AI MedEd ObservatoryWhat Can AI Do in Medical Education? An observatory

Evidence, prompts, checklists, and practical interpretation for assessment, feedback, scoring, and teaching materials.

Mantra: Evidence before automation. Judgment before adoption.Base path /ai-meded-observatory

What can AI do for generating feedback?

AI can generate immediate, task-specific formative feedback for undergraduate medical students, especially in simulated clinical encounters and text-based assessments. Current evidence suggests feasibility and some short-term learning gains, but not clinical behavior or patient-care impact.

Evidence summary

A scoping review included 42 studies found through PubMed and Web of Science searches up to 10 September 2025. Most studies used OpenAI GPT models and came from Global North settings. Only 8 studies were randomized controlled trials. Outcomes were limited: 22 studies had no student data, 10 measured student reactions, 10 assessed learning, and none measured clinical behavior or patient-level effects. LLM feedback often appeared useful or comparable to expert feedback for short-term learning, but accuracy was variable.

Practical starting points

  • Use for low-stakes formative feedback, not summative decisions
  • Use with faculty oversight, especially for clinical reasoning
  • Ask students to compare AI feedback with course expectations or expert guidance
  • Check outputs for accuracy before using them in teaching materials

Last updated: July 5, 2026

Collaboration

Planning a study related to this question?

If you have a mature study idea, drafted protocol, or ethics-stage project related to this question or another gap in AI and medical education, you can share a collaboration proposal. Please include enough detail to assess fit, feasibility, and possible collaboration. Not every proposal will lead to collaboration.

Share a collaboration proposal

Related articles

Selected studies

2026Scoping review

Applications and Outcomes of Large‑Language‑Model‑Generated Feedback in Undergraduate Medical Education: A Scoping Review

Yavuz Selim Kıyak, Tuğba İş-Kara, Emre Emekli · Medical Science Educator

This scoping review maps 42 peer-reviewed studies on LLM-generated feedback in undergraduate medical education, showing that LLMs are being used across MCQs, clinical reasoning, simulated patients, communication skills, academic writing, and self-directed learning. Evidence mainly supports feasibility and short-term learning or learner reaction, not behavior change or patient outcomes.

Related subquestions: What can AI do for generating feedback?

Published prompts

Related prompt architectures

No published prompts are linked yet.

Practical guides

Linked guides

No guides are linked yet.