An Explorative Assessment of ChatGPT as an Aid in Medical Education: Use it with Caution

Abstract

AbstractObjectiveTo explore the use of ChatGPT by educators and students in a medical school setting.MethodThis study used the public version of ChatGPT launched by OpenAI on November 30, 2022 (https://openai.com/blog/chatgpt/). We employed prompts to ask ChatGPT to 1) generate a content outline for a session on the topics of cholesterol, lipoproteins, and hyperlipidemia for medical students; 2) produce a list of learning objectives for the session; and 3) write assessment questions with and without clinical vignettes related to the identified learning objectives. We assessed the responses by ChatGPT for accuracy and reliability to determine the potential of the chatbot as an aid to educators and as a “know-it-all” medical information provider for students.ResultsChatGPT can function as an aid to educators, but it is not yet suitable as a reliable information resource for educators and medical students.ConclusionChatGPT can be a useful tool to assist medical educators draft course and session content outlines and create assessment questions. At the same time, caution must be taken as ChatGPT is prone to providing incorrect information; expert oversight and caution are necessary to ensure the information generated is accurate and beneficial to students. Therefore, it is premature for medical students to use the current version of ChatGPT as a “know-it-all” information provider. In the future, medical educators should work with programming experts to explore and grow the full potential of AI in medical education.