Comparative evaluation of ChatGPT and Gemini feedback in scenario-based clinical reasoning among medical interns

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.

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.

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.

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.