[Skip to Navigation]
Viewpoint
November 2018

Machine Learning and Health Care Disparities in Dermatology

Author Affiliations
  • 1Department of Dermatology, University of North Carolina at Chapel Hill
  • 2Dell Medical School, University of Texas, Austin
  • 3Software Engineering, Fearless Solutions, Baltimore, Maryland
JAMA Dermatol. 2018;154(11):1247-1248. doi:10.1001/jamadermatol.2018.2348

Machine learning (ML), a form of artificial intelligence using computer algorithms, is often applied in ways we take for granted: Spotify to predict music that people may enjoy, Facebook to suggest friends to tag in photos, and Amazon to identify products to buy. Aside from these quotidian tasks, ML holds the promise of enhancing the delivery of quality health care.1 Recently, ML has been used to create programs capable of distinguishing between images of benign and malignant moles with accuracy similar to that of board-certified dermatologists.2 This technology could greatly assist dermatologists in diagnosing and treating skin diseases, thereby improving patient care. However, if not developed with inclusivity in mind, ML could exacerbate health care disparities in dermatology.

×