Evaluating the performance of ChatGPT in preventive and social medicine in medical university examination

Abstract

Artificial Intelligence (AI) for community health holds transformative potential, offering data-driven insights, virtual health advisories, and efficient resource allocation for improved healthcare outcomes and population well-being. This study evaluates the potential of ChatGPT 3.5, an AI language model, in preventive and social medicine. Using medical exam questions, ChatGPT demonstrated commendable understanding, scoring 62% and 65% in Paper 1 and Paper 2, respectively. While promising for medical education and public health, caution is advised due to occasional inaccuracies, ethical considerations, and the model's inability to replace human expertise. Refinement efforts are crucial for harnessing ChatGPT's full potential in enhancing medical education and positively impacting public health outcomes. Further research should focus on real-world applications and addressing limitations for responsible integration.