MedQA-CS: Benchmarking Large Language Models Clinical Skills Using an AI-SCE Framework

Yao, Zonghai, Zhang, Zihao, Tang, Chaolong, Bian, Xingyu, Zhao, Youxia, Yang, Zhichao, Wang, Junda, Zhou, Huixue, Jang, Won Seok, Ouyang, Feiyun, Yu, Hong

arXiv.org Artificial Intelligence 

Artificial intelligence (AI) and large language models (LLMs) in healthcare require advanced clinical skills (CS), yet current benchmarks fail to evaluate these comprehensively. We introduce MedQA-CS, an AI-SCE framework inspired by medical education's Objective Structured Clinical Examinations (OSCEs), to address this gap. MedQA-CS evaluates LLMs through two instruction-following tasks, LLM-as-medical-student and LLM-as-CS-examiner, designed to reflect real clinical scenarios. Our contributions include developing MedQA-CS, a comprehensive evaluation framework with publicly available data and expert annotations, and providing the quantitative and qualitative assessment of LLMs as reliable judges in CS evaluation. Our experiments show that MedQA-CS is a more challenging benchmark for evaluating clinical skills than traditional multiple-choice QA benchmarks (e.g., MedQA). Combined with existing benchmarks, MedQA-CS enables a more comprehensive evaluation of LLMs' clinical capabilities for both open- and closed-source LLMs.