An Artificial Intelligence Chatbot is an Accurate and Useful Online Patient Resource Prior to Total Knee Arthroplasty. Academic Article uri icon

Overview

abstract

  • BACKGROUND: Online information is a useful resource for patients seeking advice on their orthopaedic care. While traditional websites provide responses to specific frequently asked questions (FAQs), sophisticated artificial intelligence (AI) tools may be able to provide the same information to patients in a more accessible manner. Chat Generative Pre-Trained Transformer (ChatGPT) is a powerful AI chatbot that has been shown to effectively draw on its large reserves of information in a conversational context with a user. The purpose of this study was to assess the accuracy and reliability of ChatGPT-generated responses to FAQs regarding total knee arthroplasty (TKA). METHODS: We distributed a survey that challenged arthroplasty surgeons to identify which of two responses to FAQs on our institution's website was human-written and which was generated by ChatGPT. All questions were TKA-related. The second portion of the survey investigated the potential to further leverage ChatGPT to assist with translation and accessibility as a means to better meet the needs of our diverse patient population. RESULTS: Surgeons correctly identified the ChatGPT-generated responses 4 out of 10 times on average (range: 0-7). No consensus was reached on any of the responses to the FAQs. Additionally, over 90% of our surgeons strongly encouraged the use of ChatGPT to more effectively accommodate the diverse patient populations that seek information from our hospital's online resources. CONCLUSION: ChatGPT provided accurate, reliable answers to our website's FAQs. Surgeons also agreed that ChatGPT's ability to provide targeted, language-specific responses to FAQs would be of benefit to our diverse patient population.

publication date

  • February 11, 2024

Research

keywords

  • Arthroplasty, Replacement, Knee
  • Artificial Intelligence
  • Internet

Identity

Digital Object Identifier (DOI)

  • 10.1016/j.arth.2024.02.005

PubMed ID

  • 38350517