Machine Learning and Health Care Disparities in Dermatology

Adamson and Smith discuss the limitations of machine learning (ML) in diagnostics involving skin of color. ML, a form of artificial intelligence using computer algorithms, is often applied in ways we take for granted. 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. 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.