ChatGPT 4.0's efficacy in the self-diagnosis of non-traumatic hand conditions.

Abstract

Background: With advancements in artificial intelligence, patients increasingly turn to generative AI models like ChatGPT for medical advice. This study explores the utility of ChatGPT 4.0 (GPT-4.0), the most recent version of ChatGPT, as an interim diagnostician for common hand conditions. Secondarily, the study evaluates the terminology GPT-4.0 associates with each condition by assessing its ability to generate condition-specific questions from a patient's perspective.

Methods: Five common hand conditions were identified: trigger finger (TF), Dupuytren's Contracture (DC), carpal tunnel syndrome (CTS), de Quervain's tenosynovitis (DQT), and thumb carpometacarpal osteoarthritis (CMC). GPT-4.0 was queried with author-generated questions. The frequency of correct diagnoses, differential diagnoses, and recommendations were recorded. Chi-squared and pairwise Fisher's exact tests were used to compare response accuracy between conditions. GPT-4.0 was prompted to produce its own questions. Common terms in responses were recorded.

Results: GPT-4.0's diagnostic accuracy significantly differed between conditions (p < 0.005). While GPT-4.0 diagnosed CTS, TF, DQT, and DC with >95 % accuracy, 60 % (n = 15) of CMC queries were correctly diagnosed. Additionally, there were significant differences in providing of differential diagnoses (p < 0.005), diagnostic tests (p < 0.005), and risk factors (p < 0.05). GPT-4.0 recommended visiting a healthcare provider for 97 % (n = 121) of the questions. Analysis of ChatGPT-generated questions showed four of the ten most used terms were shared between DQT and CMC.

Conclusions: The results suggest that GPT-4.0 has potential preliminary diagnostic utility. Future studies should further investigate factors that improve or worsen AI's diagnostic power and consider the implications of patient utilization.