AI qualitative analysis for medical education can help researchers move from lengthy transcripts and open-ended feedback to defensible themes, representative quotations, and actionable findings. The need is clear in the November 5, 2026, PLOS One study by Rajesh Kathrotia and colleagues, which combined test scores, open-ended responses, and a focus group to evaluate physical exhibit-making among undergraduate medical students. The study found that 50 first-year MBBS students improved their median higher-order cognitive test score from 12 before the intervention to 16 afterward, with p < 0.01. The qualitative findings explained why the intervention appeared useful: students described deeper learning, collaboration, practical application, and planning challenges. This post shows how researchers can use AI-enabled qualitative research workflows to analyze similar education datasets while preserving methodological transparency and human review.
Key Takeaways
According to the PLOS One study on physical exhibits in medical education, collaborative model-making was associated with improved higher-order cognitive test scores and positive student perceptions in a 2023 study published on November 5, 2026.
- The PLOS One researchers studied 50 first-year MBBS students in Rajkot, Gujarat, India, between February 17, 2023, and October 31, 2023.
- The study reported that median post-test scores increased from 12 to 16, and the within-group difference was statistically significant at p < 0.01.
- The qualitative component included open-ended feedback from all 50 students and a 96-minute focus group discussion with 10 purposively selected students.
- The researchers used a deductive thematic analysis for open-ended responses, an inductive thematic analysis for the focus group, and investigator review to strengthen credibility.
- Students identified collaboration and faculty support as enabling factors, while limited technical expertise, material access, logistics, and planning were reported as challenges.
What the Medical Education Study Measured
The PLOS One study measured both learning gains and student experience through an explanatory sequential mixed-methods design. The researchers first administered a 30-item multiple-choice test focused on application and analysis, then analyzed student feedback and conducted a focus group to explain the quantitative results.
The intervention assigned students to four teams of 12 or 13 participants, with each team creating a physical exhibit about a physiology topic. The topics covered ascending sensory pathways, light and conjunctival reflexes, the micturition reflex, and the automatic bladder.
The PLOS One researchers analyzed open-ended feedback against three predefined themes: enabling factors, hindering factors, and learning gains. The researchers also coded the focus group inductively, compared interpretations, resolved discrepancies through consensus, and reviewed the final themes through investigator triangulation.
The study reported that code saturation appeared after approximately 25 of the 50 feedback forms, although the researchers analyzed all 50 forms. The focus group transcript was anonymized, transcribed, and reviewed by multiple members of the research team.
One student described the educational value directly: "Learning through such tasks is way better and easier than anything else because this is an application-based learning method." Another participant said, "It would have been difficult for an individual to make such complex models. Divergent views helped find solutions to the problems."
Medical Education Research Findings Snapshot
| Date or period | Metric | Value | Research implication |
|---|---|---|---|
| February 17, 2023 | Study participants | 50 first-year MBBS students | The PLOS One study examined a complete cohort using convenience sampling. |
| February 17 to October 31, 2023 | Study setting | Department of Physiology, tertiary care hospital in Rajkot, Gujarat | The findings reflect one medical education setting and should not be generalized to all institutions without further research. |
| Three weeks in 2023 | Model-building intervention | Four student teams | The intervention required collaborative planning, construction, faculty mentoring, and exhibition. |
| After the intervention in 2023 | Median test score | 16 post-test versus 12 pre-test | The PLOS One researchers reported significant improvement in higher-order cognitive test performance, p < 0.01. |
| 2023 | Focus group size and duration | 10 students and 96 minutes | The discussion provided detailed context about collaboration, learning, planning, and logistical barriers. |
| November 5, 2026 | Publication | PLoS One, 21(11), e0362387 | The peer-reviewed article provides the source evidence for the mixed-methods findings summarized here. |
Implications for AI-Enabled Qualitative Research in Medical Education
How can researchers preserve both quantitative and qualitative evidence?
Researchers can preserve mixed-methods context by analyzing test scores alongside coded feedback, focus group transcripts, and participant quotations. The PLOS One study demonstrates why this matters: the score increase showed an outcome, while student narratives explained collaboration, practical application, faculty support, and logistical constraints.
An AI-enabled workflow can organize these evidence types into linked themes, segments, quotations, and findings, but researchers should retain the original data, document coding decisions, and validate AI-generated interpretations against the source material.
Why are thematic codes important in student feedback analysis?
Thematic codes are important because they turn recurring statements into an auditable structure for comparing experiences across participants or groups. The PLOS One researchers used enabling factors, hindering factors, and learning gains as a predefined framework for open-ended feedback, then used inductive coding for the focus group.
AI can accelerate first-pass coding and reveal co-occurring concepts such as collaboration, faculty guidance, technical knowledge, planning, and resource access. Human researchers remain responsible for deciding whether the codes accurately represent participant meaning.
What should medical education researchers watch for when using AI?
Medical education researchers should watch for loss of context, overconfident theme labeling, privacy risks, translation errors, and unsupported claims. The PLOS One study anonymized participants and used multiple researchers for review, providing a useful model for responsible qualitative quality control.
Researchers should treat AI output as an analytical aid rather than a substitute for methodological judgment, participant protection, reflexivity, or transparent reporting.
How Evidano Supports AI Qualitative Analysis for Medical Education
Problem: Long focus group transcripts slow down analysis
Evidano is an AI-powered qualitative data analysis platform that helps researchers analyze interviews, focus groups, open-ended surveys, and research documents.
Evidano can ingest transcripts and documents, then support thematic, content, frequency, and cross-segment analyses. Researchers can use AI chat over their source material to locate evidence for questions such as how students describe teamwork, faculty mentoring, or barriers to participation.
Researchers can review the relevant Evidano qualitative research features before building a workflow for medical education feedback.
Problem: Student feedback contains repeated and overlapping concepts
Evidano can help organize recurring concepts into thematic structures, code hierarchies, and subcodes. Word clouds, co-occurrence networks, and hierarchical code visualizations can help researchers inspect relationships among themes such as collaboration, planning, technical expertise, and learning gains.
The PLOS One study’s predefined themes provide an example of how a research team can combine a deductive framework with inductive findings from a focus group.
Problem: Mixed-language or recorded discussions require preparation
Evidano provides transcription with custom dictionaries and PII redaction, which can support the preparation of recorded interviews and focus groups for analysis. Evidano also provides translation with custom dictionaries when research teams need to preserve domain-specific terminology across languages.
Researchers should still verify transcripts and translations against recordings or source documents, especially when participant wording is central to the interpretation.
Problem: Researchers need defensible, privacy-conscious workflows
Evidano encrypts data and does not use customer data to train third-party models, according to Evidano’s platform information. Researchers should review institutional requirements and the Evidano data security information before uploading medical education research data.
A defensible workflow should combine secure storage, de-identification, documented prompts, human review, and direct links between themes and supporting quotations.
FAQ: AI Qualitative Analysis for Medical Education
What did the 2026 PLOS One study find about physical exhibits in medical education?
+
The 2026 PLOS One study found that 50 undergraduate medical students had higher median higher-order cognitive test scores after creating physical physiology exhibits, increasing from 12 before the intervention to 16 afterward with p < 0.01.
The researchers’ qualitative findings indicated that students associated the activity with deeper learning, theory-to-practice application, teamwork, and improved understanding, while also reporting planning and resource challenges.
How was qualitative data analyzed in the medical education study?
+
The researchers analyzed open-ended feedback deductively using three themes, enabling factors, hindering factors, and learning gains, and analyzed the focus group transcript inductively.
The PLOS One team reported repeated reading, descriptive coding, independent review, consensus resolution, investigator triangulation, and analysis of all 50 feedback forms.
Can AI perform thematic analysis of medical student feedback?
+
AI can support thematic analysis of medical student feedback by identifying candidate codes, grouping related statements, comparing segments, and retrieving representative quotations.
The PLOS One study’s use of predefined themes, inductive focus group analysis, anonymization, and researcher review shows why AI-generated themes should be checked against the original participant data.
What data can researchers analyze with AI qualitative research software?
+
Researchers can analyze interview transcripts, focus group transcripts, open-ended survey responses, research papers, reports, and other qualitative documents with AI qualitative research software.
For a mixed-methods project like the PLOS One study, researchers can combine structured survey or test data with narrative feedback and transcripts, provided the analysis preserves the distinction between quantitative measurements and qualitative interpretation.
What are the limitations of the PLOS One medical education study?
+
The PLOS One researchers reported that the study did not measure long-term information retention, long-term problem-solving or critical-thinking changes, or individual outcomes within the team-based intervention.
The researchers also identified the single-setting design, convenience sampling, absence of a comparator group, and need for future multicenter and randomized research as limitations.
Conclusion and Next Steps
The November 5, 2026, PLOS One study shows how mixed-methods research can connect measurable learning gains with students’ explanations of collaboration, practical application, faculty support, and implementation barriers. AI qualitative analysis can help medical education researchers process similar transcripts and open-ended responses faster while preserving searchable evidence, thematic structure, and cross-segment comparisons.
The strongest workflow combines AI-assisted coding with anonymization, transparent methods, direct quotation review, and researcher judgment. To analyze medical education feedback and mixed-methods research data more efficiently, try Evidano for free.
Topics
- AI qualitative analysis for medical education
- AI thematic analysis
- qualitative research in medical education
- mixed-methods research analysis
- student feedback analysis
Keep reading
- Commentary on NewsCommunity Health Insights: AI Qualitative Data AnalysisLearn how AI qualitative data analysis clarifies community health interviews, mechanisms, and equity insights, with lessons from the 2026 ELLY study for researchers.
- Commentary on NewsGlobal Health Roundtables: AI Qualitative ResearchLearn how AI-enabled qualitative research can strengthen global health roundtables, from inclusive dialogue to faster thematic synthesis. Try Evidano securely today.
- Commentary on NewsWhat ELLY Reveals: AI Thematic AnalysisSee how AI thematic analysis turns ELLY interview data into actionable insights on wellbeing, social connection, and community health research.