Overcoming the Limitations of Standardized Patients Through Dynamic CPX Scenario Automation and Multimodal Clinical...

This study addresses the limitations of Standardized Patients (SPs) in Traditional Korean Medicine (TKM) by developing an AI-driven CPX platform. By integrating Large Language Models (LLMs) with Retrieval-Augmented Generation (RAG) and multimodal clinical cues, the system automates scenario generation and provides quantitative feedback. Expert validation (N=10) demonstrated high validity with an overall mean score of 4.61/5.0 (SD=0.52) and a Scale-level Content Validity Index (S-CVI/Ave) of 0.98, confirming its effectiveness for clinical training.