Feasibility and Educational Value of Clinical Cases Generated Using Large Language Models

Abstract

In medical education, case-based learning (CBL) is a fundamental method for training healthcare professionals across different levels of expertise. This approach hinges on using authentic or fabricated clinical cases to bridge the gap between theoretical knowledge and its practical application. It fosters active engagement and knowledge application among learners in healthcare domains. While creating effective cases demands substantial clinical understanding and time investment, the integration of Generative Artificial Intelligence (AI) presents a promising solution to this challenge. AI can efficiently analyze extensive medical data to generate diverse and realistic clinical scenarios, continuously updating case content based on emerging medical literature and guidelines. This study explores AI-generated cases' feasibility and educational value in continuing medical education, focusing on COVID-19 scenarios tailored for the MENA region. Results indicate the potential of AI-generated cases to foster engagement and critical thinking among learners, suggesting their suitability for different levels of education. This study highlights the advantages of integrating AI into CBL and emphasizes the need for future efforts to tackle obstacles and facilitate its successful adoption.

Keywords: Artificial Intelligence (AI); Case-Based Learning (CBL); Clinical cases; Medical Education.