AI-Driven Objective Structured Clinical Examination Generation in Digital Health Education: Comparative Analysis of Three GPT-4o Configurations
Structured prompting strategies, particularly agents' simulation, enhance the reliability and usability of LLM-generated OSCE content. These results support the use of artificial intelligence in medical education, while confirming the need for expert validation.
Authors
- Anita Burgun
- Rosy Tsopra
- Zineb Zouakia
- Emmanuel Logak
- Alan Szymczak
Institutions
- Hôpital Necker-Enfants Malades (FR)
- Inserm (FR)
- Université Paris Cité (FR)
- Sorbonne Paris Cité (FR)
- Assistance Publique – Hôpitaux de Paris (FR)
- Hôpital Européen (FR)
- Institut des Maladies Génétiques Imagine (FR)
Publication Details
- Journal
- JMIR Medical Education
- Published
- 2026-01-15
- DOI
- https://doi.org/10.2196/82116
- Citations
- 1
- Primary Topic
- Artificial Intelligence in Healthcare and Education
- Type
- article
- Field-Weighted Citation Impact
- 17.70