Chat-GPT adequate response to FAQs about thumb arthritis

Abstract

The purpose of this study is to evaluate ChatGPT responses to common questions patients have regarding thumb carpometacarpal osteoarthritis (CMC OA). Ten frequently asked questions (FAQs) regarding CMC OA were chosen from FAQs found on the websites of major institutions. These were presented to ChatGPT and responses were rated as “excellent response not requiring clarification,” “satisfactory requiring minimal clarification,” “satisfactory requiring moderate clarification,” or “unsatisfactory requiring substantial clarification.” 3 responses were considered excellent requiring no clarification, 4 responses were satisfactory requiring minimal clarification, 3 were satisfactory requiring moderate clarification, and no answer was considered unsatisfactory requiring substantial clarification. As hypothesized, ChatGPT provided generally information to common questions around CMC OA. Although clarification was often needed, responses were satisfactory for providing generalized information about clinical presentation and management (conservative vs surgical).

Ähnliche Arbeiten