Generative AI · Education leadership

Actionable companion · Assessment and evidence of learning

From evidence to district action: Comparative evaluation of ChatGPT and Gemini feedback in scenario-based clinical reasoning among medical interns

AI-assisted editorial implementation guide. The district actions are proposed applications, not findings or recommendations attributed to the original authors. No additional peer review is asserted.

Read original paperSearch paper agentCC BY 4.0

Evidence and context

Health-professions education context: test transfer to K–12 rather than assuming it.

Original authors’ abstract, reproduced under the linked source license:

SUMMARY OBJECTIVE: Artificial intelligence tools are increasingly used to provide individualized feedback in medical education. The aim of this study was to compare the quality of feedback generated by ChatGPT and Gemini during scenario-based clinical reasoning activities. METHODS: A convergent mixed-methods study was conducted with 32 medical interns randomly assigned to ChatGPT (n=16) or Gemini (n=16). Following a virtual patient interview on iron deficiency anemia, artificial intelligence-generated feedback was evaluated by interns and medical education specialists using an 11-item rubric assessing clarity, accuracy, structure, identification of strengths and weaknesses, contribution to clinical reasoning, and overall educational value. Quantitative data were analyzed using descriptive statistics and Mann-Whitney U tests, while qualitative data were examined through content analysis. RESULTS: Interns rated ChatGPT slightly higher than Gemini (1.80±0.20 vs. 1.75±0.26), whereas specialists reported similar scores (1.91±0.06 vs. 1.87±0.10). No statistically significant differences were identified (p>0.05). Both systems were perceived as clear, supportive, and constructive; however, insufficient patient-centeredness emerged as a common limitation of both artificial intelligence systems. Qualitative findings indicated that ChatGPT provided more structured and reflective feedback, whereas Gemini offered more concrete examples. Common limitations included insufficient patient-centeredness, lack of systematicity, and occasional unrealistic statements. CONCLUSION: ChatGPT and Gemini generated educationally useful feedback for scenario-based clinical reasoning activities. Although artificial intelligence tools cannot replace expert supervision, they may support personalized learning and reduce faculty workload when used under human oversight.

A 90-day district pilot

  1. Days 1–15 · Appraise. Have the curriculum lead and a teacher read the methods and limitations. Record the study design, sample, comparator, outcomes and evidence gaps. Define a local question that the study can help inform.
  2. Days 16–30 · Design. Redesign one low-stakes assessment: require a first attempt, an AI-assisted revision, a source-check log and a short oral explanation. Use the same rubric for the comparison task. Name an accountable owner and set the baseline, success threshold and budget before implementation.
  3. Days 31–60 · Test. Start with a small voluntary cohort, preserve an accessible non-AI route and require teacher review. Use synthetic or de-identified examples; approve data handling and tool terms through district processes.
  4. Days 61–90 · Decide. Blind-score reasoning, factual accuracy and unaided transfer on a fresh task. Record suspected misconduct separately from demonstrated evidence. Compare with baseline, document uncertainty and stop or revise if learning worsens, access is unequal or critical errors persist.

The board decision brief

Report the learning problem, evidence quality, participating population, total cost including review time, measured benefit, errors, access differences and remaining uncertainties. Make a dated recommendation to stop, revise or expand. A positive perception survey alone does not establish learning improvement.

Attribution and reuse

Hilal Hatice Ülkü; Fulya Torun; Selcen Öncü. Comparative evaluation of ChatGPT and Gemini feedback in scenario-based clinical reasoning among medical interns. Revista da Associação Médica Brasileira (2026-10-12). https://doi.org/10.1590/1806-9282.20260869

Companion prepared 2026-10-30. Original authorship and DOI are preserved. The abstract is an attributed source extract; the implementation plan is new AI-assisted editorial material, offered under the same CC BY 4.0 license. This guide has not undergone independent peer review.