Assessing ChatGPT responses to common patient questions regarding total ankle arthroplasty

Abstract

Purpose

Artificial Intelligence is becoming increasingly integrated into healthcare, making it essential to assess its potential as a reliable information source for patient queries in the ambit of orthopaedic surgery. In literature, it is being employed in foot and ankle surgery and total hip arthroplasty. The aim of the present study was to evaluate the ability of Chat Generative Pretrained Transformer (ChatGPT) version 3.5 to give accurate, complete and comprehensive responses to the most common questions which are usually asked by the patient to the surgeon regarding total ankle arthroplasty.

Methods

Ten most common questions were selected by two ankle surgeons and then ChatGPT was used to answer these questions. The responses were analyzed using an accuracy score and the modified DISCERN score to assess clarity. WordCalc software package (educational-level indices) was used to assess the readability of the responses.

Results

Most of ChatGPT's responses were considered excellent not requiring clarification or satisfactory requiring minimal clarification. Indeed, the accuracy score was 2, suggesting that the overall responses were satisfactory requiring minimal clarification, and DISCERN score mean was 51, which is considered good-fair.

Conclusions

ChatGPT demonstrates potential as a tool for responding to common patient questions related to total ankle arthroplasty, offering clear and mostly accurate information. While its current performance is based on the available literature, ongoing advancements in artificial intelligence may further enhance its utility in healthcare communication. However, further studies are required to evaluate its role more precisely in patient information and clinical settings.

Levels of Evidence

Not applicable.