same men group for over 80 years, observing psychosocial variables and biological processes for healthy aging and well-being in late life (see Harvard Second Generation Study).

When designing longitudinal studies, researchers must consider issues like sample selection and generalizability, attrition and selectivity bias, effects of repeated exposure to measures, selection of appropriate statistical models, and coverage of the necessary timespan to capture the phenomena of interest.

Panel Study

• A panel study is a type of longitudinal study design in which the same set of participants are measured repeatedly over time.
• Data is gathered on the same variables of interest at each time point using consistent methods. This allows studying continuity and changes within individuals over time on the key measured constructs.
• Prominent examples include national panel surveys on topics like health, aging, employment, and economics. Panel studies are a type of prospective study .

Cohort Study

• A cohort study is a type of longitudinal study that samples a group of people sharing a common experience or demographic trait within a defined period, such as year of birth.
• Researchers observe a population based on the shared experience of a specific event, such as birth, geographic location, or historical experience. These studies are typically used among medical researchers.
• Cohorts are identified and selected at a starting point (e.g. birth, starting school, entering a job field) and followed forward in time. 
• As they age, data is collected on cohort subgroups to determine their differing trajectories. For example, investigating how health outcomes diverge for groups born in 1950s, 1960s, and 1970s.
• Cohort studies do not require the same individuals to be assessed over time; they just require representation from the cohort.

Retrospective Study

• In a retrospective study , researchers either collect data on events that have already occurred or use existing data that already exists in databases, medical records, or interviews to gain insights about a population.
• Appropriate when prospectively following participants from the past starting point is infeasible or unethical. For example, studying early origins of diseases emerging later in life.
• Retrospective studies efficiently provide a “snapshot summary” of the past in relation to present status. However, quality concerns with retrospective data make careful interpretation necessary when inferring causality. Memory biases and selective retention influence quality of retrospective data.

Allows researchers to look at changes over time

Because longitudinal studies observe variables over extended periods of time, researchers can use their data to study developmental shifts and understand how certain things change as we age.

High validation

Since objectives and rules for long-term studies are established before data collection, these studies are authentic and have high levels of validity.

Eliminates recall bias

Recall bias occurs when participants do not remember past events accurately or omit details from previous experiences.

Flexibility

The variables in longitudinal studies can change throughout the study. Even if the study was created to study a specific pattern or characteristic, the data collection could show new data points or relationships that are unique and worth investigating further.

Limitations

Costly and time-consuming.

Longitudinal studies can take months or years to complete, rendering them expensive and time-consuming. Because of this, researchers tend to have difficulty recruiting participants, leading to smaller sample sizes.

Large sample size needed

Longitudinal studies tend to be challenging to conduct because large samples are needed for any relationships or patterns to be meaningful. Researchers are unable to generate results if there is not enough data.

Participants tend to drop out

Not only is it a struggle to recruit participants, but subjects also tend to leave or drop out of the study due to various reasons such as illness, relocation, or a lack of motivation to complete the full study.

This tendency is known as selective attrition and can threaten the validity of an experiment. For this reason, researchers using this approach typically recruit many participants, expecting a substantial number to drop out before the end.

Report bias is possible

Longitudinal studies will sometimes rely on surveys and questionnaires, which could result in inaccurate reporting as there is no way to verify the information presented.

• Data were collected for each child at three-time points: at 11 months after adoption, at 4.5 years of age and at 10.5 years of age. The first two sets of results showed that the adoptees were behind the non-institutionalised group however by 10.5 years old there was no difference between the two groups. The Romanian orphans had caught up with the children raised in normal Canadian families.
• The role of positive psychology constructs in predicting mental health and academic achievement in children and adolescents (Marques Pais-Ribeiro, & Lopez, 2011)
• The correlation between dieting behavior and the development of bulimia nervosa (Stice et al., 1998)
• The stress of educational bottlenecks negatively impacting students’ wellbeing (Cruwys, Greenaway, & Haslam, 2015)
• The effects of job insecurity on psychological health and withdrawal (Sidney & Schaufeli, 1995)
• The relationship between loneliness, health, and mortality in adults aged 50 years and over (Luo et al., 2012)
• The influence of parental attachment and parental control on early onset of alcohol consumption in adolescence (Van der Vorst et al., 2006)
• The relationship between religion and health outcomes in medical rehabilitation patients (Fitchett et al., 1999)

Goals of Longitudinal Data and Longitudinal Research

The objectives of longitudinal data collection and research as outlined by Baltes and Nesselroade (1979):

• Identify intraindividual change : Examine changes at the individual level over time, including long-term trends or short-term fluctuations. Requires multiple measurements and individual-level analysis.
• Identify interindividual differences in intraindividual change : Evaluate whether changes vary across individuals and relate that to other variables. Requires repeated measures for multiple individuals plus relevant covariates.
• Analyze interrelationships in change : Study how two or more processes unfold and influence each other over time. Requires longitudinal data on multiple variables and appropriate statistical models.
• Analyze causes of intraindividual change: This objective refers to identifying factors or mechanisms that explain changes within individuals over time. For example, a researcher might want to understand what drives a person’s mood fluctuations over days or weeks. Or what leads to systematic gains or losses in one’s cognitive abilities across the lifespan.
• Analyze causes of interindividual differences in intraindividual change : Identify mechanisms that explain within-person changes and differences in changes across people. Requires repeated data on outcomes and covariates for multiple individuals plus dynamic statistical models.

How to Perform a Longitudinal Study

When beginning to develop your longitudinal study, you must first decide if you want to collect your own data or use data that has already been gathered.

Using already collected data will save you time, but it will be more restricted and limited than collecting it yourself. When collecting your own data, you can choose to conduct either a retrospective or prospective study .

In a retrospective study, you are collecting data on events that have already occurred. You can examine historical information, such as medical records, in order to understand the past. In a prospective study, on the other hand, you are collecting data in real-time. Prospective studies are more common for psychology research.

Once you determine the type of longitudinal study you will conduct, you then must determine how, when, where, and on whom the data will be collected.

A standardized study design is vital for efficiently measuring a population. Once a study design is created, researchers must maintain the same study procedures over time to uphold the validity of the observation.

A schedule should be maintained, complete results should be recorded with each observation, and observer variability should be minimized.

Researchers must observe each subject under the same conditions to compare them. In this type of study design, each subject is the control.

Methodological Considerations

Important methodological considerations include testing measurement invariance of constructs across time, appropriately handling missing data, and using accelerated longitudinal designs that sample different age cohorts over overlapping time periods.

Testing measurement invariance

Testing measurement invariance involves evaluating whether the same construct is being measured in a consistent, comparable way across multiple time points in longitudinal research.

This includes assessing configural, metric, and scalar invariance through confirmatory factor analytic approaches. Ensuring invariance gives more confidence when drawing inferences about change over time.

Missing data

Missing data can occur during initial sampling if certain groups are underrepresented or fail to respond.

Attrition over time is the main source – participants dropping out for various reasons. The consequences of missing data are reduced statistical power and potential bias if dropout is nonrandom.

Handling missing data appropriately in longitudinal studies is critical to reducing bias and maintaining power.

It is important to minimize attrition by tracking participants, keeping contact info up to date, engaging them, and providing incentives over time.

Techniques like maximum likelihood estimation and multiple imputation are better alternatives to older methods like listwise deletion. Assumptions about missing data mechanisms (e.g., missing at random) shape the analytic approaches taken.

Accelerated longitudinal designs

Accelerated longitudinal designs purposefully create missing data across age groups.

Accelerated longitudinal designs strategically sample different age cohorts at overlapping periods. For example, assessing 6th, 7th, and 8th graders at yearly intervals would cover 6-8th grade development over a 3-year study rather than following a single cohort over that timespan.

This increases the speed and cost-efficiency of longitudinal data collection and enables the examination of age/cohort effects. Appropriate multilevel statistical models are required to analyze the resulting complex data structure.

In addition to those considerations, optimizing the time lags between measurements, maximizing participant retention, and thoughtfully selecting analysis models that align with the research questions and hypotheses are also vital in ensuring robust longitudinal research.

So, careful methodology is key throughout the design and analysis process when working with repeated-measures data.

Cohort effects

A cohort refers to a group born in the same year or time period. Cohort effects occur when different cohorts show differing trajectories over time.

Cohort effects can bias results if not accounted for, especially in accelerated longitudinal designs which assume cohort equivalence.

Detecting cohort effects is important but can be challenging as they are confounded with age and time of measurement effects.

Cohort effects can also interfere with estimating other effects like retest effects. This happens because comparing groups to estimate retest effects relies on cohort equivalence.

Overall, researchers need to test for and control cohort effects which could otherwise lead to invalid conclusions. Careful study design and analysis is required.

Retest effects

Retest effects refer to gains in performance that occur when the same or similar test is administered on multiple occasions.

For example, familiarity with test items and procedures may allow participants to improve their scores over repeated testing above and beyond any true change.

Specific examples include:

• Memory tests – Learning which items tend to be tested can artificially boost performance over time
• Cognitive tests – Becoming familiar with the testing format and particular test demands can inflate scores
• Survey measures – Remembering previous responses can bias future responses over multiple administrations
• Interviews – Comfort with the interviewer and process can lead to increased openness or recall

To estimate retest effects, performance of retested groups is compared to groups taking the test for the first time. Any divergence suggests inflated scores due to retesting rather than true change.

If unchecked in analysis, retest gains can be confused with genuine intraindividual change or interindividual differences.

This undermines the validity of longitudinal findings. Thus, testing and controlling for retest effects are important considerations in longitudinal research.

Data Analysis

Longitudinal data involves repeated assessments of variables over time, allowing researchers to study stability and change. A variety of statistical models can be used to analyze longitudinal data, including latent growth curve models, multilevel models, latent state-trait models, and more.

Latent growth curve models allow researchers to model intraindividual change over time. For example, one could estimate parameters related to individuals’ baseline levels on some measure, linear or nonlinear trajectory of change over time, and variability around those growth parameters. These models require multiple waves of longitudinal data to estimate.

Multilevel models are useful for hierarchically structured longitudinal data, with lower-level observations (e.g., repeated measures) nested within higher-level units (e.g., individuals). They can model variability both within and between individuals over time.

Latent state-trait models decompose the covariance between longitudinal measurements into time-invariant trait factors, time-specific state residuals, and error variance. This allows separating stable between-person differences from within-person fluctuations.

There are many other techniques like latent transition analysis, event history analysis, and time series models that have specialized uses for particular research questions with longitudinal data. The choice of model depends on the hypotheses, timescale of measurements, age range covered, and other factors.

In general, these various statistical models allow investigation of important questions about developmental processes, change and stability over time, causal sequencing, and both between- and within-person sources of variability. However, researchers must carefully consider the assumptions behind the models they choose.

Longitudinal vs. Cross-Sectional Studies

Longitudinal studies and cross-sectional studies are two different observational study designs where researchers analyze a target population without manipulating or altering the natural environment in which the participants exist.

Yet, there are apparent differences between these two forms of study. One key difference is that longitudinal studies follow the same sample of people over an extended period of time, while cross-sectional studies look at the characteristics of different populations at a given moment in time.

Longitudinal studies tend to require more time and resources, but they can be used to detect cause-and-effect relationships and establish patterns among subjects.

On the other hand, cross-sectional studies tend to be cheaper and quicker but can only provide a snapshot of a point in time and thus cannot identify cause-and-effect relationships.

Both studies are valuable for psychologists to observe a given group of subjects. Still, cross-sectional studies are more beneficial for establishing associations between variables, while longitudinal studies are necessary for examining a sequence of events.

1. Are longitudinal studies qualitative or quantitative?

Longitudinal studies are typically quantitative. They collect numerical data from the same subjects to track changes and identify trends or patterns.

However, they can also include qualitative elements, such as interviews or observations, to provide a more in-depth understanding of the studied phenomena.

2. What’s the difference between a longitudinal and case-control study?

Case-control studies compare groups retrospectively and cannot be used to calculate relative risk. Longitudinal studies, though, can compare groups either retrospectively or prospectively.

In case-control studies, researchers study one group of people who have developed a particular condition and compare them to a sample without the disease.

Case-control studies look at a single subject or a single case, whereas longitudinal studies are conducted on a large group of subjects.

3. Does a longitudinal study have a control group?

Yes, a longitudinal study can have a control group . In such a design, one group (the experimental group) would receive treatment or intervention, while the other group (the control group) would not.

Both groups would then be observed over time to see if there are differences in outcomes, which could suggest an effect of the treatment or intervention.

However, not all longitudinal studies have a control group, especially observational ones and not testing a specific intervention.

Baltes, P. B., & Nesselroade, J. R. (1979). History and rationale of longitudinal research. In J. R. Nesselroade & P. B. Baltes (Eds.), (pp. 1–39). Academic Press.

Cook, N. R., & Ware, J. H. (1983). Design and analysis methods for longitudinal research. Annual review of public health , 4, 1–23.

Fitchett, G., Rybarczyk, B., Demarco, G., & Nicholas, J.J. (1999). The role of religion in medical rehabilitation outcomes: A longitudinal study. Rehabilitation Psychology, 44, 333-353.

Harvard Second Generation Study. (n.d.). Harvard Second Generation Grant and Glueck Study. Harvard Study of Adult Development. Retrieved from https://www.adultdevelopmentstudy.org.

Le Mare, L., & Audet, K. (2006). A longitudinal study of the physical growth and health of postinstitutionalized Romanian adoptees. Pediatrics & child health, 11 (2), 85-91.

Luo, Y., Hawkley, L. C., Waite, L. J., & Cacioppo, J. T. (2012). Loneliness, health, and mortality in old age: a national longitudinal study. Social science & medicine (1982), 74 (6), 907–914.

Marques, S. C., Pais-Ribeiro, J. L., & Lopez, S. J. (2011). The role of positive psychology constructs in predicting mental health and academic achievement in children and adolescents: A two-year longitudinal study. Journal of Happiness Studies: An Interdisciplinary Forum on Subjective Well-Being, 12( 6), 1049–1062.

Sidney W.A. Dekker & Wilmar B. Schaufeli (1995) The effects of job insecurity on psychological health and withdrawal: A longitudinal study, Australian Psychologist, 30: 1,57-63.

Stice, E., Mazotti, L., Krebs, M., & Martin, S. (1998). Predictors of adolescent dieting behaviors: A longitudinal study. Psychology of Addictive Behaviors, 12 (3), 195–205.

Tegan Cruwys, Katharine H Greenaway & S Alexander Haslam (2015) The Stress of Passing Through an Educational Bottleneck: A Longitudinal Study of Psychology Honours Students, Australian Psychologist, 50:5, 372-381.

Thomas, L. (2020). What is a longitudinal study? Scribbr. Retrieved from https://www.scribbr.com/methodology/longitudinal-study/

Van der Vorst, H., Engels, R. C. M. E., Meeus, W., & Deković, M. (2006). Parental attachment, parental control, and early development of alcohol use: A longitudinal study. Psychology of Addictive Behaviors, 20 (2), 107–116.

Further Information

• Schaie, K. W. (2005). What can we learn from longitudinal studies of adult development?. Research in human development, 2 (3), 133-158.
• Caruana, E. J., Roman, M., Hernández-Sánchez, J., & Solli, P. (2015). Longitudinal studies. Journal of thoracic disease, 7 (11), E537.

• Open access
• Published: 01 October 2022

Qualitative longitudinal research in health research: a method study

• Åsa Audulv 1 ,
• Elisabeth O. C. Hall 2 , 3 ,
• Åsa Kneck 4 ,
• Thomas Westergren 5 , 6 ,
• Liv Fegran 5 ,
• Mona Kyndi Pedersen 7 , 8 ,
• Hanne Aagaard 9 ,
• Kristianna Lund Dam 3 &
• Mette Spliid Ludvigsen 10 , 11  

BMC Medical Research Methodology volume  22 , Article number:  255 ( 2022 ) Cite this article

10k Accesses

18 Citations

2 Altmetric

Metrics details

Qualitative longitudinal research (QLR) comprises qualitative studies, with repeated data collection, that focus on the temporality (e.g., time and change) of a phenomenon. The use of QLR is increasing in health research since many topics within health involve change (e.g., progressive illness, rehabilitation). A method study can provide an insightful understanding of the use, trends and variations within this approach. The aim of this study was to map how QLR articles within the existing health research literature are designed to capture aspects of time and/or change.

This method study used an adapted scoping review design. Articles were eligible if they were written in English, published between 2017 and 2019, and reported results from qualitative data collected at different time points/time waves with the same sample or in the same setting. Articles were identified using EBSCOhost. Two independent reviewers performed the screening, selection and charting.

A total of 299 articles were included. There was great variation among the articles in the use of methodological traditions, type of data, length of data collection, and components of longitudinal data collection. However, the majority of articles represented large studies and were based on individual interview data. Approximately half of the articles self-identified as QLR studies or as following a QLR design, although slightly less than 20% of them included QLR method literature in their method sections.

Conclusions

QLR is often used in large complex studies. Some articles were thoroughly designed to capture time/change throughout the methodology, aim and data collection, while other articles included few elements of QLR. Longitudinal data collection includes several components, such as what entities are followed across time, the tempo of data collection, and to what extent the data collection is preplanned or adapted across time. Therefore, there are several practices and possibilities researchers should consider before starting a QLR project.

Peer Review reports

Health research is focused on areas and topics where time and change are relevant. For example, processes such as recovery or changes in health status. However, relating time and change can be complicated in research, as the representation of reality in research publications is often collected at one point in time and fixed in its presentation, although time and change are always present in human life and experiences. Qualitative longitudinal research (QLR; also called longitudinal qualitative research, LQR) has been developed to focus on subjective experiences of time or change using qualitative data materials (e.g., interviews, observations and/or text documents) collected across a time span with the same participants and/or in the same setting [ 1 , 2 ]. QLR within health research may have many benefits. Firstly, human experiences are not fixed and consistent, but changing and diverse, therefore people’s experiences in relation to a health phenomenon may be more comprehensively described by repeated interviews or observations over time. Secondly, experiences, behaviors, and social norms unfold over time. By using QLR, researchers can collect empirical data that represents not only recalled human conceptions but also serial and instant situations reflecting transitions, trajectories and changes in people’s health experiences, personal development or health care organizations [ 3 , 4 , 5 ].

Key features of QLR

Whether QLR is a methodological approach in its own right or a design element of a particular study within a traditional methodological approach (e.g., ethnography or grounded theory) is debated [ 1 , 6 ]. For example, Bennett et al. [ 7 ] describe QLR as untied to methodology, giving researchers the flexibility to develop a suitable design for each study. McCoy [ 6 ] suggests that epistemological and ontological standpoints from interpretative phenomenological analysis (IPA) align with QLR traditions, thus making longitudinal IPA a suitable methodology. Plano-Clark et al. [ 8 ] described how longitudinal qualitative elements can be used in mixed methods studies, thus creating longitudinal mixed methods. In contrast, several researchers have argued that QLR is an emerging methodology [ 1 , 5 , 9 , 10 ]. For example, Thomson et al. [ 9 ] have stated “What distinguishes longitudinal qualitative research is the deliberate way in which temporality is designed into the research process, making change a central focus of analytic attention” (p. 185). Tuthill et al. [ 5 ] concluded that some of the confusion might have arisen from the diversity of data collection methods and data materials used within QLR research. However, there are no investigations showing to what extent QLR studies use QLR as a distinct methodology versus using a longitudinal data collection as a more flexible design element in combination with other qualitative methodologies.

QLR research should focus on aspects of temporality, time and/or change [ 11 , 12 , 13 ]. The concepts of time and change are seen as inseparable since change is happening with the passing of time [ 13 ]. However, time can be conceptualized in different ways. Time is often understood from a chronological perspective, and is viewed as fixed, objective, continuous and measurable (e.g., clock time, duration of time). However, time can also be understood from within, as the experience of the passing of time and/or the perspective from the current moment into the constructed conception of a history or future. From this perspective, time is seen as fluid, meaning that events, contexts and understandings create a subjective experience of time and change. Both the chronological and fluid understanding of time influence QLR research [ 11 ]. Furthermore, there is a distinction between over-time, which constitutes a comparison of the difference between points in time, often with a focus on the latter point or destination, and through-time, which means following an aspect across time while trying to understand the change that occurs [ 11 ]. In this article, we will mostly use the concept of across time to include both perspectives.

Some authors assert that QLR studies should include a qualitative data collection with the same sample across time [ 11 , 13 ], whereas Thomson et al. [ 9 ] also suggest the possibility of returning to the same data collection site with the same or different participants. When a QLR study involves data collection in shorter engagements, such as serial interviews, these engagements are often referred to as data collection time points. Data collection in time waves relates to longer engagements, such as field work/observation periods. There is no clear-cut definition for the minimum time span of a QLR study; instead, the length of the data collection period must be decided based upon what processes or changes are the focus of the study [ 13 ].

Most literature describing QLR methods originates from the social sciences, where the approach has a long tradition [ 1 , 10 , 14 ]. In health research, one-time-data collection studies have been the norm within qualitative methods [ 15 ], although health research using QLR methods has increased in recent years [ 2 , 5 , 16 , 17 ]. However, collecting and managing longitudinal data has its own sets of challenges, especially regarding how to integrate perspectives of time and/or change in the data collection and subsequent analysis [ 1 ]. Therefore, a study of QLR articles from the health research literature can provide an insightful understanding of the use, trends and variations of how methods are used and how elements of time/change are integrated in QLR studies. This could, in turn, provide inspiration for using different possibilities of collecting data across time when using QLR in health research. The aim of this study was to map how QLR articles within the existing health research literature are designed to capture aspects of time and/or change.

More specifically, the research questions were:

What methodological approaches are described to inform QLR research?

What methodological references are used to inform QLR research?

How are longitudinal perspectives articulated in article aims?

How is longitudinal data collection conducted?

In this method study, we used an adapted scoping review method [ 18 , 19 , 20 ]. Method studies are research conducted on research studies to investigate how research design elements are applied across a field [ 21 ]. However, since there are no clear guidelines for method studies, they often use adapted versions of systematic reviews or scoping review methods [ 21 ]. The adaptations of the scoping review method consisted of 1) using a large subsample of studies (publications from a three-year period) instead of including all QLR articles published, and 2) not including grey literature. The reporting of this study was guided by the Preferred Reporting Items for Systematic reviews and Meta-Analyses extension for Scoping Reviews (PRISMA-ScR) checklist [ 20 , 22 ] (see Additional file 1 ). A (unpublished) protocol was developed by the research team during the spring of 2019.

Eligibility criteria

In line with method study recommendations [ 21 ], we decided to draw on a manageable subsample of published QLR research. Articles that were eligible for inclusion were health research primary studies written in English, published between 2017 and 2019, and with a longitudinal qualitative data collection. Our operating definition for qualitative longitudinal data collection was data collected at different time points (e.g., repeated interviews) or time waves (e.g., periods of field work) involving the same sample or conducted in the same setting(s). We intentionally selected a broad inclusion criterion for QLR since we wanted a wide variety of articles. The selected time period was chosen because the first QLR method article directed towards health research was published in 2013 [ 1 ] and during the following years the methodological resources for QLR increased [ 3 , 8 , 17 , 23 , 24 , 25 ], thus we could expect that researchers publishing QLR in 2017–2019 should be well-grounded in QLR methods. Further, we found that from 2012 to 2019 the rate of published QLR articles were steady at around 100 publications per year, so including those from a three-year period would give a sufficient number of articles (~ 300 articles) for providing an overview of the field. Published conference abstracts, protocols, articles describing methodological issues, review articles, and non-research articles (e.g., editorials) were excluded.

Search strategy

Relevant articles were identified through systematic searches in EBSCOhost, including biomedical and life science research and nursing and allied health literature. A librarian who specialized in systematic review searches developed and performed the searches, in collaboration with the author team (LF, TW & ÅA). In the search, the term “longitudinal” was combined with terms for qualitative research (for the search strategy see Additional file 2 ). The searches were conducted in the autumn of 2019 (last search 2019-09-10).

Study selection

All identified citations were imported into EndNote X9 ( www.endnote.com ) and further imported into Rayyan QCRI online software [ 26 ], and duplicates were removed. All titles and abstracts were screened against the eligibility criteria by two independent reviewers (ÅA & EH), and conflicting decisions were discussed until resolved. After discussions by the team, we decided to include articles published between 2017 and 2019, that selection alone included 350 records with diverse methods and designs. The full texts of articles that were eligible for inclusion were retrieved. In the next stage, two independent reviewers reviewed each full text article to make final decisions regarding inclusion (ÅA, EH, Julia Andersson). In total, disagreements occurred in 8% of the decisions, and were resolved through discussion. Critical appraisal was not assessed since the study aimed to describe the range of how QLR is applied and not aggregate research findings [ 21 , 22 ].

Data charting and analysis

A standardized charting form was developed in Excel (Excel 2016). The charting form was reviewed by the research team and pretested in two stages. The tests were performed to increase internal consistency and reduce the risk of bias. First, four articles were reviewed by all the reviewers, and modifications were made to the form and charting instructions. In the next stage, all reviewers used the charting form on four other articles, and the convergence in ratings was 88%. Since the convergence was under 90%, charting was performed in duplicate to reduce errors in the data. At the end of the charting process, the convergence among the reviewers was 95%. The charting was examined by the first author, who revised the charting in cases of differences.

Data items that were charted included 1) the article characteristics (e.g., authors, publication year, journal, country), 2) the aim and scope (e.g., phenomenon of interest, population, contexts), 3) the stated methodology and analysis method, 4) text describing the data collection (e.g., type of data material, number of participants, time frame of data collection, total amount of data material), and 5) the qualitative methodological references used in the methods section. Extracted text describing data collection could consist of a few sentences or several sections from the articles (and sometimes figures) concerning data collection practices, rational for time periods and research engagement in the field. This was later used to analyze how the longitudinal data collection was conducted and elements of longitudinal design. To categorize the qualitative methodology approaches, a framework from Cresswell [ 27 ] was used (including the categories for grounded theory, phenomenology, ethnography, case study and narrative research). Overall, data items needed to be explicitly stated in the articles in order to be charted. For example, an article was categorized as grounded theory if it explicitly stated “in this grounded theory study” but not if it referred to the literature by Glaser and Strauss without situating itself as a grounded theory study (See Additional file 3 for the full instructions for charting).

All charting forms were compiled into a single Microsoft Excel spreadsheet (see Supplementary files for an overview of the articles). Descriptive statistics with frequencies and percentages were calculated to summarize the data. Furthermore, an iterative coding process was used to group the articles and investigate patterns of, for example, research topics, words in the aims, or data collection practices. Alternative ways of grouping and presenting the data were discussed by the research team.

Search and selection

A total of 2179 titles and abstracts were screened against the eligibility criteria (see Fig.  1 ). The full text of one article could not be found and the article was excluded [ 28 ]. Fifty full text articles were excluded. Finally, 299 articles, representing 271 individual studies, were included in this study (see additional files 4 and 5 respectively for tables of excluded and included articles).

PRISMA diagram of study selection]

General characteristics and research areas of the included articles

The articles were published in many journals ( n  = 193), and 138 of these journals were represented with one article each. BMJ Open was the most prevalent journal ( n  = 11), followed by the Journal of Clinical Nursing ( n  = 8). Similarly, the articles represented many countries ( n  = 41) and all the continents; however, a large part of the studies originated from the US or UK ( n  = 71, 23.7% and n  = 70, 23.4%, respectively). The articles focused on the following types of populations: patients, families−/caregivers, health care providers, students, community members, or policy makers. Approximately 20% ( n  = 63, 21.1%) of the articles collected data from two or more of these types of population(s) (see Table  1 ).

Approximately half of the articles ( n  = 158, 52.8%) articulated being part of a larger research project. Of them, 95 described a project with both quantitative and qualitative methods. They represented either 1) a qualitative study embedded in an intervention, evaluation or implementation study ( n  = 66, 22.1%), 2) a longitudinal cohort study collecting both quantitative and qualitative material ( n  = 23, 7.7%), or 3) qualitative longitudinal material collected together with a cross sectional survey (n = 6, 2.0%). Forty-eight articles (16.1%) described belonging to a larger qualitative project presented in several research articles.

Methodological traditions

Approximately one-third ( n  = 109, 36.5%) of the included articles self-identified with one of the qualitative traditions recognized by Cresswell [ 27 ] (case study: n  = 36, 12.0%; phenomenology: n  = 35, 11.7%; grounded theory: n  = 22, 7.4%; ethnography: n  = 13, 4.3%; narrative method: n = 3, 1.0%). In nine articles, the authors described using a mix of two or more of these qualitative traditions. In addition, 19 articles (6.4%) self-identified as mixed methods research.

Every second article self-identified as having a qualitative longitudinal design ( n  = 156, 52.2%); either they self-identified as “a longitudinal qualitative study” or “using a longitudinal qualitative research design”. However, in some articles, this was stated in the title and/or abstract and nowhere else in the article. Fifty-two articles (17.4%) self-identified both as having a QLR design and following one of the methodological approaches (case study: n  = 8; phenomenology: n  = 23; grounded theory: n  = 9; ethnography: n  = 6; narrative method: n  = 2; mixed methods: n  = 4).

The other 143 articles used various terms to situate themselves in relation to a longitudinal design. Twenty-seven articles described themselves as a longitudinal study (9.0%) or a longitudinal study within a specific qualitative tradition (e.g., a longitudinal grounded theory study or a longitudinal mixed method study) ( n  = 64, 21.4%). Furthermore, 36 articles (12.0%) referred to using longitudinal data materials (e.g., longitudinal data or longitudinal interviews). Nine of the articles (3.0%) used the term longitudinal in relation to the data analysis or aim (e.g., the aim was to longitudinally describe), used terms such as serial or repeated in relation to the data collection design ( n  = 2, 0.7%), or did not use any term to address the longitudinal nature of their design ( n  = 5, 1.7%).

Use of methodological references

The mean number of qualitative method references in the methods sections was 3.7 (range 0 to 16), and 20 articles did not have any qualitative method reference in their methods sections. Footnote 1 Commonly used method references were generic books on qualitative methods, seminal works within qualitative traditions, and references specializing in qualitative analysis methods (see Table  2 ). It should be noted that some references were comprehensive books and thus could include sections about QLR without being focused on the QLR method. For example, Miles et al. [ 31 ] is all about analysis and coding and includes a chapter regarding analyzing change.

Only approximately 20% ( n  = 58) of the articles referred to the QLR method literature in their methods sections. Footnote 2 The mean number of QLR method references (counted for articles using such sources) was 1.7 (range 1 to 6). Most articles using the QLR method literature also used other qualitative methods literature (except two articles using one QLR literature reference each [ 39 , 40 ]). In total, 37 QLR method references were used, and 24 of the QLR method references were only referred to by one article each.

Longitudinal perspectives in article aims

In total, 231 (77.3%) articles had one or several terms related to time or change in their aims, whereas 68 articles (22.7%) had none. Over one hundred different words related to time or change were identified. Longitudinally oriented terms could focus on changes across time (process, trajectory, transition, pathway or journey), patterns of how something changed (maintenance, continuity, stability, shifts), or phenomena that by nature included change (learning or implementation). Other types of terms emphasized the data collection time period (e.g., over 6 months) or a specific changing situation (e.g., during pregnancy, through the intervention period, or moving into a nursing home). The most common terms used for the longitudinal perspective were change ( n  = 63), over time ( n  = 52), process ( n  = 36), transition ( n  = 24), implementation ( n  = 14), development ( n  = 13), and longitudinal (n = 13). Footnote 3

Furthermore, the articles varied in what ways their aims focused on time/change, e.g., the longitudinal perspectives in the aims (see Table  3 ). In 71 articles, the change across time was the phenomenon of interest of the article : for example, articles investigating the process of learning or trajectories of diseases. In contrast, 46 articles investigated change or factors impacting change in relation to a defined outcome : for example, articles investigating factors influencing participants continuing in a physical activity trial. The longitudinal perspective could also be embedded in an article’s context . In such cases, the focus of the article was on experiences that happened during a certain time frame or in a time-related context (e.g., described experiences of the patient-provider relationship during 6 months of rehabilitation).

Types of data and length of data collection

The QLR articles were often large and complex in their data collection methods. The median number of participants was 20 (range from one to 1366, the latter being an article with open-ended questions in questionnaires [ 46 ]). Most articles used individual interviews as the data material ( n  = 167, 55.9%) or a combination of data materials ( n  = 98, 32.8%) (e.g., interviews and observations, individual interviews and focus group interviews, or interviews and questionnaires). Forty-five articles (15.1%) presented quantitative and qualitative results. The median number of interviews was 46 (range three to 507), which is large in comparison to many qualitative studies. The observation materials were also comprehensive and could include several hundred hours of observations. Documents were often used as complementary material and included official documents, newspaper articles, diaries, and/or patient records.

The articles’ time spans Footnote 4 for data collection varied between a few days and over 20 years, with 60% of the articles’ time spans being 1 year or shorter ( n  = 180) (see Fig.  2 ). The variation in time spans might be explained by the different kinds of phenomena that were investigated. For example, Jensen et al. [ 47 ] investigated hospital care delivery and followed each participant, with observations lasting between four and 14 days. Smithbattle [ 48 ] described the housing trajectories of teen mothers, and collected data in seven waves over 28 years.

Number of articles in relation to the time span of data collection. The time span of data collection is given in months

Three components of longitudinal data collection

In the articles, the data collection was conducted in relation to three different longitudinal data collection components (see Table  4 ).

Entities followed across time

Four different types of entities were followed across time: 1) individuals, 2) individual cases or dyads, 3) groups, and 4) settings. Every second article ( n  = 170, 56.9%) followed individuals across time, thus following the same participants through the whole data collection period. In contrast, when individual cases were followed across time, the data collection was centered on the primary participants (e.g., people with progressive neurological conditions) who were followed over time, and secondary participants (e.g., family caregivers) might provide complementary data at several time points or only at one-time point. When settings were followed over time, the participating individuals were sometimes the same, and sometimes changed across the data collection period. Typical settings were hospital wards, hospitals, smaller communities or intervention trials. The type of collected data corresponded with what kind of entities were followed longitudinally. Individuals were often followed with serial interviews, whereas groups were commonly followed with focus group interviews complemented with individual interviews, observations and/or questionnaires. Overall, the lengths of data collection periods seemed to be chosen based upon expected changes in the chosen entities. For example, the articles following an intervention setting were structured around the intervention timeline, collecting data before, after and sometimes during the intervention.

Tempo of data collection

The data collection tempo differed among the articles (e.g., the frequency and mode of the data collection). Approximately half ( n  = 154, 51.5%) of the articles used serial time points, collecting data at several reoccurring but shorter sequences (e.g., through serial interviews or open-ended questions in questionnaires). When data were collected in time waves ( n  = 50, 16.7%), the periods of data collection were longer, usually including both interviews and observations; often, time waves included observations of a setting and/or interviews at the same location over several days or weeks.

When comparing the tempo with the type of entities, some patterns were detected (see Fig.  3 ). When individuals were followed, data were often collected at time points, mirroring the use of individual interviews and/or short observations. For research in settings, data were commonly collected in time waves (e.g., observation periods over a few weeks or months). In studies exploring settings across time, time waves were commonly used and combined several types of data, particularly from interviews and observations. Groups were the least common studied entity ( n  = 9, 3.0%), so the numbers should be interpreted with caution, but continuous data collection was used in five of the nine studies. The continuous data collection mode was, for example, collecting electronic diaries [ 62 ] or minutes from committee meetings during a time period [ 63 ].

Tempo of data collection in relation to entities followed over time

Preplanned or adapted data collection

A large majority ( n  = 224, 74.9%) of the articles used preplanned data collection (e.g., in preplanned data collection, all participants were followed across time according to the same data collection plan). For example, all participants were interviewed one, six and twelve months’ post-diagnosis. In contrast to the preplanned data collection approach, 44 articles had a participant-adapted data collection (14.7%), and participants were followed at different frequencies and/or over various lengths of time depending on each participant’s situation. Participant-adapted data collection was more common among articles following individuals or individual cases (see Fig.  4 ). To adapt the data collection to the participants, the researchers created strategies to reach participants when crucial events were happening. Eleven articles used a participant entry approach to data collection ( n  = 11, 6.7%), and the whole or parts of the data were independently sent in by participants in the form of diaries, questionnaires, or blogs. Another approach to data collection was using theoretical or analysis-driven ideas to guide the data collection ( n  = 19, 6.4%). In these articles, the analysis and data collection were conducted simultaneously, and ideas arising in the analysis could be followed up, for example, returning to some participants, recruiting participants with specific experiences, or collecting complementary types of data materials. This approach was most common in the articles following settings across time, which often included observations and interviews with different types of populations. Articles using theoretical or analysis driven data collection were not associated with grounded theory to a greater extent than the other articles in the sample (e.g., did not self-identify as grounded theory or referred to methodological literature within grounded theory traditions to a greater proportion).

Preplanned or adapted data collection in relation to entities followed over time

According to our results, some researchers used QLR as a methodological approach and other researchers used a longitudinal qualitative data collection without aiming to investigate change. Adding to the debate on whether QLR is a methodological approach in its own right or a design element in a particular study we suggest that the use of QLR can be described as layered (see Fig.  5 ). Namely, articles must fulfill several criteria in order to use QLR as a methodological approach, and that is done in some articles. In those articles QLR method references were used, the aim was to investigate change of a phenomenon and the longitudinal elements of the data collection were thoroughly integrated into the method section. On the other hand, some articles using a longitudinal qualitative data collection were just collecting data over time, without addressing time and/or change in the aim. These articles can still be interesting research studies with valuable results, but they are not using the full potential of QLR as a methodological approach. In all, around 40% of the articles had an aim that focused on describing or understanding change (either as phenomenon or outcome); but only about 24% of the articles set out to investigate change across time as their phenomenon of interest.

The QLR onion. The use of QLR design can be described as layered, where researchers use more or less elements of a QLR design. The two inmost layers represents articles using QLR as a methodological approach

Regarding methodological influences, about one-third of the articles self-identify with any of the traditional qualitative methodologies. Using a longitudinal qualitative data collection as an element integrated with another methodological tradition can therefore be seen as one way of working with longitudinal qualitative materials. In our results, the articles referring to methodologies other than QLR preferably used case study, phenomenology and grounded theory methodologies. This was surprising since Neale [ 10 ] identified ethnography, case studies and narrative methods as the main methodological influences on QLR. Our findings might mirror the profound impacts that phenomenology and grounded theory have had on the qualitative field of health research. Regarding phenomenology, the findings can also be influenced by more recent discussions of combining interpretative phenomenological analysis with QLR [ 6 ].

Half of the articles self-identified as QLR studies, but QLR method references were used in less than 20% of the identified articles. This is both surprising and troublesome since use of appropriate method literature might have supported researchers who were struggling with for example a large quantity of materials and complex analysis. A possible explanation for the lack of use of QLR method literature is that QLR as a methodological approach is not well known, and authors might not be aware that method literature exists. It is quite understandable that researchers can describe a qualitative project with longitudinal data collection as a qualitative longitudinal study, without being aware that QLR is a specific form of study. Balmer [ 64 ] described how their group conducted serial interviews with medical students over several years before they became aware of QLR as a method of study. Within our networks, we have met researchers with similar experiences. Likewise, peer reviewers and editorial boards might not be accustomed to evaluating QLR manuscripts. In our results, 138 journals published one article between 2017 and 2019, and that might not be enough for editorial boards and peer reviewers to develop knowledge to enable them to closely evaluate manuscripts with a QLR method.

In 2007, Holland and colleagues [ 65 ] mapped QLR in the UK and described the following four categories of QLR: 1) mixed methods approaches with a QLR component; 2) planned prospective longitudinal studies; 3) follow-up studies complementing a previous data collection with follow-up; and 4) evaluation studies. Examples of all these categories can be found among the articles in this method study; however, our results do paint a more complex picture. According to our results, Holland’s categories are not multi-exclusive. For example, studies with intentions to evaluate or implement practices often used a mixed methods design and were therefore eligible for both categories one and four described above. Additionally, regarding the follow-up studies, it was seldom clearly described if they were planned as a two-time-point study or if researchers had gained an opportunity to follow up on previous data collection. When we tried to categorize QLR articles according to the data collection design, we could not identify multi-exclusive categories. Instead, we identified the following three components of longitudinal data collection: 1) entities followed across time; 2) tempo; and 3) preplanned or adapted data collection approaches. However, the most common combination was preplanned studies that followed individuals longitudinally with three or more time points.

The use of QLR differs between disciplines [ 14 ]. Our results show some patterns for QLR within health research. Firstly, the QLR projects were large and complex; they often included several types of populations and various data materials, and were presented in several articles. Secondly, most studies focused upon the individual perspective, following individuals across time, and using individual interviews. Thirdly, the data collection periods varied, but 53% of the articles had a data collection period of 1 year or shorter. Finally, patients were the most prevalent population, even though topics varied greatly. Previously, two other reviews that focused on QLR in different parts of health research (e.g., nursing [ 4 ] and gerontology [ 66 ]) pointed in the same direction. For example, individual interviews or a combination of data materials were commonly used, and most studies were shorter than 1 year but a wide range existed [ 4 , 66 ].

Considerations when planning a QLR project

Based on our results, we argue that when health researchers plan a QLR study, they should reflect upon their perspective of time/change and decide what part change should play in their QLR study. If researchers decide that change should play the main role in their project, then they should aim to focus on change as the phenomenon of interest. However, in some research, change might be an important part of the plot, without having the main role, and change in relation to the outcomes might be a better perspective. In such studies, participants with change, no change or different kinds of change are compared to explore possible explanations for the change. In our results, change in relation to the outcomes was often used in relation to intervention studies where participants who reached a desired outcome were compared to individuals who did not. Furthermore, for some research studies, change is part of the context in which the research takes place. This can be the case when certain experiences happen during a period of change; for example, when the aim is to explore the experience of everyday life during rehabilitation after stroke. In such cases a longitudinal data collection could be advisable (e.g., repeated interviews often give a deep relationship between interviewer and participants as well as the possibility of gaining greater depth in interview answers during follow-up interviews [ 15 ]), but the study might not be called a QLR study since it does not focus upon change [ 13 ]. We suggest that researchers make informed decisions of what kind of longitudinal perspective they set out to investigate and are transparent with their sources of methodological inspiration.

We would argue that length of data collection period, type of entities, and data materials should be in accordance with the type of change/changing processes that a study focuses on. Individual change is important in health research, but researchers should also remember the possibility of investigating changes in families, working groups, organizations and wider communities. Using these types of entities were less common in our material and could probably grant new perspectives to many research topics within health. Similarly, using several types of data materials can complement the insights that individual interviews can give. A large majority of the articles in our results had a preplanned data collection. Participant-adapted data collection can be a way to work in alignment with a “time-as-fluid” conceptualization of time because the events of subjective importance to participants can be more in focus and participants (or other entities) change processes can differ substantially across cases. In studies with lengthy and spaced-out data collection periods and/or uncertainty in trajectories, researchers should consider participant-adapted or participant entry data collection. For example, some participants can be followed for longer periods and/or with more frequency.

Finally, researchers should consider how to best publish and disseminate their results. Many QLR projects are large, and the results are divided across several articles when they are published. In our results, 21 papers self-identified as a mixed methods project or as part of a larger mixed methods project, but most of these did not include quantitative data in the article. This raises the question of how to best divide a large research project into suitable pieces for publication. It is an evident risk that the more interesting aspects of a mixed methods project are lost when the qualitative and quantitative parts are analyzed and published separately. Similar risks occur, for example, when data have been collected from several types of populations but are then presented per population type (e.g., one article with patient data and another with caregiver data). During the work with our study, we also came across studies where data were collected longitudinally, but the results were divided into publications per time point. We do not argue that these examples are always wrong, there are situations when these practices are appropriate. However, it often appears that data have been divided without much consideration. Instead, we suggest a thematic approach to dividing projects into publications, crafting the individual publications around certain ideas or themes and thus using the data that is most suitable for the particular research question. Combining several types of data and/or several populations in an analysis across time is in fact what makes QLR an interesting approach.

Strengths and limitations

This method study intended to paint a broad picture regarding how longitudinal qualitative methods are used within the health research field by investigating 299 published articles. Method research is an emerging field, currently with limited methodological guidelines [ 21 ], therefore we used scoping review method to support this study. In accordance with scoping review method we did not use quality assessment as a criterion for inclusion [ 18 , 19 , 20 ]. This can be seen as a limitation because we made conclusions based upon a set of articles with varying quality. However, we believe that learning can be achieved by looking at both good and bad examples, and innovation may appear when looking beyond established knowledge, or assessing methods from different angles. It should also be noted that the results given in percentages hold no value for what procedures that are better or more in accordance with QLR, the percentages simply state how common a particular procedure was among the articles.

As described, the included articles showed much variation in the method descriptions. As the basis for our results, we have only charted explicitly written text from the articles, which might have led to an underestimation of some results. The researchers might have had a clearer rationale than described in the reports. Issues, such as word restrictions or the journal’s scope, could also have influenced the amount of detail that was provided. Similarly, when charting how articles drew on a traditional methodology, only data from the articles that clearly stated the methodologies they used (e.g., phenomenology) were charted. In some articles, literature choices or particular research strategies could implicitly indicate that the researchers had been inspired by certain methodologies (e.g., referring to grounded theory literature and describing the use of simultaneous data collection and analysis could indicate that the researchers were influenced by grounded theory), but these were not charted as using a particular methodological tradition. We used the articles’ aims and objectives/research questions to investigate their longitudinal perspectives. However, as researchers have different writing styles, information regarding the longitudinal perspectives could have been described in surrounding text rather than in the aim, which might have led to an underestimation of the longitudinal perspectives.

The experience and diversity of the research team in our study was a strength. The nine authors on the team represent ten universities and three countries, and have extensive experience in different types of qualitative research, QLR and review methods. The different level of experiences with QLR within the team (some authors have worked with QLR in several projects and others have qualitative experience but no experience in QLR) resulted in interesting discussions that helped drive the project forward. These experiences have been useful for understanding the field.

Based on a method study of 299 articles, we can conclude that QLR in health research articles published between 2017 and 2019 often contain comprehensive complex studies with a large variation in topics. Some research was thoroughly designed to capture time/change throughout the methodology, focus and data collection, while other articles included a few elements of QLR. Longitudinal data collection included several components, such as what entities were followed across time, the tempo of data collection, and to what extent the data collection was preplanned or adapted across time. In sum, health researchers need to be considerate and make informed choices when designing QLR projects. Further research should delve deeper into what kind of research questions go well with QLR and investigate the best practice examples of presenting QLR findings.

Availability of data and materials

The datasets used and analyzed in this current study are available in supplementary file  6 .

Qualitative method references were defined as a journal article or book with a title that indicated an aim to guide researchers in qualitative research methods and/or research theories. Primary studies, theoretical works related to the articles’ research topics, protocols, and quantitative method literature were excluded. References written in a language other than English was also excluded since the authors could not evaluate their content.

QLR method references were defined as a journal article or book that 1) focused on qualitative methodological questions, 2) used terms such as ‘longitudinal’ or ‘time’ in the title so it was evident that the focus was on longitudinal qualitative research. Referring to another original QLR study was not counted as using QLR method literature.

Words were charted depending on their word stem, e.g., change, changes and changing were all charted as change.

It should be noted that here time span refers to the data collection related to each participant or case. Researchers could collect data for 2 years but follow each participant for 6 months.

Calman L, Brunton L, Molassiotis A. Developing longitudinal qualitative designs: lessons learned and recommendations for health services research. BMC Med Res Methodol. 2013;13:14.

Article   PubMed   PubMed Central   Google Scholar  

Solomon P, Nixon S, Bond V, Cameron C, Gervais N. Two approaches to longitudinal qualitative analyses in rehabilitation and disability research. Disabil Rehabil. 2020;42:3566–72.

Article   PubMed   Google Scholar  

Grossoehme D, Lipstein E. Analyzing longitudinal qualitative data: the application of trajectory and recurrent cross-sectional approaches. BMC Res Notes. 2016;9:136.

SmithBattle L, Lorenz R, Reangsing C, Palmer JL, Pitroff G. A methodological review of qualitative longitudinal research in nursing. Nurs Inq. 2018;25:e12248.

Tuthill EL, Maltby AE, DiClemente K, Pellowski JA. Longitudinal qualitative methods in health behavior and nursing research: assumptions, design, analysis and lessons learned. Int J Qual Methods. 2020;19:10.

Article   PubMed Central   Google Scholar  

McCoy LK. Longitudinal qualitative research and interpretative phenomenological analysis: philosophical connections and practical considerations. Qual Res Psychol. 2017;14:442–58.

Article   Google Scholar  

Bennett D, Kajamaa A, Johnston J. How to... Do longitudinal qualitative research. Clin Teach. 2020;17:489–92.

Plano Clark V, Anderson N, Wertz JA, Zhou Y, Schumacher K, Miaskowski C. Conceptualizing longitudinal mixed methods designs: a methodological review of health sciences research. J Mix Methods Res. 2014;23:1–23.

Google Scholar  

Thomson R, Plumridge L, Holland J. Longitudinal qualitative research: a developing methodology. Int J Soc Res Methodol. 2003;6:185–7.

Neale B. The craft of qualitative longitudinal research: thousand oaks. Sage. 2021.

Balmer DF, Varpio L, Bennett D, Teunissen PW. Longitudinal qualitative research in medical education: time to conceptualise time. Med Educ. 2021;55:1253–60.

Smith N. Cross-sectional profiling and longitudinal analysis: research notes on analysis in the longitudinal qualitative study, 'Negotiating transitions to Citizenship'. Int J Soc Res Methodol. 2003;6:273–7.

Saldaña J. Longitudinal qualitative research - analyzing change through time. Walnut Creek: AltaMira Press; 2003.

Corden A, Millar J. Time and change: a review of the qualitative longitudinal research literature for social policy. Soc Policy Soc. 2007;6:583–92.

Thorne S. Interpretive description: qualitative research for applied practice (2nd ed): Routledge; 2016.

Book   Google Scholar  

Kneck Å, Audulv Å. Analyzing variations in changes over time: development of the pattern-oriented longitudinal analysis approach. Nurs Inq. 2019;26:e12288.

Whiffin CJ, Bailey C, Ellis-Hill C, Jarrett N. Challenges and solutions during analysis in a longitudinal narrative case study. Nurse Res. 2014;21:20–62.

Arksey H, O'Malley L. Scoping studies: towards a methodological framework. Int J Soc Res Methodol. 2005;8:19–32.

Levac D, Colquhoun H, O’Brien KK. Scoping studies: advancing the methodology. Implement Sci. 2010;5:69.

Peters MDJ, Marnie C, Tricco AC, Pollock D, Munn Z, Alexander L, et al. Updated methodological guidance for the conduct of scoping reviews. JBI Evidence Implementation. 2021;19:3–10.

Mbuagbaw L, Lawson DO, Puljak L, Allison DB, Thabane L. A tutorial on methodological studies: the what, when, how and why. BMC Med Res Methodol. 2020;20:226.

Tricco AC, Lillie E, Zarin W, O’Brien KK, Colquhoun H, Levac D, et al. PRISMA extension for scoping reviews (PRISMA-ScR): checklist and explanation. Ann Intern. 2018;169:467–73.

Neale B. Adding time into the mix: stakeholder ethics in qualitative longitudinal research. Methodological Innovations Online. 2013;8:6–20.

Henderson S, Holland J, McGrellis S, Sharpe S, Thomson R. Storying qualitative longitudinal research: sequence, voice and motif. Qual Res. 2016;12:16–34.

Balmer DF, Richards BF. Longitudinal qualitative research in medical education. Perspect Med Educ. 2017;6:306–10.

Ouzzani M, Hammady H, Fedorowicz Z, Elmagarmid A. Rayyan-a web and mobile app for systematic reviews. Syst Rev. 2016;5:210.

Creswell JW. Qualitative inquiry and research design: choosing among five approaches. 3rd ed: SAGE Publications; 2012.

McIntyre H, Fraser D. 'Hands-off' breastfeeding skill development in a UK, UNICEF baby friendly initiative pre-registration midwifery programme. MIDIRS Midwifery Digest. 2018;28:98–102.

Braun V, Clarke V. Using thematic analysis in psychology. Qual Res Psychol. 2006;3:77–101.

Patton MQ. Qualitative research and evaluation methods: integrating theory and practice. Sage. 2015.

Miles M, Huberman A, Saldaña J. Qualitative data analysis: a methods sourcebook. 4th ed: Sage Publications; 2020.

Miles MB, Huberman AM. Qualitative data analysis: an expanded sourcebook (2nd ed): Sage Publications; 1994.

Smith JA, Flowers P, Larkin M. Interpretative phenomenological analysis: theory, method and research. Sage. 2009.

Hsieh HF, Shannon SE. Three approaches to qualitative content analysis. Qual Health Res. 2005;15:1277–88.

Glaser B, Strauss A. The discovery of grounded theory: strategies for qualitative research. Aldine De Gruyter. 1967.

Tong A, Sainsbury P, Craig J. Consolidated criteria for reporting qualitative research (COREQ): a 32-item checklist for interviews and focus groups. Int J Qual Health Care. 2007;19:349–57.

Murray SA, Kendall M, Carduff E, Worth A, Harris FM, Lloyd A, et al. Use of serial qualitative interviews to understand patients' evolving experiences and needs. BMJ. 2009;339:b3702.

Thomson R, Holland J. Hindsight, foresight and insight: the challenges of longitudinal qualitative research. Int J Soc Res Methodol. 2003;6:233–44.

Morrow V, Tafere Y, Chuta N, Zharkevich I. "I started working because I was hungry": the consequences of food insecurity for children's well-being in rural Ethiopia. Soc Sci Med. 2017;182:1–9.

Solomon P, O'Brien KK, Nixon S, Letts L, Baxter L, Gervais N. Qualitative longitudinal study of episodic disability experiences of older women living with HIV in Ontario, Canada. BMJ Open. 2018;8:e021507.

Coombs MA, Parker R, de Vries K. Managing risk during care transitions when approaching end of life: a qualitative study of patients’ and health care professionals’ decision making. Palliat Med. 2017;31:617–24.

Vaghefi I, Tulu B. The continued use of mobile health apps: insights from a longitudinal study. JMIR Mhealth And Uhealth. 2019;7:e12983.

Andersen IC, Thomsen TG, Bruun P, Bødtger U, Hounsgaard L. Patients' and their family members' experiences of participation in care following an acute exacerbation in chronic obstructive pulmonary disease: a phenomenological-hermeneutic study. J Clin Nurs. 2017;26:4877–89.

Albrecht TA, Keim-Malpass J, Boyiadzis M, Rosenzweig M. Psychosocial experiences of young adults diagnosed with acute leukemia during hospitalization for induction chemotherapy treatment. JHPN. 2019;21:167–73.

PubMed   Google Scholar  

Corepal R, Best P, O'Neill R, Tully MA, Edwards M, Jago R, et al. Exploring the use of a gamified intervention for encouraging physical activity in adolescents: a qualitative longitudinal study in Northern Ireland. BMJ Open. 2018;8:e019663.

PubMed   PubMed Central   Google Scholar  

Malin H, Liauw I, Damon W. Purpose and character development in early adolescence. J Youth Adolesc. 2017;46:1200–15.

Jensen AM, Pedersen BD, Olsen RB, Hounsgaard L. Medication and care in Alzheimer's patients in the acute care setting: a qualitative analysis. Dementia. 2019;18:2173–88.

SmithBattle L. Housing trajectories of teen mothers and their families over 28 years. Am J Orthop. 2019;89:258–67.

Denney-Koelsch EM, Côté-Arsenault D, Jenkins Hall W. Feeling cared for versus experiencing added burden: Parents' interactions with health-care providers in pregnancy with a lethal fetal diagnosis. Illn Crisis Loss. 2018;26:293–315.

Pyörälä E, Mäenpää S, Heinonen L, Folger D, Masalin T, Hervonen H. The art of note taking with mobile devices in medical education. BMC Med Educ. 2019;19:96.

Lindberg K, Mørk BE, Walter L. Emergent coordination and situated learning in a hybrid OR: the mixed blessing of using radiation. Soc Science Med. 2019;228:232–9.

Frost J, Wingham J, Britten N, Greaves C, Abraham C, Warren FC, et al. Home-based rehabilitation for heart failure with reduced ejection fraction: mixed methods process evaluation of the REACH-HF multicentre randomised controlled trial. BMJ Open. 2019;9:e026039.

Young JL, Werner-Lin A, Mueller R, Hoskins L, Epstein N, Greene MH. Longitudinal cancer risk management trajectories of BRCA1/2 mutation-positive reproductive-age women. J Psych Oncology. 2017;35:393–408.

Lewis M, Jones A, Hunter B. Women's experience of trust within the midwife-mother relationship. Int J Childbirth. 2017;7:40–52.

Mozaffar H, Cresswell KM, Williams R, Bates DW, Sheikh A. Exploring the roots of unintended safety threats associated with the introduction of hospital ePrescribing systems and candidate avoidance and/or mitigation strategies: a qualitative study. BMJ Qual Saf. 2017;26:722–33.

Castro A, Andrews G. Nursing lives in the blogosphere: a thematic analysis of anonymous online nursing narratives. J Adv Nurs. 2018;74:329–38.

Jensen AM, Pedersen BD, Olsen RB, Wilson RL, Hounsgaard L. "if only they could understand me!" acute hospital care experiences of patients with Alzheimer's disease. Dementia. 2018;19:2332–53.

Nash BH, Mitchell AW. Longitudinal study of changes in occupational therapy students' perspectives on frames of reference. Am J Occup Ther. 2017;71:7105230010p1–7.

Bright FAS, Kayes NM, McPherson KM, Worrall LE. Engaging people experiencing communication disability in stroke rehabilitation: a qualitative study. Int J Lang Commun Disord. 2018;53:981–94.

Superdock AK, Barfield RC, Brandon DH, Docherty SL. Exploring the vagueness of religion & spirituality in complex pediatric decision-making: a qualitative study. BMC Palliat. 2018;17:107.

Gordon L, Jindal-Snape D, Morrison J, Muldoon J, Needham G, Siebert S, et al. Multiple and multidimensional transitions from trainee to trained doctor: a qualitative longitudinal study in the UK. BMJ Open. 2017;7:e018583.

Cain CL, Frazer M, Kilaberia TR. Identity work within attempts to transform healthcare: invisible team processes. Hum Relat. 2019;72:370–96.

Klinga C, Hasson H, Andreen Sachs M, Hansson J. Understanding the dynamics of sustainable change: a 20-year case study of integrated health and social care. BMC Health Serv Res. 2018;18:400.

Balmer DF, Richards BF. Conducting qualitative research through time: how might theory be useful in longitudinal qualitative research? Adv Health Sci Educ Theory Pract. 2021;27:277–88.

Holland J. Qualitative longitudinal research: exploring ways of researching lives through time. ESRC National Centre for Research Methods Workshop; London: London South Bank University; 2007.

Nevedal AL, Ayalon L, Briller SH. A qualitative evidence synthesis review of longitudinal qualitative research in gerontology. Gerontologist. 2019;59:e791–801.

Download references

Acknowledgments

The authors wish to acknowledge Ellen Sejersted, librarian at the University of Agder, Kristiansand, Norway, who conducted the literature searches and Julia Andersson, research assistant at the Department of Nursing, Umeå University, Sweden, who supported the data management and took part in the initial screening phases of the project.

Open access funding provided by Umea University. This project was conducted within the authors’ positions and did not receive any specific funding.

Author information

Authors and affiliations.

Department of Nursing, Umeå University, Umeå, Sweden

Faculty of Health, Aarhus University, Aarhus, Denmark

Elisabeth O. C. Hall

Faculty of Health Sciences, University of Faroe Islands, Thorshavn, Faroe Islands, Denmark

Elisabeth O. C. Hall & Kristianna Lund Dam

Department of Health Care Sciences, Ersta Sköndal Bräcke University College, Stockholm, Sweden

Department of Health and Nursing Science, University of Agder, Kristiansand, Norway

Thomas Westergren & Liv Fegran

Department of Public Health, University of Stavanger, Stavanger, Norway

Thomas Westergren

Center for Clinical Research, North Denmark Regional Hospital, Hjørring, Denmark

Mona Kyndi Pedersen

Department of Clinical Medicine, Aalborg University, Aalborg, Denmark

Lovisenberg Diaconale Univeristy of College, Oslo, Norway

Hanne Aagaard

Department of Clinical Medicine-Randers Regional Hospital, Aarhus University, Aarhus, Denmark

Mette Spliid Ludvigsen

Faculty of Nursing and Health Sciences, Nord University, Bodø, Norway

You can also search for this author in PubMed   Google Scholar

Contributions

ÅA conceived the study. ÅA, EH, TW, LF, MKP, HA, and MSL designed the study. ÅA, TW, and LF were involved in literature searches together with the librarian. ÅA and EH performed the screening of the articles. All authors (ÅA, EH, TW, LF, ÅK, MKP, KLD, HA, MSL) took part in the data charting. ÅA performed the data analysis and discussed the preliminary results with the rest of the team. ÅA wrote the 1st manuscript draft, and ÅK, MSL and EH edited. All authors (ÅA, EH, TW, LF, ÅK, MKP, KLD, HA, MSL) contributed to editing the 2nd draft. MSL and LF provided overall supervision. All authors read and approved the final manuscript.

Authors’ information

All authors represent the nursing discipline, but their research topics differ. ÅA and ÅK have previously worked together with QLR method development. ÅA, EH, TW, LF, MKP, HA, KLD and MSL work together in the Nordic research group PRANSIT, focusing on nursing topics connected to transition theory using a systematic review method, preferably meta synthesis. All authors have extensive experience with qualitative research but various experience with QLR.

Corresponding author

Correspondence to Åsa Audulv .

Ethics declarations

Ethics approval and consent to participate.

Not applicable.

Consent for publication

Competing interests.

The authors declare that they have no competing interests.

Additional information

Publisher’s note.

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

Supplementary Information

Additional file 1..

PRISMA-ScR checklist.

Additional file 2.

Data base searches.

Additional file 3.

 Guidelines for data charting

Additional file 4.

List of excluded articles

Additional file 5.

Table of included articles (author(s), year of publication, reference, country, aims and research questions, methodology, type of data material, length of data collection period, number of participants)

Additional file 6.

Rights and permissions.

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

Reprints and permissions

About this article

Cite this article.

Audulv, Å., Hall, E.O.C., Kneck, Å. et al. Qualitative longitudinal research in health research: a method study. BMC Med Res Methodol 22 , 255 (2022). https://doi.org/10.1186/s12874-022-01732-4

Download citation

Received : 13 January 2022

Accepted : 22 September 2022

Published : 01 October 2022

DOI : https://doi.org/10.1186/s12874-022-01732-4

Share this article

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

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

Provided by the Springer Nature SharedIt content-sharing initiative

• Qualitative longitudinal research
• Method development
• Repeated data collection

BMC Medical Research Methodology

ISSN: 1471-2288

• General enquiries: [email protected]

• Skip to main content
• Skip to primary sidebar
• Skip to footer
• QuestionPro

• Solutions Industries Gaming Automotive Sports and events Education Government Travel & Hospitality Financial Services Healthcare Cannabis Technology Use Case NPS+ Communities Audience Contactless surveys Mobile LivePolls Member Experience GDPR Positive People Science 360 Feedback Surveys
• Resources Blog eBooks Survey Templates Case Studies Training Help center

Home Market Research

What is a Longitudinal Study?: Definition and Explanation

In this article, we’ll cover all you need to know about longitudinal research. 

Let’s take a closer look at the defining characteristics of longitudinal studies, review the pros and cons of this type of research, and share some useful longitudinal study examples. 

Content Index

What is a longitudinal study?

Types of longitudinal studies, advantages and disadvantages of conducting longitudinal surveys.

• Longitudinal studies vs. cross-sectional studies

Types of surveys that use a longitudinal study

Longitudinal study examples.

A longitudinal study is a research conducted over an extended period of time. It is mostly used in medical research and other areas like psychology or sociology. 

When using this method, a longitudinal survey can pay off with actionable insights when you have the time to engage in a long-term research project.

Longitudinal studies often use surveys to collect data that is either qualitative or quantitative. Additionally, in a longitudinal study, a survey creator does not interfere with survey participants. Instead, the survey creator distributes questionnaires over time to observe changes in participants, behaviors, or attitudes. 

Many medical studies are longitudinal; researchers note and collect data from the same subjects over what can be many years.

LEARN ABOUT:   Action Research

Longitudinal studies are versatile, repeatable, and able to account for quantitative and qualitative data . Consider the three major types of longitudinal studies for future research:

Panel study: A panel survey involves a sample of people from a more significant population and is conducted at specified intervals for a more extended period. 

One of the panel study’s essential features is that researchers collect data from the same sample at different points in time. Most panel studies are designed for quantitative analysis , though they may also be used to collect qualitative data and unit of analysis .

LEARN ABOUT: Level of Analysis

Cohort Study: A cohort study samples a cohort (a group of people who typically experience the same event at a given point in time). Medical researchers tend to conduct cohort studies. Some might consider clinical trials similar to cohort studies. 

In cohort studies, researchers merely observe participants without intervention, unlike clinical trials in which participants undergo tests.

Retrospective study: A retrospective study uses already existing data, collected during previously conducted research with similar methodology and variables. 

While doing a retrospective study, the researcher uses an administrative database, pre-existing medical records, or one-to-one interviews.

As we’ve demonstrated, a longitudinal study is useful in science, medicine, and many other fields. There are many reasons why a researcher might want to conduct a longitudinal study. One of the essential reasons is, longitudinal studies give unique insights that many other types of research fail to provide. 

Advantages of longitudinal studies

• Greater validation: For a long-term study to be successful, objectives and rules must be established from the beginning. As it is a long-term study, its authenticity is verified in advance, which makes the results have a high level of validity.
• Unique data: Most research studies collect short-term data to determine the cause and effect of what is being investigated. Longitudinal surveys follow the same principles but the data collection period is different. Long-term relationships cannot be discovered in a short-term investigation, but short-term relationships can be monitored in a long-term investigation.
• Allow identifying trends: Whether in medicine, psychology, or sociology, the long-term design of a longitudinal study enables trends and relationships to be found within the data collected in real time. The previous data can be applied to know future results and have great discoveries.
• Longitudinal surveys are flexible: Although a longitudinal study can be created to study a specific data point, the data collected can show unforeseen patterns or relationships that can be significant. Because this is a long-term study, the researchers have a flexibility that is not possible with other research formats.

Additional data points can be collected to study unexpected findings, allowing changes to be made to the survey based on the approach that is detected.

Disadvantages of longitudinal studies

• Research time The main disadvantage of longitudinal surveys is that long-term research is more likely to give unpredictable results. For example, if the same person is not found to update the study, the research cannot be carried out. It may also take several years before the data begins to produce observable patterns or relationships that can be monitored.
• An unpredictability factor is always present It must be taken into account that the initial sample can be lost over time. Because longitudinal studies involve the same subjects over a long period of time, what happens to them outside of data collection times can influence the data that is collected in the future. Some people may decide to stop participating in the research. Others may not be in the correct demographics for research. If these factors are not included in the initial research design, they could affect the findings that are generated.
• Large samples are needed for the investigation to be meaningful To develop relationships or patterns, a large amount of data must be collected and extracted to generate results.
• Higher costs Without a doubt, the longitudinal survey is more complex and expensive. Being a long-term form of research, the costs of the study will span years or decades, compared to other forms of research that can be completed in a smaller fraction of the time.

Longitudinal studies vs. Cross-sectional studies

Longitudinal studies are often confused with cross-sectional studies. Unlike longitudinal studies, where the research variables can change during a study, a cross-sectional study observes a single instance with all variables remaining the same throughout the study. A longitudinal study may follow up on a cross-sectional study to investigate the relationship between the variables more thoroughly.

The design of the study is highly dependent on the nature of the research questions . Whenever a researcher decides to collect data by surveying their participants, what matters most are the questions that are asked in the survey.

Knowing what information a study should gather is the first step in determining how to conduct the rest of the study. 

With a longitudinal study, you can measure and compare various business and branding aspects by deploying surveys. Some of the classic examples of surveys that researchers can use for longitudinal studies are:

Market trends and brand awareness: Use a market research survey and marketing survey to identify market trends and develop brand awareness. Through these surveys, businesses or organizations can learn what customers want and what they will discard. This study can be carried over time to assess market trends repeatedly, as they are volatile and tend to change constantly.

Product feedback: If a business or brand launches a new product and wants to know how it is faring with consumers, product feedback surveys are a great option. Collect feedback from customers about the product over an extended time. Once you’ve collected the data, it’s time to put that feedback into practice and improve your offerings.

Customer satisfaction: Customer satisfaction surveys help an organization get to know the level of satisfaction or dissatisfaction among its customers. A longitudinal survey can gain feedback from new and regular customers for as long as you’d like to collect it, so it’s useful whether you’re starting a business or hoping to make some improvements to an established brand.

Employee engagement: When you check in regularly over time with a longitudinal survey, you’ll get a big-picture perspective of your company culture. Find out whether employees feel comfortable collaborating with colleagues and gauge their level of motivation at work.

Now that you know the basics of how researchers use longitudinal studies across several disciplines let’s review the following examples:

Example 1: Identical twins

Consider a study conducted to understand the similarities or differences between identical twins who are brought up together versus identical twins who were not. The study observes several variables, but the constant is that all the participants have identical twins.

In this case, researchers would want to observe these participants from childhood to adulthood, to understand how growing up in different environments influences traits, habits, and personality.

LEARN MORE ABOUT: Personality Survey

Over many years, researchers can see both sets of twins as they experience life without intervention. Because the participants share the same genes, it is assumed that any differences are due to environmental analysis , but only an attentive study can conclude those assumptions.

Example 2: Violence and video games

A group of researchers is studying whether there is a link between violence and video game usage. They collect a large sample of participants for the study. To reduce the amount of interference with their natural habits, these individuals come from a population that already plays video games. The age group is focused on teenagers (13-19 years old).

The researchers record how prone to violence participants in the sample are at the onset. It creates a baseline for later comparisons. Now the researchers will give a log to each participant to keep track of how much and how frequently they play and how much time they spend playing video games. This study can go on for months or years. During this time, the researcher can compare video game-playing behaviors with violent tendencies. Thus, investigating whether there is a link between violence and video games.

Conducting a longitudinal study with surveys is straightforward and applicable to almost any discipline. With our survey software you can easily start your own survey today. 

GET STARTED

MORE LIKE THIS

NPS Survey Platform: Types, Tips, 11 Best Platforms & Tools

Apr 26, 2024

User Journey vs User Flow: Differences and Similarities

Best 7 Gap Analysis Tools to Empower Your Business

Apr 25, 2024

12 Best Employee Survey Tools for Organizational Excellence

Other categories.

• Academic Research
• Artificial Intelligence
• Assessments
• Brand Awareness
• Case Studies
• Communities
• Consumer Insights
• Customer effort score
• Customer Engagement
• Customer Experience
• Customer Loyalty
• Customer Research
• Customer Satisfaction
• Employee Benefits
• Employee Engagement
• Employee Retention
• Friday Five
• General Data Protection Regulation
• Insights Hub
• Life@QuestionPro
• Market Research
• Mobile diaries
• Mobile Surveys
• New Features
• Online Communities
• Question Types
• Questionnaire
• QuestionPro Products
• Release Notes
• Research Tools and Apps
• Revenue at Risk
• Survey Templates
• Training Tips
• Uncategorized
• Video Learning Series
• What’s Coming Up
• Workforce Intelligence

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

What Is a Longitudinal Study?

Tracking Variables Over Time

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

Amanda Tust is a fact-checker, researcher, and writer with a Master of Science in Journalism from Northwestern University's Medill School of Journalism.

Steve McAlister / The Image Bank / Getty Images

The Typical Longitudinal Study

Potential pitfalls, frequently asked questions.

A longitudinal study follows what happens to selected variables over an extended time. Psychologists use the longitudinal study design to explore possible relationships among variables in the same group of individuals over an extended period.

Once researchers have determined the study's scope, participants, and procedures, most longitudinal studies begin with baseline data collection. In the days, months, years, or even decades that follow, they continually gather more information so they can observe how variables change over time relative to the baseline.

For example, imagine that researchers are interested in the mental health benefits of exercise in middle age and how exercise affects cognitive health as people age. The researchers hypothesize that people who are more physically fit in their 40s and 50s will be less likely to experience cognitive declines in their 70s and 80s.

Longitudinal vs. Cross-Sectional Studies

Longitudinal studies, a type of correlational research , are usually observational, in contrast with cross-sectional research . Longitudinal research involves collecting data over an extended time, whereas cross-sectional research involves collecting data at a single point.

To test this hypothesis, the researchers recruit participants who are in their mid-40s to early 50s. They collect data related to current physical fitness, exercise habits, and performance on cognitive function tests. The researchers continue to track activity levels and test results for a certain number of years, look for trends in and relationships among the studied variables, and test the data against their hypothesis to form a conclusion.

Examples of Early Longitudinal Study Design

Examples of longitudinal studies extend back to the 17th century, when King Louis XIV periodically gathered information from his Canadian subjects, including their ages, marital statuses, occupations, and assets such as livestock and land. He used the data to spot trends over the years and understand his colonies' health and economic viability.

In the 18th century, Count Philibert Gueneau de Montbeillard conducted the first recorded longitudinal study when he measured his son every six months and published the information in "Histoire Naturelle."

The Genetic Studies of Genius (also known as the Terman Study of the Gifted), which began in 1921, is one of the first studies to follow participants from childhood into adulthood. Psychologist Lewis Terman's goal was to examine the similarities among gifted children and disprove the common assumption at the time that gifted children were "socially inept."

Types of Longitudinal Studies

Longitudinal studies fall into three main categories.

• Panel study : Sampling of a cross-section of individuals
• Cohort study : Sampling of a group based on a specific event, such as birth, geographic location, or experience
• Retrospective study : Review of historical information such as medical records

Benefits of Longitudinal Research

A longitudinal study can provide valuable insight that other studies can't. They're particularly useful when studying developmental and lifespan issues because they allow glimpses into changes and possible reasons for them.

For example, some longitudinal studies have explored differences and similarities among identical twins, some reared together and some apart. In these types of studies, researchers tracked participants from childhood into adulthood to see how environment influences personality , achievement, and other areas.

Because the participants share the same genetics , researchers chalked up any differences to environmental factors . Researchers can then look at what the participants have in common and where they differ to see which characteristics are more strongly influenced by either genetics or experience. Note that adoption agencies no longer separate twins, so such studies are unlikely today. Longitudinal studies on twins have shifted to those within the same household.

As with other types of psychology research, researchers must take into account some common challenges when considering, designing, and performing a longitudinal study.

Longitudinal studies require time and are often quite expensive. Because of this, these studies often have only a small group of subjects, which makes it difficult to apply the results to a larger population.

Selective Attrition

Participants sometimes drop out of a study for any number of reasons, like moving away from the area, illness, or simply losing motivation . This tendency, known as selective attrition , shrinks the sample size and decreases the amount of data collected.

If the final group no longer reflects the original representative sample , attrition can threaten the validity of the experiment. Validity refers to whether or not a test or experiment accurately measures what it claims to measure. If the final group of participants doesn't represent the larger group accurately, generalizing the study's conclusions is difficult.

The World’s Longest-Running Longitudinal Study

Lewis Terman aimed to investigate how highly intelligent children develop into adulthood with his "Genetic Studies of Genius." Results from this study were still being compiled into the 2000s. However, Terman was a proponent of eugenics and has been accused of letting his own sexism , racism , and economic prejudice influence his study and of drawing major conclusions from weak evidence. However, Terman's study remains influential in longitudinal studies. For example, a recent study found new information on the original Terman sample, which indicated that men who skipped a grade as children went on to have higher incomes than those who didn't.

A Word From Verywell

Longitudinal studies can provide a wealth of valuable information that would be difficult to gather any other way. Despite the typical expense and time involved, longitudinal studies from the past continue to influence and inspire researchers and students today.

A longitudinal study follows up with the same sample (i.e., group of people) over time, whereas a cross-sectional study examines one sample at a single point in time, like a snapshot.

A longitudinal study can occur over any length of time, from a few weeks to a few decades or even longer.

That depends on what researchers are investigating. A researcher can measure data on just one participant or thousands over time. The larger the sample size, of course, the more likely the study is to yield results that can be extrapolated.

Piccinin AM, Knight JE. History of longitudinal studies of psychological aging . Encyclopedia of Geropsychology. 2017:1103-1109. doi:10.1007/978-981-287-082-7_103

Terman L. Study of the gifted . In: The SAGE Encyclopedia of Educational Research, Measurement, and Evaluation. 2018. doi:10.4135/9781506326139.n691

Sahu M, Prasuna JG. Twin studies: A unique epidemiological tool .  Indian J Community Med . 2016;41(3):177-182. doi:10.4103/0970-0218.183593

Almqvist C, Lichtenstein P. Pediatric twin studies . In:  Twin Research for Everyone . Elsevier; 2022:431-438.

Warne RT. An evaluation (and vindication?) of Lewis Terman: What the father of gifted education can teach the 21st century . Gifted Child Q. 2018;63(1):3-21. doi:10.1177/0016986218799433

Warne RT, Liu JK. Income differences among grade skippers and non-grade skippers across genders in the Terman sample, 1936–1976 . Learning and Instruction. 2017;47:1-12. doi:10.1016/j.learninstruc.2016.10.004

Wang X, Cheng Z. Cross-sectional studies: Strengths, weaknesses, and recommendations .  Chest . 2020;158(1S):S65-S71. doi:10.1016/j.chest.2020.03.012

Caruana EJ, Roman M, Hernández-Sánchez J, Solli P. Longitudinal studies .  J Thorac Dis . 2015;7(11):E537-E540. doi:10.3978/j.issn.2072-1439.2015.10.63

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

Longitudinal Case Study Research to Study Self-Regulation of Professional Learning: Combining Observations and Stimulated Recall Interviews Throughout Everyday Work

• First Online: 31 August 2022

Cite this chapter

• Katrien Cuyvers 8 , 9 ,
• Piet Van den Bossche 10 , 11 &
• Vincent Donche 12  

Part of the book series: Professional and Practice-based Learning ((PPBL,volume 33))

1318 Accesses

3 Citations

Professional learning reflects critical processes of change whereby one modifies and extends prior competencies while performing one’s job. Over the past two decades, the need has emerged and grown for insights on how employees take responsibility for their own learning and engage in self-regulation of professional learning. However, the process of measuring professional learning as well as self-regulation of professional learning during everyday work has raised difficult methodological problems for various reasons. The retrospective, cross-sectional, self-report measurement techniques often used, tend to de-contextualise learning from the complex environments in which professionals operate. Under such techniques, study participants are asked to make abstractions of this complexity to self-report regarding possibly implicit, multifaceted competencies and metacognitive strategy use as features of self-regulated learning. In this chapter, we offer an alternative approach via a longitudinal multiple case study design combining long-term observations with immediate consecutive stimulated recall interviews, towards building a more dynamic and situated understanding of professional learning through which to explore participants’ self-regulation. Using both ‘on-line’ and ‘off-line’ measurement techniques, the proposed interactive approach was empirically applied to investigate self-regulation of professional learning in medical practice. Without pretentiously suggesting that this is the ultimate research solution, we aim to outline the approach, its opportunities and challenges, how to tackle these challenges, and how the approach’s research insights could function to advance theory-building on professional learning in general—and self-regulation of professional learning in particular—in everyday work.

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

Access this chapter

• Available as PDF
• Read on any device
• Instant download
• Own it forever
• Available as EPUB and PDF
• Compact, lightweight edition
• Dispatched in 3 to 5 business days
• Free shipping worldwide - see info
• Durable hardcover edition

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

Angrosino, M., & Rosenberg, J. (2011). Observations on observations, continuities and challenges. In N. K. Denzin & Y. S. Lincoln (Eds), The SAGE handbook of qualitative research (4th ed., pp. 467–478). Sage publications, Inc.

Google Scholar  

Azevedo, R., Moos, D. C., Johnson, A. M., & Chauncey, A. D. (2010). Measuring cognitive and metacognitive regulatory processes during hypermedia learning: Issues and challenges. Educational Psychologist, 45 (4), 210–223.

Article   Google Scholar  

Azevedo, R., Taub, M., & Mudrick, N. V. (2018). Understanding and reasoning about real-time cognitive, affective, and metacognitive processes to foster self-regulation with advanced learning technologies. In D. H. Schunk & J. A. Greene (Eds.), Handbook of self-regulation of learning and performance (2nd ed., pp. 254–270). Routledge.

Bakeman, R. (2000). Behavioral observation and coding. In H. T. Reis & C. M. Judd (Eds.), Handbook of research methods in social and personality psychology (pp. 138–159). Cambridge University Press.

Bernacki, M. L. (2018). Examining the cyclical, loosely sequenced, and contingent features of self-regulated learning: The promise of in-depth case study methodologies. In D. H. Schunk & J. A. Greene (Eds.), Handbook of self-regulation of learning and performance (2nd ed., pp. 370–387). Routledge.

Bransen, D., Govaerts, M. J. B., Sluijsmans, D. M. A., & Driessen, E. W. (2020). Beyond the self: The role of co-regulation in medical students’ self-regulated learning. Medical Education, 54 (3), 234–241.

Bratich, J. (2018). Observations in a surveilled world. In N. K. Denzin & Y. S. Lincoln (Eds.), The sage handbook of qualitative research (5th ed., pp. 526–545). SAGE.

Brydges, R., Tran, J., Goffi, A., Lee, C., Miller, D., & Mylopoulos, M. (2020). Resident learning trajectories in the workplace: A self-regulated learning analysis. Medical Education, 54 , 1120–1128. https://doi.org/10.1111/medu.14288

Cresswell, J. W., & Miller, D. L. (2000). Determining validity in qualitative inquiry. Theory Into Practice, 39 (3), 124–130. https://doi.org/10.1207/s15430421tip3903_2

Cuyvers, K. (2019). Unravelling medical specialists’ self-regulated learning in the clinical environment . Academic dissertation. University of Antwerp.

Cuyvers, K., Donche, V., & Van den Bossche, P. (2016). Learning beyond graduation: Exploring newly qualified medical specialists’ entrance into daily practice from a learning perspective. Advances in Health Sciences Education, 21 (2), 439–453.

Cuyvers, K., Van den Bossche, P., & Donche, V. (2020). Self-regulation of professional learning in the workplace: A state of the art and future perspectives. Vocations and Learning, 13 , 281–312. https://doi.org/10.1007/s12186-019-09236-x

Cuyvers, K., Donche, V., & Van den Bossche, P. (2021). Unravelling the process of self-regulated learning of medical specialists in the clinical environment. Journal of Workplace Learning, 33 (5), 375–400. https://doi.org/10.1108/JWL-09-2020-0151

Ellström, P.-E. (2001). Integrating learning and work: Problems and prospects. Human Resource Development Quarterly, 12 (4), 421–435. https://doi.org/10.1002/hrdq.1006

Endedijk, M. D., & Cuyvers, K. (2021). Self-regulation of professional learning: Towards a new era of research. In C. Harteis, D. Gijbels, & E. Kyndt (Eds.), Research approaches on workplace learning: Arising perspectives and retrospective . Springer.

Endedijk, M. D., Brekelmans, M., Sleegers, P., & Vermunt, J. D. (2016). Measuring students’ self-regulated learning in professional education: Bridging the gap between event and aptitude measurements. Quality & Quantity, 50 , 2141–2164. https://doi.org/10.1007/s11135-015-0255-4

Eraut, M. (2000). Non-formal learning and tacit knowledge in professional work. British Journal of Educational Psychology, 70 , 113–136.

Eraut, M. (2004). Informal learning in the workplace. Studies in Continuing Education, 26 (2), 247–273.

Eraut, M. (2007). Learning from other people in the workplace. Oxford Review of Education, 33 (4), 403–422. https://doi.org/10.1080/03054980701425706

Eraut, M., Alderton, J., Cole, G., & Senker, P. (1998). Learning from other people at work. In F. Coffield (Ed.), Learning at work (pp. 37–48). Policy Press.

Ericsson, K. A., & Simon, H. A. (1993). Protocol analysis. Verbal reports as data . Massachusetts Institute of Technology.

Book   Google Scholar  

Ezzy, D. (2013). Qualitative analysis: Practice and innovation . Routledge.

Furner, J., & Steadman, S. (2004). Eliciting professional practical knowledge: Experiences and problems. Conference paper, British Educational Research Association Annual Conference , University of Manchester, 16–18 September. Assessed 2 Mar 2018 from http://www.leeds.ac.uk/educol/documents/00003884.htm

Gobo, G., & Marciniak, L. T. (2011). What is ethnography? In D. Silverman (Ed.), Qualitative research 4E (3rd ed., pp. 103–120). SAGE.

Graneheim, U. H., & Lundman, B. (2004). Qualitative content analysis in nursing research: Concepts, procedures and measures to achieve trustworthiness. Nurse Education Today, 24 , 105–112. https://doi.org/10.1016/j.nedt.2003.10.001

Guillemin, M., & Gillam, L. (2004). Ethics, reflexivity, and “ethically important moments” in research. Qualitative Inquiry, 10 (2), 261–280.

Henderson, L., & Tallman, J. (2006). Stimulated recall and mental models, tools for teaching and learning computer information literacy . The Sacrecrow Press.

Jossberger, H. (2022). Eye tracking in professional learning and development: Uncovering expertise development among residents in radiology. In M. Goller, E. Kyndt, S. Paloniemi, & C. Damşa (Eds.), Methods for researching professional learning and development: Challenges, applications, and empirical illustrations (pp. 467–489). Springer.

Lincoln, Y. S., & Guba, E. G. (1985). Naturalistic inquiry . SAGE.

Littlejohn, A., Milligan, C., Fontana, P. R., & Margaryan, A. (2016). Professional learning through everyday work: How finance professionals self-regulate their learning. Vocations and Learning, 9 , 207–226. https://doi.org/10.1007/s12186-015-9144-1

Moorman, R. H., & Podsakoff, P. M. (1992). A meta-analytic review and empirical test of the potential confounding effects of social desirability response sets in organizational behavior research. Journal of Occupational and Organizational Psychology, 65 (2), 131–149.

Morse, J. (2018). Reframing rigor in qualitative inquiry. In N. K. Denzin & Y. S. Lincoln (Eds.), The sage handbook of qualitative research (5th ed., pp. 796–817). SAGE.

Noble, H., & Heale, R. (2019). Triangulation in research, with examples. Evidence Based Nursing, 22 (3), 67–68. https://doi.org/10.1136/ebnurs-2019-103145

Rausch, A. (2014). Using diaries in research on work and learning. In C. Harteis, A. Rausch, & J. Seifried (Eds.), Discourses on professional learning: On the boundary between learning and working (pp. 341–366). Springer. https://doi.org/10.1007/978-94-007-7012-6_17

Chapter   Google Scholar  

Rausch, A., Goller, M., & Steffen, B. (2022). Uncovering informal workplace learning by using diaries. In M. Goller, E. Kyndt, S. Paloniemi, & C. Damşa (Eds.), Methods for researching professional learning and development: Challenges, applications, and empirical illustrations (pp. 43–70). Springer.

Roulet, T. J., Gill, M. J., Stenger, S., & Gill, D. J. (2017). Reconsidering the value of covert research: The role of ambiguous consent in participant observation. Organizational Research Methods, 20 (3), 487–517.

Schunk, D. H., & Greene, J. A. (2018). Historical, contemporary, and future perspectives on self-regulated learning and performance. In D. H. Schunk & J. A. Greene (Eds.), Handbook of self-regulation of learning and performance (2nd ed., pp. 1–17). Routledge.

Sitzmann, T., & Ely, K. (2011). A meta-analysis of self-regulated learning in work-related training and educational attainment: What we know and where we need to go. Psychological Bulletin, 137 (3), 421–442.

Spliethoff, L., & Abele, S. (2022). Measuring professional competence using computer-generated log data. In M. Goller, E. Kyndt, S. Paloniemi, & C. Damşa (Eds.), Methods for researching professional learning and development: Challenges, applications, and empirical illustrations (pp. 165–186). Springer.

Stake, R. E. (1995). The art of case study research . SAGE.

Tynjälä, P. (2008). Perspectives into learning at the workplace. Educational Research Review, 3 (2), 130–154.

Tynjälä, P. (2013). Toward a 3-P model of workplace learning: A literature review. Vocations and Learning, 6 , 11–36. https://doi.org/10.1007/s12186-012-9091-z

Van Eekelen, I. M., Boshuizen, H. P. A., & Vermunt, J. D. (2005). Self-regulation in higher education teacher learning. Higher Education, 50 , 447–471. https://doi.org/10.1007/s10734-004-6362-0

Veenman, M. V. J. (2005). The assessment of metacognitive skills: What can be learned from multi-method designs. In C. Artelt & B. Moschner (Eds.), Lernstrategien und metacognition, implikationen für forschung und praxis (pp. 77–100). Waxmann Verlag GmbH.

Veenman, M. V. J. (2007). Learning to self-monitor and self-regulate. In P. Alexander & R. E. Mayer (Eds.), Handbook of research on learning and instruction, educational psychology handbook series (pp. 197–218). Routledge.

Veenman, M. V. J. (2011). Alternative assessment of strategy-use with self-report instruments: A discussion. Metacognition and Learning, 6 , 205–211.

Veenman, M. V. J., Van Hout-Wolters, B. H. A. M., & Afflerbach, P. (2006). Metacognition and learning: Conceptual and methodological considerations. Metacognition and Learning, 1 , 3–14.

Vrieling-Teunter, E., Stijnen, S., & Bastiaens, T. (2021). Promoting student teachers’ self-regulated learning in the workplace. Vocations and Learning, 14 , 223–242. https://doi.org/10.1007/s12186-021-09264-6

Winne, P. H. (2010). Improving measurements of self-regulated learning. Educational Psychologist, 45 (4), 267–276. https://doi.org/10.1080/00461520.2010.517150

Wolters, C. A., & Won, S. (2018). Validity and the use of self-report questionnaires to assess self-regulated learning. In D. H. Schunk & J. A. Greene (Eds.), Handbook of self-regulation of learning and performance (2nd ed., pp. 307–322). Routledge.

Wolters, C. A., Benzon, M. B., & Arroyo-Giner, C. (2011). Assessing strategies for the self-regulation of motivation. In B. J. Zimmerman & D. A. Schunk (Eds.), Handbook of self-regulation of learning and performance (pp. 298–312). Routledge.

Yin, R. K. (1999). Enhancing the quality of case studies in health services research. Health Services Research, 34 (5), 1209–1224.

Yin, R. K. (2014). Case study research: Design and methods . SAGE.

Yin, R. K. (2018). Case study research and applications, design and methods (6th ed.). SAGE.

Download references

Author information

Authors and affiliations.

Faculty of Social Sciences, Department of Training and Education Sciences and Antwerp School of Education, University of Antwerp, Antwerp, Belgium

Katrien Cuyvers

Faculty of Behavioural, Management and Social Sciences, Department of Educational Science, University of Twente, Enschede, The Netherlands

Department of Educational Research and Development, School of Business and Economics, Maastricht University, Maastricht, The Netherlands

Piet Van den Bossche

Faculty of Social Sciences, University of Antwerp, Antwerp, Belgium

Faculty of Social Sciences, Department of Training and Education Sciences, University of Antwerp, Antwerp, Belgium

Vincent Donche

You can also search for this author in PubMed   Google Scholar

Corresponding author

Correspondence to Katrien Cuyvers .

Editor information

Editors and affiliations.

Institute of Educational Science, Paderborn University, Paderborn, Germany

Michael Goller

Centre for Transformative Innovation, Swinburne University of Technology, Melbourne, VIC, Australia

Department of Education, University of Jyväskylä, Jyväskylä, Finland

Susanna Paloniemi

Department of Education, University of Oslo, Blindern, Oslo, Norway

Crina Damşa

Rights and permissions

Reprints and permissions

Copyright information

© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG

About this chapter

Cuyvers, K., Van den Bossche, P., Donche, V. (2022). Longitudinal Case Study Research to Study Self-Regulation of Professional Learning: Combining Observations and Stimulated Recall Interviews Throughout Everyday Work. In: Goller, M., Kyndt, E., Paloniemi, S., Damşa, C. (eds) Methods for Researching Professional Learning and Development. Professional and Practice-based Learning, vol 33. Springer, Cham. https://doi.org/10.1007/978-3-031-08518-5_26

Download citation

DOI : https://doi.org/10.1007/978-3-031-08518-5_26

Published : 31 August 2022

Publisher Name : Springer, Cham

Print ISBN : 978-3-031-08517-8

Online ISBN : 978-3-031-08518-5

eBook Packages : Education Education (R0)

Share this chapter

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

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

Provided by the Springer Nature SharedIt content-sharing initiative

• Publish with us

Policies and ethics

• Find a journal
• Track your research

An official website of the United States government

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

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

• Publications
• Account settings
• Browse Titles

NCBI Bookshelf. A service of the National Library of Medicine, National Institutes of Health.

Hagen S, Bugge C, Dean SG, et al. Basic versus biofeedback-mediated intensive pelvic floor muscle training for women with urinary incontinence: the OPAL RCT. Southampton (UK): NIHR Journals Library; 2020 Dec. (Health Technology Assessment, No. 24.70.)

Basic versus biofeedback-mediated intensive pelvic floor muscle training for women with urinary incontinence: the OPAL RCT.

Chapter 6 longitudinal qualitative case study.

• Introduction

This chapter reports the methods and findings from the longitudinal qualitative case study. In line with contemporary process evaluation guidance, this is an in-depth, pre-planned and theoretically driven longitudinal, comparative, qualitative case study to support understanding of two complex interventions that aim to reduce UI in women. 53 In this chapter, we refer to the interview participants as women, in recognition of the fact that this chapter is based on women’s interview accounts (rather than using the term ‘participants’ as elsewhere in the report).

In this chapter, the longitudinal qualitative comparative case study will be referred to as the case study. Given the link between this study and the main OPAL trial, the same conventions in terms of referral to group allocation will be adhered to: specifically, when referring to the basic PFMT group we are referring to women allocated to basic PFMT group (ITT), whether or not the women adhered to treatment or crossed over treatment group; similarly, when referring to the biofeedback PFMT group, we are referring to women allocated to the biofeedback PFMT group.

When quotations are presented, they are followed by the case number of the woman, the interview (0M for baseline, 6M for 6 months, 12M for 12 months and 24M for 24 months) and the woman’s group allocation.

This chapter addresses one aim from the OPAL trial, namely to:

• investigate women’s experiences of the interventions, identify the barriers and facilitators that affect adherence in the short and long term, to explain the process through which they influence adherence and to identify whether or not these differ between randomised groups.

A longitudinal, qualitative, two-tailed case study design 60 was employed, in which the tails were the biofeedback PFMT and basic PFMT trial groups. A detailed protocol has been published. 21 A sample of women from both groups took part in semistructured interviews. The two-tailed case study design complemented the trial design in its comparative focus, with the analysis set up to explore group differences. In this chapter, we will hereafter refer to groups rather than tails, in line with the terminology used in the trial. Case study design supports robust group comparison in a qualitative way; 61 therefore, conclusions of similarity and difference should be read as qualitative comparison as opposed to quantitative (statistical) comparison.

Sampling and recruitment

Forty randomised women (20 in each group) were purposively sampled for variance in centre type, women’s type of UI and therapist type. Each recruited woman was one case. Women were asked to consent to the case study specifically (having already consented to take part in the trial). The women were given an additional invitation letter [see the project web page: www.journalslibrary.nihr.ac.uk/programmes/hta/117103/#/ (accessed 29 July 2019)] and patient information leaflet [see the project web page: www.journalslibrary.nihr.ac.uk/programmes/hta/117103/#/ (accessed 29 July 2019)]. Women who remained interested were contacted by telephone approximately 1 week later to ask if they would like to participate. Written consent was obtained at the time of the first interview [see the project web page: www.journalslibrary.nihr.ac.uk/programmes/hta/117103/#/ (accessed 29 July 2019)].

Case study data collection

Data were collected by a series of semistructured interviews [see the project web page: www.journalslibrary.nihr.ac.uk/programmes/hta/117103/#/ (accessed 29 July 2019)]. Each interview had a specific focus:

• Baseline pre-treatment interviews (face to face) explored the woman’s experience of UI, the social contexts within which she experienced UI and her expectations of treatment.
• A 6-month post-treatment interview (face to face) explored the woman’s experience of the trial intervention, her adherence to therapy appointments and the prescribed programme, factors that affected that adherence and her perceptions of treatment outcome.
• 12- and 24-month interviews (telephone) explored, at each time point, the woman’s experience of UI post intervention, the intervention, factors that influence ongoing PFMT adherence and treatment outcome.

Interview data were, with consent, collected using a password-protected audio digital recorder. Interview audio-recordings were anonymised, transcribed verbatim and entered into NVivo software to support analysis.

Case study data analysis

Analysis was guided by the OPAL trial protocol [see the project web page: www.journalslibrary.nihr.ac.uk/programmes/hta/117103/#/ (accessed 29 July 2019)] and the OPAL qualitative study and process evaluation analysis plan [see the project web page: www.journalslibrary.nihr.ac.uk/programmes/hta/117103/#/ (accessed 29 July 2019)]. Three different researchers have worked on the OPAL case study (Anne Taylor, Aileen Grant and Marija Kovandzic), alongside the responsible grant holders (Carol Bugge, Jean Hay-Smith and Sarah Dean). By the nature of qualitative analysis, each analyst had a different approach to data analysis. This was encouraged by the grant holders, within the confines of the protocol, to maximise the insights into the data. Sources that were drawn on to support that analysis included Yin, 60 , 61 Alvesson and Sköldberg, 62 Grant et al ., 63 Kovandžić et al ., 64 Stake 65 and Ritchie et al . 66

Overall, analysis was iterative with data collection. Analysis occurred on four interacting levels to facilitate within- and cross-case comparisons.

At the level of the individual interview

An initial a priori coding scheme was developed and initially applied, focusing on core areas of interest: UI experience, PFMT ± biofeedback experience, factors that influenced adherence in the short and long term and perceptions of treatment outcome. The coding was developed through team discussions, iterative coding and multiple analysts’ perceptions. The analytic purpose was to identify barriers and facilitators that influenced adherence and patient-reported UI outcomes.

At the level of the case (woman)

Case summaries in narrative and tabular form were written with a focus on understanding a woman’s experience of UI, the treatment, adherence, treatment outcome and how these factors interacted. Analysis focused on identifying issues relating to changes over time and in developing rival explanations (additional theoretical propositions) that guided subsequent analysis. 60 Theoretical propositions and rival explanations are analytic strategies drawn from case study design. 61 The theoretical propositions used in the OPAL trial were drawn from the original research questions and the rival explanations arose from working with the data.

At the level of the trial group

Using case summaries and matrices from the framework approach, 66 the cases for one trial group were arranged together and consistencies and inconsistencies searched for. The aim of analysis was to identify the core barriers and facilitators within the trial group, the detailed explanations for them and interactions between them.

At the group comparison level

The biofeedback PFMT and basic PFMT groups were compared using the theoretical propositions in order to identify similarities and differences in barriers and facilitators between the trial groups.

After the trial result was known, an additional analysis was undertaken that aimed to explore who biofeedback works for and why. This analysis is not presented in this report, but may be helpful in understanding subgroups of women for whom biofeedback is more useful.

Management and governance

Ethics approval for the case study was gained within the main trial approvals (see Chapter 2 ).

The case study and process evaluation team had a management group with the required mix of clinical, qualitative, quantitative and theoretical skills and experience. The group met regularly to discuss the research management and emerging findings. The case study was carried out at a separate academic institution to the main trial. The case study team participated in trial meetings to understand how the trial was progressing, but the case study and process evaluation team meetings were closed. Data were not shared from the case study and process evaluation group with the main trial group until the final PMG meeting in September 2018.

Forty women, 20 per group, were recruited to the case study, as planned. Twenty-five women completed all four interviews, but, owing to the technical problems with the audio-recorder, a full data set was available for only 24 women (10 biofeedback PFMT and 14 basic PFMT). The total data set consisted of 125 interviews, including 24 complete cases (96 interviews). The total number of minutes of recorded interviews per case ranged from 15 minutes to 126 minutes, with a total of 2856 minutes of recorded interview data. There were 40 baseline interviews (20 biofeedback PFMT and 20 basic PFMT), 32 interviews at 6 months (16 biofeedback PFMT and 16 basic PFMT), 28 interviews at 12 months (13 biofeedback PFMT and 15 basic PFMT) and 25 interviews at 24 months (11 biofeedback PFMT and 14 basic PFMT).

The age of women in the case study ranged from 20 to 76 years, with both the biofeedback PFMT and the basic PFMT groups including women with a wide age range ( Table 31 ). In the main trial, women ranged in age from 20 to 83 years (22–83 years in the biofeedback PFMT group and 20–78 years in the basic PFMT group); thus, the women in the case study were comparable in age to the main trial sample. From the total case study sample, 11 women had SUI and 29 MUI; the proportions were similar within groups. Six women in the sample were treated in community clinics, 16 in university hospitals and 18 in district general hospitals; again, there were similar proportions in the groups. The vast majority of women were treated by physiotherapists ( n  = 36) and four women were treated by nurses.

Characteristics of women in the case study by group allocation

Women’s adherence to the interventions

Women’s adherence to the interventions was analysed in two phases: active treatment and maintenance. ‘Active treatment’ refers to the time when women were attending appointments and receiving the OPAL trial interventions delivered by a trained therapist. It is the proxy for shorter-term adherence – the uptake and adoption phase of PFMT – including women’s attendance at appointments, receiving biofeedback-mediated PFMT or basic PFMT in the clinic and then undertaking their prescribed programme (biofeedback PFMT or basic PFMT) at home between appointments. The ‘maintenance’ phase is when long-term adherence is demonstrated and is the period of time after the active treatment has ended when women were asked to continue PFMT themselves at home without therapist supervision, including relapse management, up to their final follow-up at 24 months.

Table 32 shows examples of the variation in women’s adherence to PFMT. These examples illustrate that there are no obvious group differences in adherence in the case study sample in terms of the frequency with which they undertook biofeedback PFMT or basic PFMT.

Case study examples of variation in adherence to treatment by allocated treatment group and across time

Facilitators of adherence during the active treatment phase

There was greater similarity than difference in facilitators of adherence in the active treatment phase when the trial groups were compared. Two key themes, among the many that were identified, focused on UI symptoms and factors related to the OPAL trial therapist.

Urinary incontinence symptoms acted as a facilitator in several ways. One way was through the mechanism of women wanting to eliminate or reduce their UI, so that they could get on with their lives and improve their quality of life:

Case 27, 0M, biofeedback: Well I’m hoping that it’ll help the leaking and it’ll, it might never stop, but it won’t be as bad as it’s been . . . that’s what I’m hoping.

Researcher: Yeah. Is there a goal; do you have, like, a personal goal that you would like?

Case 27, 0M, biofeedback: Just that really, just . . . to stop the leaking, maybe be able to go back to yoga and not feel like I’m worrying about leaking or whatever.

I’m not that old that I, I’m ready to kind of hang up my dancing shoes. Case 26, 0M, basic

Women also wanted to prevent a deterioration in their UI symptoms and to avoid surgery. Seeing an improvement in UI during the active treatment phase motivated women to adhere because they felt that their treatment, and their skill to undertake the exercise, was working:

Doing the exercises [was most helpful about treatment] and noticing that there was a change, do you know what I mean? And then realising myself that that was, there had been a change . . . Case 24, 6M, basic

For women from both groups who had a break in their regular biofeedback PFMT or basic PFMT practice, a deterioration in symptoms (after a period of improvement) provided proof of PFMT effectiveness and acted as a facilitator to use the skills that they had learned to overcome the symptomatic deterioration.

Many women from both groups talked at length about the positive impact of the therapist. Women talked about their therapist as an important and credible source of information, as a motivator and as someone who taught them the exercise, lifestyle and behavioural skills needed to undertake biofeedback PFMT or basic PFMT (in line with theoretical model underlying the interventions). 17 All of these factors influenced adherence in the active treatment phase in both groups. However, possibly the most important element of the interventions in each trial group was the instruction on how to perform PFMEs, given by the therapist during the vaginal examination (digital assessment). Given the sensitivity of the topic, vaginal examination was not easy to talk about during the research interviews and, consequently, not an easy finding to capture in the analysis. Yet there was a consistent observation of the importance of the therapist-mediated vaginal feedback as being one of two distinctive and valuable forms of vaginal feedback in PFMT (therapist mediated and EMG mediated). The findings from the case study point to the therapist-mediated feedback as being the priority and as one of the most important therapist-related facilitators in gaining confidence in PFMT skills and adhering to treatment.

The quotation below provides an illustration of the difficulties of articulating experience of PFME instructions during the vaginal examination, as well as the importance of these instructions, which included feedback (as exemplified in the quotation, a part of the feedback loop was the act of the therapist feeling the difference in muscular activity during the examination):

That was quite good actually, having somebody there, and I think when you’re doing exercises and then being able tae feel that it was working, do you know that way when you would get your assessment . . . and you did have to do them, the exercises, and she could feel the, the difference [ . . . ] I felt [ . . . ] that was good, u-uuh, just to know that you were doing it properly [ . . . ] ’cause you do those exercises and you really don’t know one way or another if you are doing it right. Case 30, 6M, biofeedback

Another important therapist-related factor that had an impact on adherence was the rapport created between the therapist and the woman. The conditions for creating rapport require further analysis. It is possible that the above-mentioned therapist-mediated vaginal feedback plays a role, but at this point of analysis it is certain that having dedicated space and time (secured by OPAL trial intervention design) to build understanding and trust through repeated appointments with the same therapist acted as a motivator to adhere to the treatment, if not being a therapeutic agent on its own:

And it’s very motivating . . . you know, seeing someone who’s interested in you, who wants to help you is terribly motivating . . . ‘cause otherwise you’re just on your own, ‘cause you don’t chat to your friends about it . . . the only person I’ve ever really spoken to about this [UI] is [OPAL therapist] and the nurse specialist. Case 32, 6M, biofeedback

[ . . . ] it was good having a one to one with someone who kind of constantly, you were able to talk to about your symptoms and how to improve it and I think just knowing that em that they were there and they were able to tell you, you know, ‘if you work on this, it will improve’ and I think that was a big help, even right at the end there, it was a really good for her to tell me, the physio[therapist] to tell me, like, what exercises it’s best for you to do, what’s not good for you to do and if you keep going wi’ this it’s going to continue to improve, I think that will help me. [ . . . ] you know, psychologically, even if it wasn’t physically, you know, I mean it eventually will be physically, but em, you know, even psychologically I think that was good. Case 15, 6M, basic

Other therapist-related facilitators included education provided by the therapist, being treated by an accommodating and skilful therapist, being treated by a therapist who adjusted the treatment protocol based on individual needs and feeling accountable to the therapist:

I think it was the, the, eh what’s the, what’s the best way to describe it, the actual having to report back to [therapist], because then you knew, you know, you can’t, well you can’t just sort of, you know, sit there and say ‘right, OK I didn’t do it,’ and she would know herself when we did the sort of, the few, even, you know, not the internal examination, when we did the actual work, you know, when she was there and she could tell from my posture, you know, if I was doing it right or not, she was like ‘right, you’re slacking’ . . . Case 3, 24M, basic

Beyond the symptom- and therapist-related facilitators summarised above, women identified other facilitators of adherence that included the following:

• Service structure, framing and physical environment. Having regular appointments; ease and flexibility of making appointments; feeling positive about the physical environment of the treatment facilities; feeling that the intervention was within the framework of womanhood; or the woman finding the treatment as a whole a novelty were all facilitators of adherence.

I was so determined though, I mean the thing is you’ve got to want to, to help yourself I think [ . . . ] you know, it’s just not going to, just taking a note of what somebody says to do, you’ve got to want to do it as well [ . . . ] you’ve got to want to, you’ve got to need to do it as well, you know. Case 20, 24M, basic

• Support from relevant others. Their partner, participation in the trial and a sense of accountability to the trial team were all facilitators of adherence.

. . . so the education was eh the principal thing, when you learn how to do and why it’s wrong, what is wrong . . . and then you can do your, do good for your body. Case 13, 6M, biofeedback

. . . it’s probably the easiest form o’ exercise you could do, I mean you don’t even need tae go tae a gym, it’s so easy. Case 34, 12M, basic

There were facilitators that were specific to biofeedback. Some women reported liking the biofeedback device and having confidence that, by using biofeedback PFMT, they were more likely to achieve symptomatic improvement than if they were doing PFMT alone. In developing the OPAL trial intervention, the research team hypothesised that visualisation of the pelvic floor muscle contraction via biofeedback PFMT would support self-efficacy for performing the correct contraction, leading to improved adherence and better outcomes. Some women in the biofeedback PFMT group did report that visualisation was important for them for two main reasons: (1) they could see if they were doing the pelvic floor muscle contraction correctly and (2) they could see improvement in their pelvic floor muscle contraction ability over time. Women valued the opportunity to be able to discuss the visualised contraction with their therapist.

Other features of biofeedback PFMT that women valued were biofeedback supporting women being competitive with themselves; having a new ‘toy’ to play with; the physical presence of the unit acting as a reminder; getting instruction from the biofeedback device in terms of counting of repetitions and pace of PFMT; and an awareness that the data on the biofeedback device would be looked at by and discussed with the therapist:

I thought it was quite positive that when you were actually using it you could see, and I think it did make you try, it definitely made me try harder, and also I felt that I was doing it for longer, like it, you know, a 10-second hold I think when you haven’t got the biofeedback is probably, in reality, an 8-second hold, because you count quite quickly . . . whereas with the biofeedback I felt that you were doing it properly and I was definitely trying harder because I was seeing it and I was thinking ‘right, I want’ it’s that sort of slightly competitive side to human nature, you’re thinking ‘right, I want to get, I want to get it higher’. Case 8, 6M, biofeedback

In summary, although some group differences were noted, there were more similarities in facilitators of adherence than differences. There were many facilitators of adherence in the active treatment phase, with being motivated to improve symptoms and the effect of the therapist being clear facilitators in both groups.

Barriers to intervention adherence during active treatment phase

There were more similarities across barriers than there were differences between the groups. Time and contextual factors in a woman’s life (such as daily routines) were two of the themes that could be seen to act as barriers to adherence.

Women talked about having a lack of time for themselves; hence, finding time for appointments and to exercise was difficult. Women reported a lack of time to attend appointments in general and frequent appointments in particular, to focus on practising PFMT, either with or without biofeedback; biofeedback was even more time-demanding and, as such, a potentially greater barrier in the biofeedback group:

I don’t know who supplied the physio[therapist] with the dates, but she kinda had a calendar, at the end o’ my appointment she could tell me the time frame when I was due back . . . and I would look at my diary and was like ‘oh, that’s only like 2 weeks’ time’, so I don’t know, maybe even once every 5, 6 weeks or something, em but that, again, that’s just because I’m a working mum and I don’t always have the child care, so em it wasn’t always easy for me to, to get the kids watched, . . . Case 16, 6M, biofeedback

Lack of time was compounded by having a generally busy life that included being a working mother, having unpredictable work patterns and going on holiday. For several women, their UI, and its treatment, was not a priority given the array of other things that were competing for their time. Illness – theirs, or in family members – was a particular barrier to adherence:

Em . . . most of the time I’m OK now, as I say I still do my pelvic floor exercise at the moment, eh it’s not always OK, but [most of them are?], em [sighs] that’s nothing to do wi’ the machine [?] that I dropped out [of treatment], I took, mum took no’ well and I took really bad depression and I would’nae get out the bed. Case 17, 6M, biofeedback

Other contextual factors that acted to diminish adherence included not having a routine (or hook) for doing PFMT, lack of privacy at home, lack of support from their partner and simply forgetting (in the array of other things to do).

Several other barriers could also be identified, these included the following:

• A lack of sufficient, or sufficiently quick, improvement in the UI symptoms. This led to a drop in motivation to adhere. Despite this drop in motivation, many women were still inclined to continue treatment.

Yeah, there seemed to be quite a lot, you know, I seemed to have a lot of appointments, em . . . my husband’s going ‘oh you’re not going there again, what are you going for, what on earth are you going for this time?’ . . . Em maybe the odd time I did feel a bit like that ‘cause I felt, u-uuh, at times I thought ‘oh God here, we’re just going to talk about exercises’ [ . . . ] the odd time I did feel ‘gosh, maybe that was a bit of a waste of time’ [slight laugh] . . . Case 15, 6M, basic

I thought there would be, I thought there would maybe be more em involved in helping support you doing the actual . . . exercises; not that they were difficult or anything like that, I just, I, I think I just felt, you know, you get told what to do, you’re advised about what, how to do them, they don’t, [sighs] I’ve only once been checked to make sure I was doing them right, em so my feeling kinda was am I doing these right? Are they really effective?, and it was a bit hit and miss I felt . . . to how well I was doing; . . . Case 26, 6M, basic

There were some barriers that were specific to the biofeedback PFMT group. Some women found the biofeedback device intrusive or painful to use and others found it inconvenient (e.g. having to set it up, or to clean it):

I found it intrusive and painful to be honest [ . . . ] if I had of [sic] found it less uncomfortable it possibly would have made me notice what I was doing more, but I, I just couldn’t put up [with] the, the pain of it, so I couldn’t be bothered with it. Case 5, 24M, biofeedback

Women reported that they needed to find even more time to undertake PFMT supported by biofeedback. Some women also reported embarrassment and a lack of privacy about using biofeedback:

I think it was quite a good idea, but I don’t think it worked for me, for my personal circumstances, I found it too footery [fiddly] to do, and I just found it quite difficult to have that kind of privacy . . . just to do it, because I found it easier if I was lying down in the bedroom but then, you know, the kids were always like in and out, running around and obviously I didn’t want them to see it, and I just felt it took quite a lot of time and I just felt I didn’t really have the privacy to do it properly, em, so I don’t think it really worked for me, I felt it was too footery; but on the other hand I think it had lots of advantages, ‘cause I think it was quite useful to see, to see what was actually happening. Case 8, 24M, biofeedback

Other issues with the biofeedback included one woman reporting that she got thrush from using the biofeedback unit; the biofeedback unit could be framed as externalising the movement of the pelvic floor muscles and a distraction to embodiment of PFMT; and practical problems with the biofeedback unit that hampered ability to use it:

I thought I was doing super, then one day it died and it, I knew it had a brand new battery so that shouldn’t have happened . . . it died, so I rang them up and I took it in and we got a new battery, then I came back and it happened again, it kept doing weird things, and then I bought batteries up the road in the end, so, . . . And then I realised that by looking at the machine I was distracted from doing the exercises. Case 32, 6M, biofeedback

In summary, there were more similarities than differences in barriers to adherence in the active treatment phase; there were also additional barriers in the biofeedback PFMT group. A lack of time and many contextual factors were the key barriers to adherence to biofeedback PFMT and basic PFMT.

Facilitators of women’s adherence in the maintenance phase

None of the women in the biofeedback PFMT group reported using biofeedback after the end of treatment in the trial. None of the interviewed women reported buying biofeedback equipment; some therapists did give women the probe to keep and use, yet none of the women reported using it, even though some reported intention to use it. Thus, the data below relate to women, from both groups, undertaking basic PFMT in the maintenance phase.

Women in both groups reported a change in their adherence from the active treatment phase. PFMT maintenance was not consistent over time in either group and there were no differences (from qualitative comparison) between the groups in their adherence. The inconsistency in adherence between women can be seen in Table 32 , in which, at the extremes, some women undertook PFMT in a regular and daily manner, whereas others did not do PFMT at all. In between these extremes were women who undertook PFMT with varying degrees of regularity. As well as the inconsistency between different women, there were fluctuations in adherence for individual women over the time period with, for example, other health concerns taking over and diminishing adherence at some points in time.

Many of the facilitators that applied when women were in the active phase of treatment also applied in the maintenance phase.

Similar to the active treatment phase, women’s desire to lessen UI symptoms supported adherence to PFMT in the maintenance phase. If women perceived symptom deterioration or recurrence and associated this with PFMT as a mechanism to improve symptoms, adherence was facilitated. The interpretation of the data would suggest that symptoms may only act as a prompt to undertake PFMT in the maintenance phase if the woman perceived that there was an improvement in symptoms as a consequence of doing PFMT during the active treatment:

Not really no [been doing PFMT], but quite often in the last week, ‘cause I’ve noticed a difference that’s why I’ve sort of started to try and do it again, ‘cause I have noticed a difference in not doing it . . . Case 8, 6M, biofeedback

Oh yes, I always will [exercise] now, that’s it . . . that’s it, because I know it, I know it’s, you know how much it’s helped. Case 20, 24M, basic

There were multiple factors that seemed to influence women’s confidence (self-efficacy) to continue, or feel able to restart, PFMT in the maintenance phase. Many women reported feeling that they had good levels of knowledge and skill to undertake PFMT correctly. Beliefs in their skills and knowledge could be attributed to women feeling they had mastery of PFMT; having memories of the support they received from the therapist during active treatment; recalling information imparted by the therapist; using the resources given by the therapist (such as information leaflets); keeping a record of PFMT like an exercise diary; and recalling the sense of hope given during treatment and the control they gained:

I don’t feel like I need to go back and see a doctor or, you know, see a nurse or anything, I feel like if it got bad again I could, you know, I’ve got these exercises to fall back on. Case 27, 24M, biofeedback

I remember the girl who, or the nurse that, the lady, you know the . . . pelvic floor . . . in [location], and I remember her, she was very good, gave me a lot of confidence in myself, you know and . . . it was really good, she was very, very helpful, and I can remember, I can remember the improvement, . . . Case 20, 24M, basic

In the biofeedback PFMT group some women related having good skills and knowledge of PFMT directly to biofeedback during active treatment. Women in the basic group also felt that they had good skills and knowledge of PFMT acquired from teaching by, and feedback from, therapists. Therefore, biofeedback was not a necessary prerequisite for having skills and knowledge for PFMT maintenance:

[I remember] learning to use the machine properly . . . knowing I was doing it right and . . . yeah, and just generally being made more aware of the muscles that you need to squeeze and . . . when you’re, and you know you do one at a time and then you hold them all . . . so yeah . . . being taught how to do pelvic floor . . . muscle training . . . yeah, being taught that properly, yeah, . . . made a big difference. Case 23, 24M, biofeedback

Other factors that facilitated adherence in the maintenance phase included the following:

• A supportive home environment.
• Establishing the intervention as part of life: being able to find time for themselves; helpful work patterns (e.g. working from home or time spent commuting); making use of available time to do exercises (e.g. sitting and waiting time such as while commuting, or watching television).

I don’t think so, I mean I know what to do, I mean it’s . . . I, I, aye, I know what tae dae and I know what I should be doing but it’s just the getting intae it, so . . . maybe I should start up a wee book kinda thing again, I done that the last time and I was dain’ wee [unclear word] like when, how many I had done, do you know, how many kinda exercises I’d done that day, and eh, do you know what I mean, I think I should start that, when it’s doon in black and white sometimes that kinda, kinda motivates you oan . . . Case 24, 12M, basic

Oh probably [doing PFMT] daily, ‘cause I do sort o’ try to keep it going . . . ‘cause I’ve got to keep control o’ something, I can’nae control everything else [that I’ve got?] . . . [I was more?] conscious of it then, but, as I said, it’s one thing I’m sort of trying to keep control of . . . so I’ll try and keep that bit going. Case 17, 24M, biofeedback

• Trial-specific factors – research interviews acting as a trigger to undertake PFMT, interviews providing a space for reflection on a woman’s own PFMT practice, attending the 6-month pelvic floor assessment and wanting to demonstrate that the therapist had done an excellent job. These factors occurred in both groups.

I [got] the squeeze App on my phone and that was really good . . . you know, it helps you, you obviously train yourself to hold for longer [kind of thing], that was good. Case 19, 24M, basic

In summary, adherence did change in the maintenance phase from the active treatment phase. There was considerable variance, in individual women and between women, in adherence in the longer term. Many of the facilitators that supported women in adhering in the active treatment phase continued to facilitate adherence in the maintenance phase.

Barriers to women’s adherence in the maintenance phase

One barrier to adherence that was unique to the maintenance phase was the loss of therapist support, and accountability to the therapist, when the active treatment phase ended. Some women felt ‘alone’ in their efforts to improve their UI. Others expressed the view that, because they were no longer accountable to the therapist, there was no longer that prompt to exercise. Other women said that they got out of the habit of writing their exercises down (as they would have done in the exercise diary during active treatment):

I thought, you know when the nurse did it with me, you know, did it, that helped me a lot, really it did, if I could keep going to the physiotherapist and if she kept checking me, because I think, you think you’re doing it right and then I could be doing it wrong and that, you know what I mean, I mightn’t be feeling . . . Yeah, I mean I would have liked then to be able to phone up, you know, the physio[therapist] and say ‘look, can I have another appointment?’, rather than the length of time between each, and then of course it stopped for so many months . . . Case 6, 12M, basic

Otherwise, the main barriers for women in maintaining PFMT, whether allocated to the biofeedback PFMT or basic PFMT group, were similar to those found in the active treatment phase. First, some women’s UI had improved to such an extent that they had no symptoms to act as a reminder to exercise:

. . . as I said my symptoms have reduced so there’s not so much of a physical reminder that ‘oh, I need to do them’ [PFMT]. Case 28, 12M, biofeedback

The second key barrier was the loss of motivation or loss of the habit of doing PFMT due to life events taking over, even if this was contrary to the intent they had at the end of active treatment. Women spoke of various contextual factors in their lives that prevented them from maintaining a PFMT regime, such as having too many other things to do, work commitments or work changes getting in the way, or more generally feeling that they lacked support. Commonly, women talked of having other non-UI health problems that overshadowed their focus on UI and/or on their attention being more on the needs of others (commonly immediate family). In keeping with the active treatment phase, the findings suggest an interaction between a lack of time (e.g. as shown below, women not having time for themselves) and the multiple other contextual factors that get in the way of life:

Well I’ve had a lot o’ other health issues so it’s kinda been, that’s [PFMT] been the least o’ my worries [UI] tae be honest wi’ yae [slight laugh]. Case 10, 24M, basic

Case 32, 12M, biofeedback: . . . it really is down to me . . . I expect you hear that from a lot of women . . . And it’s very hard to put yourself at the top of your own time agenda . . .

Researcher: As women . . .

Case 32, 12M, biofeedback: Yeah, yeah [talks about her husband exercising every day no matter what] . . . So, but with me something seems to come up, [then it’s?] all my stuff goes to pot on my own agenda . . ., I suppose it’s just, [he’s] not easily distracted but there are more pressures on me . . . and I think it’s probably the same for women generally.

Other factors that acted as barriers to adherence in the maintenance phase were as follows:

• Not establishing PFMT as part of life. Some women found maintaining a PFMT exercise programme to be difficult because they had no routine in life generally, or for PFMT specifically, or that routine changed (e.g. going on holiday).
• Not feeling confident in their PFMT technique and when to use it after treatment had stopped. This seemed to manifest as a lack of confidence in (1) their ability to undertake PFMT generally or (2) how to get restarted after a break in PFMT. Various reasons can be identified for this lack of confidence in the maintenance phase: forgetting what they were taught, not feeling that PFMT was going to work, not perceiving that their UI was caused by pelvic floor weakness (it was caused by something else) or because they had not seen symptomatic improvement during active treatment. However, there was a stronger pattern for women to feel confident about continuing PFMT than not having the confidence to continue.
• Ownership and agency in PFMT. Some women talked about a lack of motivation and willpower, they talked about forgetting to exercise (sometimes or always), and PFMT lost the novelty factor and priority over time.

In summary, large-scale systematic differences between the biofeedback PFMT and basic PFMT groups in barriers to PFMT maintenance were not evident from the data set. Key barriers to maintaining PFMT lay in loss of support following the active treatment phase and busy lives.

Women’s urinary incontinence outcomes in the short and long term

The case study did not set out to explore outcome, but women discussed outcome as part of their experience. Given the longitudinal case study design, and the core aim of the trial, it was useful to consider women’s views of outcome in this chapter in relation to UI symptoms. However, interviewed women reported outcomes that were considerably broader than UI symptoms alone. For example, the women talked about changes they made to their lifestyle, changes to their feelings about UI and about a myriad of things they had learned from being part of the trial. These additional outcomes will be documented in more detail in future publications.

At 24 months (when the primary outcome was measured in the trial) there was no obvious difference between the groups in UI severity from qualitative comparison; rather, there were women in both groups with varying outcomes ( Table 33 ).

Case study examples of variance in UI outcomes at 24 months by allocated treatment group

In both the biofeedback PFMT and basic PFMT groups there were more women talking about positive outcomes in relation to their UI symptoms at 24 months than there were talking about poor outcomes (i.e. from baseline it seemed as if women tended to be better than they were before they entered the trial). This information, however, needs to be considered with caution, as qualitative studies do not aim to statistically generalise:

I was just going to say well no, thank you for the opportunity because I’ve seen a massive, you know, improvement and because I’ve got a prolapse and obviously, I’m quite young, I’m only 38, it was making me sort of anxious about [?] and you know, everything has improved, my bladder control and my prolapse symptoms have improved, I’m not getting as many em, I used to get sort of quite a lot of dragging sort of tummy ache [muscle, or little,?] and I don’t get that any more, so, you know, and I know that that is definitely all down to the trial, if I wouldn’t have been involved in that, then I know that I’d still be having the problems and still be anxious, you know, if I went out walking or if I went, went running, or to the gym or whatever, so, so I’d like to say thank you to you guys as well. Case 28, 24M, biofeedback

In terms of short-term outcomes, in both groups there was a pattern that suggested that women were likely to have better UI outcomes at 6 months (immediately post-active treatment phase) than at 24 months. For example, case 13 (biofeedback PFMT) reported symptomatic improvement at 6 and 12 months, but at 24 months reported that her symptoms were the same or a little worse than when she started the trial. There was, however, variance between individuals. For example, for case 32 (biofeedback PFMT), there was no improvement noted at 6 months and at 24 months her symptoms were worse than when she started the trial. There were other cases when improvements occurred beyond 6 months (i.e. 6 months was not the best outcome point). For example, case 36 (basic PFMT) reported good improvement at 6 months, further improvement at 12 months and yet further improvement at 24 months.

In summary, there were no obvious differences in UI outcome between the trial groups.

Theoretical propositions

Two theoretical propositions and one rival explanation were considered. The theoretical propositions were driven by the theory that supported the hypothesised mechanism of action (propositions 1 and 2) and one rival explanation that arose from analysis of the data (proposition 3).

Proposition 1: biofeedback PFMT will improve (1) women’s adherence and (2) women’s urinary incontinence outcomes more than basic PFMT in the short and long term

This proposition was the main hypothesis of the trial. There was no clear evidence that biofeedback PFMT improved adherence over basic PFMT in the short or long term, nor any clear evidence of greater improvement of outcomes in either the short or the long term. Therefore, the theoretical proposition was not supported.

Proposition 2: the factors that influence women’s adherence and women’s urinary incontinence outcomes change over time

This proposition arose from the long-term nature of the follow-up that was part of the commissioning brief and was based in our understanding of the influence of context (e.g. Wells et al. 67 ). This proposition was supported in that it was clear that the factors that influence adherence and outcome for an individual woman do change over time. For example, there were women who were diagnosed with other conditions during the trial that, for them, took precedence in their quest for good health. However, the hypothesis aimed to identify if there were factors that arose at specific time points for a group of women. It does not seem that there were factors that occurred at the same time point in specific groups of women (other than the removal of support when treatment finished); however, this will be the subject of further analysis.

Proposition 3: factors other than biofeedback PFMT or basic PFMT will influence adherence and urinary incontinence outcome in the short and long term

This proposition arose from rival explanations (to biofeedback PFMT or basic PFMT directly linking to adherence and outcome) being identified iteratively in data analysis. Although there were factors other than the interventions that influenced adherence and outcome, there were considerably more similarities in the factors than differences between the groups. The notion of life events taking over encapsulates this well. However, for some women with multiple other life events, there was still adherence and a symptomatic improvement (i.e. these factors did not always act to diminish adherence or outcome, but they often did).

Women reported positive experiences of both the biofeedback PFMT and basic PFMT interventions; in particular, women were clear about the benefit of therapist input. There were no major differences, based on qualitative comparison, in adherence to PFMT or UI outcome between the biofeedback PFMT and basic PFMT groups, with wide variation in adherence and outcome in both groups. Adherence in the short and long term was facilitated by women’s desire to improve or cure their UI symptoms and by factors related to the therapists, which included feedback given through vaginal examination and rapport. A lack of time and life taking over were key barriers to adherence in both the short and long term. Adherence did change over time, but there were no clear differences between the groups. Although UI outcome did not appear to differ between the groups, there was a trend towards improved outcomes at 2 years when compared with baseline. There were features of biofeedback PFMT that worked as anticipated (such as visualisation), but there were also drawbacks to biofeedback (such as it taking more time than PFMT alone).

Strengths and limitations of the case study

A key strength of the case study, and qualitative research linked to trials in general, is that it facilitated the voice of those whom the intervention aimed to help to be heard and represented. The longitudinal nature of the case study, with detailed follow-up at the same time points as the trial, and the purposeful searching for expansion on emerging ideas at subsequent interviews, allowed consideration of women’s expressions of adherence to PFMT over time. Studies of long-term adherence in UI are rare (only one other longitudinal study, 68 with women who have UI, has been identified), but are important as reduced adherence is a common explanation for why treatment effect is not sustained over time. 69 The two-tailed case study design offers a robust, qualitative means of comparison that supports the comparison in the trial.

The process evaluation and case study drew on a contemporary published framework in further developing the work and developing the analysis plan. 63 That framework proposes multiple candidate approaches to understanding various features of the trial and its effects. However, one weakness was that data were not gathered on all the candidate approaches. 63 However, data were gathered on several candidate approaches that were central to the research questions, such as maintenance. Another potential weakness of the case study in relation to the trial is that the interviews may have acted as a co-intervention to promote adherence, for example women reflected that they undertook PFMT because they knew that an interview was coming up. However, the case study recruited women from both the biofeedback PFMT and basic PFMT groups and any effect of the interviews on adherence potentially occurred equally in both groups.

Comparison of findings to existing literature

The evidence from the case study is consistent with the trial finding that biofeedback PFMT did not improve UI outcomes more than basic PFMT. Insights from the case study are helpful in explaining the main trial finding. The qualitative data demonstrated that biofeedback could work as anticipated, with women reporting the benefits of being able to visualise the contraction and know that they were doing the contraction correctly, alongside their learning in partnership with the therapist. However, women in the basic PFMT group also had confidence in their ability to undertake PFMT. For these women, this was based on learning in partnership with the therapist. A possible conclusion is, therefore, that biofeedback does not need to be added to a strong basic PFMT programme in order for women to achieve self-efficacy for and adherence to PFMT; good therapist input can also provide self-efficacy and adherence.

Aspects that are central to this conclusion are that the OPAL trial basic PFMT (and biofeedback PFMT) programmes allowed sufficient time with therapists to support a treatment effect; 70 both interventions were based on BCTs; 8 both demonstrated that some women achieved self-efficacy for PFMT; 71 both groups received therapist-mediated vaginal feedback; and one group also received biofeedback. 7 Although it is possible that if biofeedback PFMT had been compared with a less robust basic PFMT programme there would have be been a difference between groups, it would then have been difficult to reach conclusions about the effectiveness of adding biofeedback because of other confounding variables. 7 Our conclusions therefore support a finding that, if all other aspects of PFMT are kept equal, the addition of biofeedback may not lead to a greater improvement in continence outcomes.

Another possible explanation for why biofeedback PFMT was not more effective than the basic PFMT is that, although women in the biofeedback PFMT group did identify features of biofeedback as facilitators of adherence, they also identified features of biofeedback as barriers to adherence. One tentative hypothesis here is that the facilitators and barriers simply cancel one another out. However, this needs further analysis.

Case study findings demonstrated that women generally reported positive experiences of the OPAL trial interventions. Women were positive about learning to do PFMT (with or without biofeedback), which is consistent with a previous qualitative synthesis. 18 Women were also very positive about the therapists. Women talked about the therapist in ways that suggested that the therapist was seen as a credible source of information, a motivator and as someone who could support the learning of the necessary behavioural skills, all of which supports the theory underlying the development of the interventions (IMB 17 ). Furthermore, in keeping with previous suggestions, rapport between woman and therapist was seen as a factor in supporting adherence. 18

There was a trend identified in the case study data for women to perceive that their UI was better at 2 years than it was when they started the trial. This was not the case for all women. It was, however, an important finding in the context of the worldwide evidence that UI negatively affects women’s day-to-day lives (see, for example, Bradway, 72 Delarmelindo Rde et al. 73 and Hamid et al. 74 ). Although it is possible that the improvement described by women is not linked to the interventions, the evidence suggests that women did perceive a link between the intervention they received, their adherence to PFMT and their positive outcome. This link will be explored in more detail in further analysis.

Adherence to PFMT did change over time, but not differently between the allocated groups. A key reason for including the case study alongside the trial was the recognition of the influence of context on the effectiveness of complex interventions. 67 , 75 It is now widely recognised that context interacts, modifies, shapes and constrains the intervention and implementation. 76 This study chose to investigate the influence of context in-depth from the participants’ perspectives (rather than also exploring the problem, trial and organisational contexts), because it was believed these would be the most important factors to shape the interventions and influence their effectiveness. It is important to understand the dynamic relationship between context, implementation and intervention to define what was implemented and understand how works in certain contexts. It is now no longer enough to say what works, we need to explore what works, for whom and in what context. 53 It was clear that many varied personal contextual factors influenced adherence. The longitudinal nature of the study was important in highlighting that for all women, context and implementation were dynamic and life events got in the way. In addition, many women put the needs of others before themselves. We need to carry out a nuanced analysis to explore the characteristics of these women to understand the various ways women may overcome these events. Previous research supports the links between life taking over and inconsistent adherence in UI. 57 , 77 These findings suggest that when delivering a PFMT intervention, or in future research, consideration should be given to helping women balance the multiple contextual factors in ways that may support their engagement with PFMT and their re-engagement with PFMT after a break.

Urinary incontinence symptoms were an important factor in adherence at the outset, and continued to be so in the long term. Symptoms influenced adherence in a number of ways. Women adhered to rid themselves of symptoms, but, conversely, when symptoms were no longer present, the trigger to exercise was no longer there and some women then stopped exercising. Women had to perceive change and believe that it was linked to treatment to maintain adherence in the longer term. This finding is consistent with other studies. 18 It is an important feature of care delivery for therapists to keep the connection between PFMT and symptomatic improvement at the forefront of women’s minds.

• Cite this Page Hagen S, Bugge C, Dean SG, et al. Basic versus biofeedback-mediated intensive pelvic floor muscle training for women with urinary incontinence: the OPAL RCT. Southampton (UK): NIHR Journals Library; 2020 Dec. (Health Technology Assessment, No. 24.70.) Chapter 6, Longitudinal qualitative case study.
• PDF version of this title (2.0M)

In this Page

Other titles in this collection.

• Health Technology Assessment

Recent Activity

• Longitudinal qualitative case study - Basic versus biofeedback-mediated intensiv... Longitudinal qualitative case study - Basic versus biofeedback-mediated intensive pelvic floor muscle training for women with urinary incontinence: the OPAL RCT

Your browsing activity is empty.

Activity recording is turned off.

Turn recording back on

Connect with NLM

National Library of Medicine 8600 Rockville Pike Bethesda, MD 20894

Web Policies FOIA HHS Vulnerability Disclosure

Help Accessibility Careers

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

Please note you do not have access to teaching notes, learning from within: a longitudinal case study of an education research group.

Studies in Graduate and Postdoctoral Education

ISSN : 2398-4686

Article publication date: 13 November 2017

Professionals in higher education are expected to be informed consumers of knowledge who seek out scholarship, critical evaluators of the applicability of extant knowledge, and contributors who build new knowledge for higher education practice. Despite the understood importance of developing research competencies, many have limited opportunities to develop these skills. This study aims to explore one way individuals develop research competencies: through participation in team-based research experiences.

Design/methodology/approach

A longitudinal case study approach was used to investigate what participants in an education research group learn, and how their participation in the group changes the ways in which they think about themselves as researchers and scholars. Four group members participated in two focus group interviews (at the end of the fall 2015 and spring 2016 academic semesters). Interviews were analyzed using thematic analysis.

Study participants report gaining knowledge about research, developing an identity as a researcher, and learning about faculty roles. Particular group practices and activities (e.g. full group meetings, subgroup meetings, professional development moments) helped mediate members’ learning and identity development.

Originality/value

Research groups should be considered valuable contexts where teaching and learning take place. By learning – and integrating what we learn – from research group participation, the higher education and student affairs fields may become better able to generate innovative practices and activities that provide students and professionals with opportunities to develop important research competencies.

• Graduate education
• Learning theory
• Longitudinal
• Research group
• Research supervision

Burt, B.A. , Lundgren, K. and Schroetter, J. (2017), "Learning from within: a longitudinal case study of an education research group", Studies in Graduate and Postdoctoral Education , Vol. 8 No. 2, pp. 128-143. https://doi.org/10.1108/SGPE-D-17-00002

Emerald Publishing Limited

Copyright © 2017, Emerald Publishing Limited

Related articles

We’re listening — tell us what you think, something didn’t work….

Report bugs here

All feedback is valuable

Please share your general feedback

Join us on our journey

Platform update page.

Visit emeraldpublishing.com/platformupdate to discover the latest news and updates

Questions & More Information

Answers to the most commonly asked questions here

• Basics of Research Process
• Methodology

Longitudinal Research Design: Methods and Examples

• Speech Topics
• Basics of Essay Writing
• Essay Topics
• Other Essays
• Main Academic Essays
• Research Paper Topics
• Basics of Research Paper Writing
• Miscellaneous
• Chicago/ Turabian
• Data & Statistics
• Admission Writing Tips
• Admission Advice
• Other Guides
• Student Life
• Studying Tips
• Understanding Plagiarism
• Academic Writing Tips
• Basics of Dissertation & Thesis Writing

• Essay Guides
• Research Paper Guides
• Formatting Guides
• Admission Guides
• Dissertation & Thesis Guides

Table of contents

Use our free Readability checker

A longitudinal study is a research method used to investigate changes in a group of subjects over an extended period of time. Unlike cross-sectional studies that capture data at a single point in time, longitudinal studies follow participants over a prolonged period. This allows researchers to examine how variables gradually evolve or affect individuals.

In case your research revolves around observing the same group of participants, you need to know well how to conduct longitudinal study. Today we’ll focus on this type of research data collection and find out which scientific areas require it. Its peculiar features and differences from other research types will also be examined.  This article can help a lot with planning and organizing a research project over a long time period. Below you’ll find some tips on completing such work as well as a few helpful examples from a college paper writing service . Feel free to go on in case you aim to complete such work.

What Is a Longitudinal Study: Definition

Let’s define ‘ longitudinal study ’ to begin with. This is an approach when data from the same respondents’ group is gathered repeatedly over a period of time. The reason why the same individuals are continuously observed over an extended period is to find changes and trends which can be analyzed. This approach is essentially observational as you aren’t expected to influence the group’s parameters you are monitoring in any way. It is typically used in scope of correlational research which means collecting data about variables without assuming any dependencies. Let’s find out more about its usage and how much time it could take.

How Long Are Longitudinal Studies?

How long is a longitudinal study? It depends on your topic and research goals. In case characteristics of the subject are changing fast, it might be enough to take just a few measurements one by one. Otherwise, one might have to wait for a long time before measuring again. So, such projects can take weeks or months but they also can extend over years or even decades. Studies like that are common in medicine, psychology and sociology, where it is important to observe how participants’ characteristics evolve.

How to Perform Longitudinal Research?

Before actively engaging in longitudinal research, it is important to understand well what your next steps should be. Let’s define study subtypes that can be used for such research. They are:

• Collecting and analyzing your own data.
• Finding data already collected by some other researcher and analyzing it.

Each of these subtypes has certain pros and cons. Gathering data yourself usually gives more confidence but it might be hard to contact the right individuals. Let’s discuss each point in detail. Likewise, you can pay someone to write my research paper .

Longitudinal Study: Data From Other Sources

When doing longitudinal studies of a certain group over a long period, you might find available data about them left from other researchers. Make sure to carefully examine sources of each dataset you decide to reuse. Otherwise previous researchers’ mistakes or bias may influence your results after you’ve analyzed that data. However this approach could be very efficient in case the subject has already been investigated by different researchers. Their results could be compared and gaps or bias could be easier to eliminate. As a result, much time and effort could be saved.

Longitudinal Design: Own Data

When doing longitudinal studies without any significant predecessors’ works available, using your own data is the only reasonable way. This data is collected through surveys, measurement or observations. Thus you have more confidence in these results however this approach requires more time and effort. You need proper research design methods  prior to starting the collection process. If you choose such an approach, keep in mind that it has two major subtypes:

• retrospective research: collecting data about past events.
• prospective research: observing ongoing events, making measurements in more or less real time.

Longitudinal Study Types

A longitudinal study can be applied to a wide range of cases. You need to adjust your approach, depending on a specific situation, subject’s peculiarities and your research goals.  There are three major research types you can use for continuous observation:

Longitudinal Cohort Study

Retrospective longitudinal study, longitudinal panel study.

Let’s take a closer look at each type’s definition with our coursework writing service . Dive deep to learn how data is collected and what impact is made on results.

A cohort longitudinal study involves selecting a group based on some unique event which unifies them all. It can be their birth date, geographic location, or historical experience. So there are special relationships between that group’s members which play significant roles for the entire research process. Such a peculiarity is to be carefully selected when doing test design and planning your test steps. Sometimes one unifying event may be more relevant or convenient than another.

This approach takes a special place among longitudinal studies as it involves conducting some historical investigations. As we’ve already mentioned above, during a retrospective, researchers have to make observations and measurements of past events. Collecting historical data and analyzing changes might be easier than tracking live data. However the development of such research design must include checking the credibility of datasets that were used for it.

A panel study involves sampling a cross-section of individuals. This approach is often used for collecting medical data. Such a study when performed continuously is considered more reliable compared to a regular cross sectional study and allows using smaller sample sizes, while still being representative. However, there are various problems that may occur during such studies, especially those which go on for decades. Particularly, such samples can be eventually eroded because of deaths, migration, fatigue, or even by development of response bias.

Longitudinal Research Design

Longitudinal study design requires some serious planning to complete it properly. Keep in mind that your purpose is to directly address some individual change and variation cases. The target population should be chosen carefully so that results achieved through this study would be accurate enough. Another key element is deciding about proper timing. For example you would need bigger intervals to ensure you detect important changes. At the same time, dissertation writers suggest that the intervals shouldn’t be too big. Otherwise, you might lose track of the actual trends within your target population.

Advantages and Disadvantages of Longitudinal Study

Let’s review longitudinal study advantages and disadvantages. Better wrap your head around this information if you are still choosing an optimal approach for your own project. Any study that involves complicated planning and extensive techniques can have some downsides. It is common for them to come together with benefits. So pay close attention to the information below before deciding what method to choose to observe your research subject.

Advantages of Longitudinal Study

These are the benefits of longitudinal study:

• it can provide unique insight that might not be available any other way. Particularly, it is the only way to investigate lifespan issues. It allows researchers to track changes across the entire generation . Let’s suppose the task is to track the percentage of farms which pass from parents to children in a certain location. Obtaining such information requires using historical records.
• such observational approach shows dynamics in respondent’s data and thus allows to model trends and understand their influence. Collecting data once provides only a snapshot of your group’s current state. Doing it continuously allows you to observe this group from some new angles. For example, you would get more information about your respondents’ habits if you observe them at least several times.

Longitudinal Study Disadvantages

This is the disadvantages of longitudinal study:

• it can be quite expensive since numerous repeated measurements require enormous amounts of time and effort. Imagine you need to collect data about a certain group for 10 years. Processing this data alone would require a lot of resources.
• such high costs may induce another problem: researchers might decide to use lesser samples in order to cut the expenditures. Consequently, results of such studies may not be representative enough.
• its participants tend to drop out eventually. The reasons may vary: moving to another location, illness, death or just loss of motivation to participate further. As a result, a sample is shrinking and thus decreasing the amount of data collection in research . This process is called selective attrition. A typical example is observing the life of some neighborhood in a big city: numerous people would move in and out so it would be hard to find a single individual who is available for a long time.

Longitudinal Study Examples

Let’s review some longitudinal study example which would be helpful for illustrating the above information.

Longitudinal research example A famous longitudinal case is The Terman Study of the Gifted also known previously as Genetic Studies of Genius. Its founder and the main researcher, Lewis Terman, aimed to investigate how highly intelligent children developed into adulthood. He was also going to disprove the then-prevalent belief that gifted children were typically delicate physically and also socially inept. Initial observations began in 1921, at Stanford University. Eventually it led to confirming that gifted children were not significantly different from their peers in terms of physical development and social skills. The results of this study were still being compiled during the 2000s which makes it the oldest and longest-running longitudinal study in the world. Such a huge period of data collection made it possible to obtain some really unique knowledge, not only about children’s development but about the history of education as well.

Longitudinal: Final Thoughts

In this article we’ve explored the longitudinal research notion and reviewed its main characteristics:

• conducting observations and measurements continuously over a long period of time
• some particular new insights which can be obtained by prolonged studies
• prospective advantages and disadvantages for researchers.

Or just unsure of where to start from? No worries, you’ve come to the right place – just check out our writing services . We are a team of skilled authors with significant experience in various academic areas. Just let us know how we can help you and you’ll get your paper completed in time!

Frequently Asked Questions About Longitudinal Studies

1. is a longitudinal study quantitative or qualitative.

According to the definition of a longitudinal study, quantitative methods don’t play any significant role in the process. This approach includes extended case studies, observing individuals over long periods and gaining additional insights thanks to the possibility to analyze changes over time. Since these observations and resulting assumptions mostly consist of descriptions of trends, changes and influences, we can say that it is a purely qualitative approach.

2. Are longitudinal studies more reliable?

Longitudinal studies in general have similar amounts of problems and risks as other studies do. This includes:

• survey aging and period effects.
• delayed results.
• achieving continuity in funding and research direction.
• cumulative attrition.

These factors can decrease reliability of this study type and must be taken into account when selecting such an approach. 

3. Is attrition a limitation of longitudinal studies?

Depending on how big is the period they take, longitudinal studies may suffer more or less for the attrition factor. It can deteriorate generalizability of findings if participants who stay in a study are significantly different from those who drop out. In case a particular study takes many years, researchers need to see the attrition factor as a serious problem and to develop some ways to counter its negative effect.

4. What is longitudinal data collection?

Longitudinal data collection occurs sequentially from the same respondents over time. This is the core element of this study type. Repeated collection of data allows researchers to see temporal changes and understand what trends are there in this population. It allows viewing it from some new angles and thus to obtain new insights about it. There are certain limitations to such data collection, particularly when the target group tends to change over time.

Joe Eckel is an expert on Dissertations writing. He makes sure that each student gets precious insights on composing A-grade academic writing.

You may also like

• Open access
• Published: 22 April 2024

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

• Kannan Sridharan 1 &
• Reginald P. Sequeira 1  

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

454 Accesses

1 Altmetric

Metrics details

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

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

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

Conclusions

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

Peer Review reports

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

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

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

Study design and ethics

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

Study procedure

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

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

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

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

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

Specific learning objectives

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

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

A-type MCQs

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

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

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

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

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

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

Integrated case cluster MCQs

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

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

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

Integrated short answer questions

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

Short answer questions

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

Strengths and limitations

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

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

Data availability

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

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

Article   Google Scholar  

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

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

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

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

Google Scholar  

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

Download references

Author information

Authors and affiliations.

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

Kannan Sridharan & Reginald P. Sequeira

You can also search for this author in PubMed   Google Scholar

Contributions

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

Corresponding author

Correspondence to Kannan Sridharan .

Ethics declarations

Ethics approval and consent to participate.

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

Consent for publication

Not applicable.

Competing interests

The authors declare no competing interests.

Additional information

Publisher’s note.

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

Electronic supplementary material

Below is the link to the electronic supplementary material.

Supplementary Material 1

Rights and permissions.

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

Reprints and permissions

About this article

Cite this article.

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

Download citation

Received : 26 September 2023

Accepted : 28 March 2024

Published : 22 April 2024

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

Share this article

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

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

Provided by the Springer Nature SharedIt content-sharing initiative

• Medical education
• Pharmacology
• Therapeutics

BMC Medical Education

ISSN: 1472-6920

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

• Skip to main content
• Keyboard shortcuts for audio player

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

Reproductive rights in America

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

Selena Simmons-Duffin

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

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

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

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

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

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

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

1. Idaho physicians warn patients are being harmed

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

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

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

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

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

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

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

2. Hospitals are closing units and struggling to recruit doctors

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

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

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

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

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

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

3. Justices could weigh in on fetal "personhood"

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

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

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

Shots - Health News

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

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

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

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

4. The election looms large

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

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

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

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

Correction April 23, 2024

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

• Abortion rights
• Supreme Court