ChatGPT Can Offer At Least Satisfactory Responses to Common Patient Questions Regarding Hip Arthroscopy.

ABSTRACT

PURPOSE: To assess the accuracy of answers provided by ChatGPT 4.0 (an advanced language model developed by OpenAI) regarding 25 common patient questions about hip arthroscopy. METHODS: ChatGPT 4.0 was presented with 25 common patient questions regarding hip arthroscopy with no follow-up questions and repetition. Each response was evaluated by two board-certified orthopaedic sports medicine surgeons, independently. Responses were rated as scores 1, 2, 3 and 4 corresponded to "excellent response not requiring clarification", "satisfactory requiring minimal clarification", "satisfactory requiring moderate clarification", and "unsatisfactory requiring substantial clarification", respectively. RESULTS: Twenty responses were rated "excellent" and 2 responses were rated "satisfactory requiring minimal clarification" by both of reviewers. Responses to questions "What kind of anesthesia is used for hip arthroscopy" and "What is the average age for hip arthroscopy?" were the two that both reviewers rated as "satisfactory requiring minimal clarification". None of the responses were rated as "satisfactory requiring moderate clarification" or "unsatisfactory" by either of the reviewers. CONCLUSIONS: ChatGPT 4.0 provides at least satisfactory responses to patient questions regarding hip arthroscopy. Under the supervision of an orthopaedic sports medicine surgeon it could be used as a supplementary tool for patient education. CLINICAL RELEVANCE This study compared the answers of ChatGPT to patients' questions regarding hip arthroscopy with the current literature. As ChatGPT have gained popularity among patients, the study aimed to find if the responses patients get from this chatbot is compatible with the up-to-date literature.