An evaluation of AI generated literature reviews in musculoskeletal radiology.

Journal: The surgeon : journal of the Royal Colleges of Surgeons of Edinburgh and Ireland
Published Date: Jan 12, 2024

Abstract

PURPOSE: The use of artificial intelligence (AI) tools to aid in summarizing information in medicine and research has recently garnered a huge amount of interest. While tools such as ChatGPT produce convincing and naturally sounding output, the answers are sometimes incorrect. Some of these drawbacks, it is hoped, can be avoided by using programmes trained for a more specific scope. In this study we compared the performance of a new AI tool (the-literature.com) to the latest version OpenAI's ChatGPT (GPT-4) in summarizing topics that the authors have significantly contributed to.

Authors

  • N Jenko
    Radiology, Royal Orthopaedic Hospital NHS Foundation Trust, Birmingham, UK. Electronic address: Nathan.jenko@nhs.net.
  • S Ariyaratne
    Radiology, Royal Orthopaedic Hospital NHS Foundation Trust, Birmingham, UK.
  • L Jeys
    Orthopaedic Surgery, Royal Orthopaedic Hospital NHS Foundation Trust, Birmingham, UK.
  • S Evans
    Orthopaedic Surgery, Royal Orthopaedic Hospital NHS Foundation Trust, Birmingham, UK.
  • K P Iyengar
    Orthopaedic Surgery, Mersey and West Lancashire Teaching Hospitals NHS Trust, Southport, UK.
  • R Botchu
    Radiology, Royal Orthopaedic Hospital NHS Foundation Trust, Birmingham, UK.

Keywords

External Resources

Popular Topics
Recent Journals