Artificial Intelligence Language Models Are Useful Tools for Patients Undergoing Total Ankle Replacement

Abstract

Background

Artificial intelligence (AI) large language models (LLMs), such as Chat Generative Pre-trained Transformer (ChatGPT), have gained traction as both augmentative tools in patient care but also as powerful synthesizing machines. The use of ChatGPT in orthopaedic foot and ankle surgery, particularly as an informative resource for patients, has not been described to date. The purpose of this study was to assess the quality of information provided by ChatGPT in response to commonly asked questions about total ankle replacement (TAR).

Methods

ChatGPT was asked 10 frequently asked questions about TAR in a conversational thread. Responses were recorded without follow-up, and subsequently graded A, B, C, or F, corresponding with “excellent response,” “adequate response needing mild clarification,” “inadequate response needing moderate clarification,” and “poor response needing severe clarification.”

Results

Of the 10 responses, 2 were grade “A,” 6 were grade “B,” 2 were grade “C,” and none were grade “F.” Overall, the LLM provided good-quality responses to the posed prompts. Conclusion. Overall, the provided responses were understandable and representative of the current literature surrounding TAR. This study highlights the potential role LLMs in augmenting patient understanding of foot and ankle operative procedures.

Levels of Evidence:

IV.