Medical Education Insights: AI Qualitative Analysis

Medical education researchers often collect rich qualitative data through focus groups, open-ended questionnaires, and student reflections, but manual analysis can make it difficult to connect participant experience with measurable learning outcomes. AI qualitative analysis in medical education offers a way to organize transcripts, identify recurring themes, compare perspectives, and preserve supporting quotations for reporting. The November 5, 2026, PLOS One study by Rajesh Kathrotia and colleagues provides a useful example: 50 undergraduate medical students built physical physiology exhibits, completed pre-tests and post-tests, and shared their experiences through open-ended feedback and a focus group. This article explains what the study found, how its qualitative design worked, and how AI-assisted analysis can help education researchers move from raw student feedback to defensible insights.

Key Takeaways

According to the November 5, 2026, PLOS One study, physical exhibit building was associated with improved higher-order cognitive test scores and positive student perceptions among 50 first-year medical students.

The study shows why qualitative analysis matters in medical education: student quotations explained how collaboration, faculty support, practical application, and planning challenges shaped the learning experience.

According to the 2026 PLOS One study, median post-test scores increased from 12 before the intervention to 16 after the intervention, with p < 0.01.
According to the study methods, 50 students were divided into four teams of 12 or 13 students and created exhibits over a three-week period in 2023.
According to the study's qualitative analysis, open-ended feedback was organized into enabling factors, hindering factors, and learning gains.
According to the study, a 96-minute focus group with 10 purposively selected students was transcribed and analyzed inductively.
According to the study authors, students described the activity as application-based learning that improved conceptual clarity, teamwork, and problem-solving.

What the Medical Education Study Measured

The 2026 PLOS One study used an explanatory sequential mixed-methods design to examine whether creating physical physiology exhibits developed higher-order cognitive skills and influenced student perceptions.

According to the study, the research took place in the Department of Physiology at a tertiary care hospital in Rajkot, Gujarat, India, between February 17, 2023, and October 31, 2023.

The researchers first administered a validated 30-item multiple-choice test focused on application and analysis, then asked students to create exhibits about sensory pathways, reflexes, micturition, and the automatic bladder. The researchers administered the same test after the exhibition and collected questionnaire responses, open-ended feedback, and focus group data.

According to the study, the qualitative component combined deductive thematic analysis of all 50 feedback forms with inductive thematic analysis of a focus group transcript. The researchers used independent review, consensus discussions, and investigator triangulation to strengthen credibility.

One student summarized the perceived value of the activity by saying, "Learning through such tasks is way better and easier than anything else because this is an application-based learning method."

Findings Snapshot: AI Qualitative Analysis Opportunities

Date or stage	Metric	Value	Research implication
February 17, 2023	Students included	50 first-year MBBS students	A defined participant group supported a focused comparison of quantitative and qualitative evidence.
February 18, 2023	Teams formed	4 teams of 12 or 13 students	Team-level analysis could reveal how collaboration and task division influenced experiences.
2023 intervention	Model-building period	3 weeks	Time pressure and planning could be coded as contextual factors in student feedback.
2023 post-intervention	Median test score	16 after the intervention versus 12 before it, p < 0.01	The quantitative result provided a measurable outcome for the qualitative findings to explain.
2023 focus group	Participants and duration	10 students and 96 minutes	A substantial transcript created evidence for inductive theme development.
2023 questionnaire analysis	Feedback reliability	Cronbach's alpha = 0.82	The questionnaire showed reported internal consistency before open-ended responses were interpreted.

What the Student Feedback Reveals Through Qualitative Analysis

How did collaboration affect medical students' learning?

According to the 2026 PLOS One study, collaboration helped students divide work, combine different skills, communicate ideas, and solve practical problems.

One participant said, "The coordination among members, division of tasks at the beginning of the project, and individuals’ dedication towards the role assigned to each one of them, were factors that helped us in model making." This quotation illustrates how thematic analysis can connect a broad theme, collaboration, with specific mechanisms such as role allocation and complementary expertise.

What barriers did students report?

According to the study, students identified limited technical knowledge, difficulty implementing ideas, material procurement, and insufficient project planning as major barriers.

A participant stated, "We did not have a blueprint of the logistics for the materials. Probably the costs would not have escalated." An AI-assisted qualitative workflow can surface related codes such as logistics, resources, cost, deadlines, and planning, while researchers verify whether those codes accurately represent the transcript.

What learning gains did students describe?

According to the study, students reported clearer concepts, deeper learning, improved application of theory, better memory, teamwork, communication, and problem-solving.

Another participant said, "Because we created a model, we could understand accurately. Holding the model in the hand lent clarity to the concepts." The quotation shows why frequency counts alone are insufficient: researchers need thematic interpretation to explain how a physical activity produced perceived understanding.

How Evidano Helps With AI Qualitative Analysis in Medical Education

Problem: Focus group transcripts are slow to review

Evidano is an AI-powered qualitative data analysis platform that helps researchers analyze interviews, focus groups, open-ended surveys, and documents.

Researchers can use Evidano to ingest transcripts and organize recurring ideas through thematic, content, frequency, and cross-segment analyses. The Evidano features page describes the platform's analysis capabilities for qualitative research workflows.

Problem: Themes must remain connected to participant evidence

Evidano can help researchers move from codes and themes to supporting quotations by providing AI chat over uploaded documents and analyses.

For a study like the 2026 PLOS One research, a researcher could ask which excerpts support themes such as collaboration, faculty support, planning, or learning gains, then review the original transcript before publication.

Problem: Educators need to compare student groups and responses

Evidano supports cross-segment analysis, which can help researchers compare feedback by team, intervention group, course, demographic segment, or other study-defined categories.

Cross-segment analysis does not replace statistical testing or methodological judgment, but it can help researchers identify where experiences converge or differ and decide which patterns warrant closer examination.

Problem: Audio data must become usable research text

Evidano provides transcription with options such as custom dictionaries and PII redaction, which are relevant when medical education teams begin with recorded focus groups or interviews.

Researchers should still validate transcripts, translations, codes, and quotations against the source audio or documents before using them in a manuscript.

FAQ: AI Qualitative Analysis in Medical Education

What is AI qualitative analysis in medical education?

AI qualitative analysis in medical education uses machine learning or large language model tools to help organize, code, summarize, compare, and retrieve evidence from educational research data.

The 2026 PLOS One study demonstrates the type of material that can benefit from this workflow, including 50 open-ended feedback forms and a 96-minute focus group transcript.

How did the PLOS One study analyze student feedback?

The PLOS One study used deductive thematic analysis for 50 feedback forms and inductive thematic analysis for a focus group transcript.

The researchers began with three broad categories for the feedback forms, enabling factors, hindering factors, and learning gains, then developed themes and categories from the focus group data.

What were the main findings about physical exhibits?

The study found that median higher-order cognitive test scores increased from 12 before the activity to 16 afterward, with p < 0.01.

The qualitative findings indicated that students valued practical application, conceptual clarity, collaboration, faculty guidance, and the opportunity to solve problems together, while reporting challenges involving planning, expertise, time, and materials.

Can AI replace a medical education qualitative researcher?

AI can accelerate organization and synthesis, but AI cannot replace researcher judgment, ethical oversight, contextual interpretation, or responsibility for the final claims.

Researchers should check AI-generated codes, themes, summaries, and quotations against the original data and document how AI was used.

What should researchers verify before publishing AI-assisted findings?

Researchers should verify transcript accuracy, participant anonymization, translation quality, code definitions, theme boundaries, quotation fidelity, and the connection between evidence and conclusions.

The 2026 PLOS One study provides a useful standard because its authors described transcription validation, independent review, consensus discussions, and investigator triangulation.

Conclusion and Next Steps for Medical Education Researchers

The November 5, 2026, PLOS One study shows how quantitative outcomes and student narratives can jointly explain the value and limits of active learning in medical education.

The study's 50 participants improved their median test score from 12 to 16, while qualitative findings identified collaboration, practical application, faculty support, and planning as central parts of the learning experience.

AI qualitative analysis can help medical education researchers process transcripts and open-ended feedback more consistently, but researchers must retain responsibility for methodological decisions and evidence verification.

Evidano can help teams organize mixed qualitative datasets, identify themes, compare segments, and retrieve supporting evidence. Try Evidano for free and build a faster, auditable qualitative research workflow.

Topics

AI qualitative analysis in medical education
qualitative analysis of focus groups
AI thematic analysis
medical education research
mixed methods research

Keep reading

Browse all articles