Evaluating ChatGPT Responses to Patient Questions About Total Ankle Arthroplasty
Author Information
Author(s): Artioli Elena, Veronesi Francesca, Mazzotti Antonio, Brogini Silvia, Zielli Simone Ottavio, Giavaresi Gianluca, Faldini Cesare
Primary Institution: IRCCS Istituto Ortopedico Rizzoli Bologna
Hypothesis
Can ChatGPT provide accurate and comprehensive responses to common patient questions regarding total ankle arthroplasty?
Conclusion
ChatGPT demonstrates potential as a tool for responding to common patient questions related to total ankle arthroplasty, offering clear and mostly accurate information.
Supporting Evidence
- ChatGPT's responses were generally satisfactory, requiring minimal clarification.
- The mean accuracy score was 2, indicating satisfactory responses.
- The mean DISCERN score was 51, which is considered good-fair.
- Responses were evaluated by orthopedic surgeons for quality and clarity.
- ChatGPT's performance may improve with ongoing advancements in AI.
Takeaway
ChatGPT can help answer questions about ankle surgery, making it easier for patients to understand their options.
Methodology
Ten common questions were selected by two ankle surgeons, and ChatGPT was used to answer these questions, with responses analyzed for accuracy and clarity.
Potential Biases
Responses may vary based on the available literature and lack clinical judgment.
Limitations
The study only posed questions in English and did not assess variations in responses based on rephrasing or different users.
Digital Object Identifier (DOI)
Want to read the original?
Access the complete publication on the publisher's website