Improving radiology reporting accuracy: use of GPT-4 to reduce errors in reports.

Journal: Abdominal radiology (New York)
Published Date: Jun 27, 2025

Abstract

PURPOSE: Radiology reports are essential for communicating imaging findings to guide diagnosis and treatment. Although most radiology reports are accurate, errors can occur in the final reports due to high workloads, use of dictation software, and human error. Advanced artificial intelligence models, such as GPT-4, show potential as tools to improve report accuracy. This retrospective study evaluated how GPT-4 performed in detecting and correcting errors in finalized radiology reports in real-world settings for abdominopelvic computed tomography (CT) reports.

Authors

  • Connor J Mayes
    Mayo Clinic College of Medicine and Science, Phoenix, USA.
  • Chloe Reyes
    Mayo Clinic, Phoenix, USA.
  • Mia E Truman
    Mayo Clinic Scottsdale, Scottsdale, USA.
  • Christopher A Dodoo
    Mayo Clinic Scottsdale, Scottsdale, USA.
  • Cameron R Adler
    Mayo Clinic, Phoenix, USA.
  • Imon Banerjee
    Mayo Clinic, Department of Radiology, Scottsdale, AZ, USA.
  • Ashish Khandelwal
    Department of Radiology, Mayo Clinic, 200 First St, Rochester, MN, 55902, USA.
  • Lauren F Alexander
    Mayo Clinic Jacksonville, Jacksonville, USA.
  • Shannon P Sheedy
    Mayo Clinic Rochester, Rochester, USA.
  • Cole P Thompson
    Mayo Clinic, Phoenix, USA.
  • Jacob A Varner
    Mayo Clinic, Phoenix, USA.
  • Maria Zulfiqar
    Mayo Clinic, Phoenix, USA.
  • Nelly Tan
    Associate Professor, Department of Radiology, Mayo Clinic, Phoenix, Arizona. Electronic address: tan.nelly@mayo.edu.

Keywords

No keywords available for this article.

External Resources

Popular Topics
Recent Journals