<scp>AI</scp> ‐generated dermatologic images show deficient skin tone diversity and poor diagnostic accuracy: An experimental study
The study highlights substantial deficiencies in the diversity and accuracy of AI-generated dermatological images. AI programs may exacerbate cognitive bias and health inequity, suggesting the need for ethical AI guidelines and diverse datasets to improve disease diagnosis and dermatologic care.
Authors
- Lucie Joerg
- Marc Cohen (ORCID: https://orcid.org/0000-0002-0872-7672)
- Evan Austin
- Jared Jagdeo (ORCID: https://orcid.org/0000-0002-7619-7650)
- Alana Kurtti
- Jennifer Y. Wang (ORCID: https://orcid.org/0009-0003-1921-1908)
- Margaret Kabakova
Institutions
- State University of New York (US)
- SUNY Downstate Health Sciences University (US)
- VA NY Harbor Healthcare System (US)
- Albany Medical Center Hospital (US)
Publication Details
- Journal
- Journal of the European Academy of Dermatology and Venereology
- Published
- 2025-07-16
- DOI
- https://doi.org/10.1111/jdv.20849
- Citations
- 9
- Primary Topic
- Cutaneous Melanoma Detection and Management
- Type
- article
- Field-Weighted Citation Impact
- 9.41