An Agentic AI Framework for Training General Practitioner Student Skills
🤖 AI Summary
Current virtual simulated patients (VSPs) suffer from low medical accuracy, poor role consistency, inflexible scenario generation, and absence of structured educational feedback. To address these limitations, this study proposes an agent-based AI framework tailored for general practice medical students’ skill training. The framework introduces a novel decoupled architecture comprising three modules: scenario control, interaction control, and standardized assessment. It integrates evidence-based case generation, persona-aware RAG-enhanced dialogue, medical knowledge graph alignment, and dual-dimensional evaluation modeling—spanning communication competence and clinical reasoning. Built upon large language models and the agent paradigm, the system enables high-fidelity, configurable, and pedagogically grounded VSP training. In empirical evaluation with 14 medical students, the system achieved high ratings in dialogue authenticity, case consistency, persona stability, and feedback utility, demonstrating excellent usability.
Application Category
📝 Abstract
Advancements in large language models offer strong potential for enhancing virtual simulated patients (VSPs) in medical education by providing scalable alternatives to resource-intensive traditional methods. However, current VSPs often struggle with medical accuracy, consistent roleplaying, scenario generation for VSP use, and educationally structured feedback. We introduce an agentic framework for training general practitioner student skills that unifies (i) configurable, evidence-based vignette generation, (ii) controlled persona-driven patient dialogue with optional retrieval grounding, and (iii) standards-based assessment and feedback for both communication and clinical reasoning. We instantiate the framework in an interactive spoken consultation setting and evaluate it with medical students ($mathbf{N{=}14}$). Participants reported realistic and vignette-faithful dialogue, appropriate difficulty calibration, a stable personality signal, and highly useful example-rich feedback, alongside excellent overall usability. These results support agentic separation of scenario control, interaction control, and standards-based assessment as a practical pattern for building dependable and pedagogically valuable VSP training tools.
Problem
Research questions and friction points this paper is trying to address.
Enhancing virtual simulated patients for medical education accuracy
Improving roleplaying consistency and scenario generation in training
Providing structured feedback for communication and clinical reasoning
Innovation
Methods, ideas, or system contributions that make the work stand out.
Agentic framework for GP training
Configurable evidence-based vignette generation
Standards-based assessment and feedback
🔎 Similar Papers
No similar papers found.
