Evaluating AI Proficiency in Nuclear Cardiology: Large Language Models take on the Board Preparation Exam.
Valerie BuiloffAakash ShanbhagRobert Jh MillerDamini DeyJoanna X LiangKathleen FloodJamieson M BourquePanithaya ChareonthaitaweeLawrence M PhillipsPiotr J SlomkaPublished in: medRxiv : the preprint server for health sciences (2024)
GPT-4o demonstrated superior performance among the four LLMs, achieving scores likely within or just outside the range required to pass a test akin to the CBNC examination. Although improvements in medical image interpretation are needed, GPT-4o shows potential to support physicians in answering text-based clinical questions.