AI-generated dermatologic images show deficient skin tone diversity and poor diagnostic accuracy: An experimental study.

Journal: Journal of the European Academy of Dermatology and Venereology : JEADV
Published Date: Jul 16, 2025

Abstract

BACKGROUND: Generative AI models are increasingly used in dermatology, yet biases in training datasets may reduce diagnostic accuracy and perpetuate ethnic health disparities.

Authors

  • Lucie Joerg
    Albany Medical College, Albany, New York, USA.
  • Margaret Kabakova
    Department of Dermatology, State University of New York, Downstate Health Sciences University, Brooklyn, New York, USA.
  • Jennifer Y Wang
    Department of Dermatology, State University of New York, Downstate Health Sciences University, Brooklyn, New York, USA.
  • Evan Austin
    Department of Dermatology, State University of New York, Downstate Health Sciences University, Brooklyn, New York, USA.
  • Marc Cohen
    Department of Dermatology, State University of New York, Downstate Health Sciences University, Brooklyn, New York, USA.
  • Alana Kurtti
    Department of Dermatology, State University of New York, Downstate Health Sciences University, Brooklyn, New York, USA.
  • Jared Jagdeo
    Department of Dermatology, State University of New York, Downstate Health Sciences University, Brooklyn, New York, USA.

Keywords

No keywords available for this article.

External Resources

Popular Topics
Recent Journals