Expert evaluation of ChatGPT-generated responses to patient questions in conventional and fast-track total knee arthroplasty - Takeaways - MDSpire
Coming Soon: Introducing MDSpire News. Learn more
Conexiant’s news site is now MDSpire News. Learn more

Expert Assessment of ChatGPT’s Answers to Patient Questions About Standard and Fast-Track Total Knee Arthroplasty

  • By

  • Bartosz Maciag

  • Dawid Jegierski

  • Andrzej Frankiewicz

  • Piotr Tarkowski

  • Krystian Żarnovsky

  • Filip Mietlicki

  • Artur Stolarczyk

  • October 15, 2026

Share

  • 1

    This cross-sectional study assessed ChatGPT’s answers to 50 conventional TKA questions and 20 fast-track TKA questions.

  • 2

    Three high-volume arthroplasty surgeons independently rated each answer for accuracy, completeness, safety, and readability on 5-point scales.

  • 3

    The fast-track questions addressed early mobilization and discharge, multimodal analgesia, selective use of drains and urinary catheters, and postdischarge safety.

  • 4

    Experts also recorded whether each answer required specialist correction or contained potentially unsafe patient information.

  • 5

    Because the question sets were developed using different methods, their comparison was not intended to assess equivalence or noninferiority.

Original Source(s)

Related Content