ABSTRACT
PURPOSE: There is increasing interest in the use of digital platforms such as ChatGPT for anatomy education. This study aims to evaluate the efficacy of ChatGPT in providing accurate and consistent responses to questions focusing on musculoskeletal anatomy across various time points (hours and days). METHODS: A selection of 6 Anatomy-related questions were asked to ChatGPT 3.5 in 4 different timepoints. All answers were rated blindly by 3 expert raters for quality according to a 5 -point Likert Scale. Difference of 0 or 1 points in Likert scale scores between raters was considered as agreement and between different timepoints was considered as consistent indicating good reproducibility. RESULTS: There was significant variation in the quality of the answers ranging from extremely good to very poor quality. There was also variation of consistency levels between different timepoints. Answers were rated as good quality (≥ 3 in Likert scale) in 50% of cases (3/6) and as consistent in 66.6% (4/6) of cases. In the low-quality answers, significant mistakes, conflicting data or lack of information were encountered. CONCLUSION: As of the time of this article, the quality and consistency of the ChatGPT v3.5 answers is variable, thus limiting its utility as independent and reliable resource of learning musculoskeletal anatomy. Validating information by reviewing the anatomical literature is highly recommended.
ABSTRACT
PURPOSE: A recent study published in the JMIR Med Educ Journal explored the potential impact of the Generative Pre-Train (ChatGPT), a generative language model, on medical education, research, and practice. In the present study, an interview with ChatGPT was conducted to determine its capabilities and potential for use in anatomy education (AE) and anatomy research (AR). METHODS: The study involved 18 questions asked of ChatGPT after obtaining an online subscription to the 4th edition. The questions were randomly selected and evaluated based on accuracy, relevance, and comprehensiveness. RESULTS: The ChatGPT provided accurate and well-structured anatomical descriptions, including clinical relevance and relationships between structures. The chatbot also offered concise summaries of chapters and helpful advice on anatomical terminology, even with complex terms. However, when it came to anatomical variants and their clinical significance, the chatbot's replies were inadequate unless variants were systematically classified into types. ChatGPT-4 generated multiple-choice quizzes and matching questions of varying difficulty levels, as well as summaries of articles when presented with text. However, the chatbot recognized its limitations in terms of accuracy, as did the authors of the current study. CONCLUSION: ChatGPT-4 can be a valuable interactive educational tool for students in the field of anatomy, encouraging engagement and further questions. However, it cannot replace the critical role of educators and should be used as a complementary tool. Future research should establish guidelines for ChatGPT's optimal use and application in medical education.