2025 ISAKOS Biennial Congress Paper
Evaluating ChatGPT’s Performance in Answering Patients’ Questions Relating to Femoroacetabular Impingement Syndrome and Arthroscopic Hip Surgery
David Slawaska-Eng, MDCM, Hamilton, Ontario CANADA
Yoan Bourgeault-Gagnon, MD, FRCSC, Sherbrooke, Quebec CANADA
Dan Cohen, MD, Hamilton CANADA
Thierry Pauyo, MD, FRCSC, Montreal, QC CANADA
Etienne Belzile, MD, FRCSC, Quebec, QC CANADA
Olufemi R. Ayeni, MD, PhD, MSc, FRCSC, Hamilton, ON CANADA
McMaster University, Hamilton, Ontario, CANADA
FDA Status Not Applicable
Summary
Both versions of ChatGPT provided mostly accurate responses to FAQs on FAI and arthroscopic surgery, with no significant difference between the versions. The findings suggest potential utility of ChatGPT in patient education, though cautious implementation and further evaluation are recommended due to variability in response accuracy and low power of the study.
Abstract
Purpose
This study aimed to evaluate the accuracy of ChatGPT in answering patient questions about femoroacetabular impingement (FAI) and arthroscopic hip surgery, comparing the performance of versions ChatGPT-3.5 and ChatGPT-4.
Methods
Twelve frequently asked questions (FAQs) relating to FAI were selected and posed to ChatGPT-3.5 and ChatGPT-4. Responses were assessed for accuracy by three hip arthroscopy surgeons using a four-tier grading system. Statistical analyses included Wilcoxon signed-rank tests and Gwet's AC2 coefficient for interrater agreement corrected for chance and employing quadratic weights.
Results
Median ratings for responses ranged from "excellent not requiring clarification" to "satisfactory requiring moderate clarification." No responses were rated as "unsatisfactory requiring substantial clarification." Median accuracy scores were 2 (range 1-3) for ChatGPT-3.5 and 1.5 (range 1-3) for ChatGPT-4, with 25% of ChatGPT-3.5's responses and 50% of ChatGPT-4's responses rated as "excellent." There was no statistical difference in performance between the two versions (p = 0.279) although ChatGPT-4 showed a tendency towards higher accuracy in some areas. Interrater agreement was substantial for ChatGPT-3.5 (Gwet’s AC2 = 0.79 [95%CI = 0.6 – 0.94]) and moderate to substantial for ChatGPT-4 (Gwet’s AC2 = 0.65 [95%CI = 0.43 – 0.87]).
Conclusion
Both versions of ChatGPT provided mostly accurate responses to FAQs on FAI and arthroscopic surgery, with no significant difference between the versions. The findings suggest potential utility of ChatGPT in patient education, though cautious implementation and further evaluation are recommended due to variability in response accuracy and low power of the study. The study highlights the potential of large language models like ChatGPT to enhance patient understanding of complex orthopedic conditions and surgical options, suggesting their supplementary role in patient education alongside traditional methods.