Evaluating the accuracy and relevance of ChatGPT responses to frequently asked questions regarding total knee replacement

Abstract

BackgroundChat Generative Pretrained Transformer (ChatGPT), a generative artificial intelligence chatbot, may have broad applications in healthcare delivery and patient education due to its ability to provide human-like responses to a wide range of patient queries. However, there is limited evidence regarding its ability to provide reliable and useful information on orthopaedic procedures. This study seeks to evaluate the accuracy and relevance of responses provided by ChatGPT to frequently asked questions (FAQs) regarding total knee replacement (TKR).MethodsA list of 50 clinically-relevant FAQs regarding TKR was collated. Each question was individually entered as a prompt to ChatGPT (version 3.5), and the first response generated was recorded. Responses were then reviewed by two independent orthopaedic surgeons and graded on a Likert scale for their factual accuracy and relevance. These responses were then classified into accurate versus inaccurate and relevant versus irrelevant responses using preset thresholds on the Likert scale.ResultsMost responses were accurate, while all responses were relevant. Of the 50 FAQs, 44/50 (88%) of ChatGPT responses were classified as accurate, achieving a mean Likert grade of 4.6/5 for factual accuracy. On the other hand, 50/50 (100%) of responses were classified as relevant, achieving a mean Likert grade of 4.9/5 for relevance.ConclusionChatGPT performed well in providing accurate and relevant responses to FAQs regarding TKR, demonstrating great potential as a tool for patient education. However, it is not infallible and can occasionally provide inaccurate medical information. Patients and clinicians intending to utilize this technology should be mindful of its limitations and ensure adequate supervision and verification of information provided.