Associate Professor Central Michigan University College of Medicine Mt Pleasant, Michigan
Abstract: Medical ethics is a critical component of medical education, with specific learning objectives outlined in both the United States Medical Licensing Examination (USMLE) Content Outlines and the Comprehensive Osteopathic Medical Licensing Examination (COMLEX-USA) Blueprint–the sets of board exams that medical students in the United States must pass in order to achieve medical licensure. However, generating high-quality MCQs for medical ethics presents unique challenges, as ethical reasoning is often perceived as more subjective and less matter-of-fact. While considerable research has examined AI-generated MCQs in clinical and biomedical domains, much of this work has focused on medical knowledge rather than ethics. Additionally, emerging evidence suggests that AI models do not perform as well on medical ethics questions compared to those assessing medical knowledge. The present study will evaluate the performance of five non-OpenAI models—claude 3s, claude 3, gemini, perplexity, and deepseek—in regard to the relevance, clarity, and accuracy of generated ethics-based MCQs.
Keywords: medical education, artificial intelligence, medical ethics
Learning Objectives:
After participating in this conference, attendees should be able to:
At the end of this session, attendees will be able to explain the strengths and weaknesses of AI models in generating ethics-based MCQs for medical education
At the end of this session, attendees will be able to explain the difficulties medical educators face when crafting MCQs for undergraduate medical education
At the end of this session, attendees will be able to explain how AI-generated ethics-based MCQs can be incorporated into medical education
.png)
