A French OSCE Dialogue Dataset and Controllable Virtual Patient System for Clinical Training

Researchers introduced a French OSCE dialogue dataset with 240 student-patient interactions and developed a controllable LLM-based pipeline to generate synthetic OSCE dialogues for clinical training. The system includes modular components for patient fidelity and a multi-level evaluation framework, with an interactive prototype allowing students to practice with a virtual patient and receive automatic feedback.

arXiv:2606.28526v1 Announce Type: new Abstract: The clinical and communication skills of medical students are commonly assessed through Objective Structured Clinical Examinations OSCEs , which consist of brief scenario-driven simulations of doctor-patient interactions. However, training is often limited by the low availability of human standardized patients, motivating the development of realistic virtual patients VPs . To address this gap, we introduce a French OSCE dialogue dataset comprising 240 student-patient training interactions. We build upon it a controllable LLM-based pipeline to generate synthetic OSCE dialogues. The pipeline integrates modular components, such as retrieval-based grounding and a reflection loop, to ensure patient fidelity, coherence, and realism. Additionally, we propose a multi-level evaluation framework assessing patient simulation quality, student performance, and linguistic quality, using an LLM-as-a-Judge approach. Experiments suggest that controllability modules generally improve patient fidelity and student evaluation consistency. Finally, we implement an interactive prototype in which students can practice with a VP and receive automatic feedback.