Exploring the role of artificial intelligence in Turkish orthopedic progression exams

Abstract

Objective: The aim of this study was to evaluate and compare the performance of the artificial intelligence (AI) models ChatGPT-3.5, ChatGPT-4, and Gemini on the Turkish Specialization Training and Development Examination (UEGS) to determine their utility in medical education and their potential to improve patient care. Methods: This retrospective study analyzed responses of ChatGPT-3.5, ChatGPT-4, and Gemini to 1000 true or false questions from UEGS administered over 5 years (2018-2023). Questions, encompassing 9 orthopedic subspecialties, were categorized by 2 independent residents, with discrepancies resolved by a senior author. Artificial intelligence models were restarted for each query to prevent data retention. Performance was evaluated by calculating net scores and comparing them to orthopedic resident scores obtained from the Turkish Orthopedics and Traumatology Education Council (TOTEK) database. Statistical analyses included chi-squared tests, Bonferroni-adjusted Z tests, Cochran's Q test, and receiver operating characteristic (ROC) analysis to determine the optimal question length for AI accuracy. All AI responses were generated independently without retaining prior information. Results: Significant differences in AI tool accuracy were observed across different years and subspecialties (P < .001). ChatGPT-4 consistently outperformed other models, achieving the highest overall accuracy (95% in specific subspecialties). Notably, ChatGPT-4 demonstrated superior performance in Basic and General Orthopedics and Foot and Ankle Surgery, while Gemini and ChatGPT-3.5 showed variability in accuracy across topics and years. Receiver operating characteristic analysis revealed a significant relationship between shorter letter counts and higher accuracy for ChatGPT-4 (P = .002). ChatGPT-4 showed significant negative correlations between letter count and accuracy across all years (r=-0.099, P = .002), outperformed residents in basic and general orthopedics (P = .015) and trauma (P = .012), unlike other AI models. Conclusion: The findings underscore the advancing role of AI in the medical field, with ChatGPT-4 demonstrating significant potential as a tool for medical education and clinical decision-making. Continuous evaluation and refinement of AI technologies are essential to enhance their educational and clinical impact.