ChatGPT Conquers the Saudi Medical Licensing Exam: Exploring the Accuracy of Artificial Intelligence in Medical Knowledge Assessment and Implications for Modern Medical Education

Abstract

Background The application of artificial intelligence (AI) in education is undergoing rapid advancements, with models such as ChatGPT-4 showing potential in medical education. This study aims to evaluate the proficiency of ChatGPT-4 in answering Saudi Medical Licensing Exam (SMLE) questions. Methodology A dataset of 220 questions across four medical disciplines was used. The model was trained using a specific code to answer the questions accurately, and its performance was assessed using key performance indicators, difficulty level, and exam sections. Results ChatGPT-4 demonstrated an overall accuracy of 88.6%. It showed high proficiency with <i>Easy</i> and <i>Average</i> questions, but accuracy decreased for <i>Hard</i> questions. Performance was consistent across all disciplines, indicating a broad knowledge base. However, an error analysis revealed areas for further refinement, particularly with category (Option) A questions across all sections. Conclusions This study underscores the potential of ChatGPT-4 as an AI-assisted tool in medical education, demonstrating high proficiency in answering SMLE questions. Future research is recommended to expand the scope of training and evaluation as well as to enhance the model's performance on complex clinical questions.