Evaluating the Diagnostic Accuracy of ChatGPT-4 Omni and ChatGPT-4 Turbo in Identifying Melanoma: Comparative Study.

Journal: JMIR dermatology
Published Date: Mar 21, 2025

Abstract

ChatGPT is increasingly used in healthcare. Fields like dermatology and radiology could benefit from ChatGPT's ability to help clinicians diagnose skin lesions. This study evaluates the accuracy of ChatGPT in diagnosing melanoma. Our analysis indicates that ChatGPT cannot be used reliably to diagnose melanoma, and further improvements are needed to reach this capability.

Authors

  • Samantha S Sattler
    Department of Dermatology, Stony Brook University Hospital, Stony Brook, NY, United States.
  • Nitin Chetla
    University of Virginia School of Medicine, Charlottesville, VA, United States.
  • Matthew Chen
    Renaissance School of Medicine, Stony Brook University, Stony Brook, NY, United States.
  • Tamer Rajai Hage
    Virginia Tech, Blacksburg, VA, 24061, United States, 1 7038948362.
  • Joseph Chang
    University of Passau, Passau, Germany.
  • William Young Guo
    Department of Dermatology, Stony Brook University Hospital, Stony Brook, NY, United States.
  • Jeremy Hugh
    Department of Dermatology, Stony Brook University Hospital, Stony Brook, NY, United States.

Keywords

External Resources

Popular Topics
Recent Journals