As the rates of melanoma for all Americans continue a 30-year climb, dermatologists have begun exploring new technologies to try to reverse this deadly trend—including artificial intelligence. There’s been a growing hope in the field that using machine-learning algorithms to diagnose skin cancers and other skin issues could make for more efficient doctor visits and increased, reliable diagnoses. The earliest results are promising—but also potentially dangerous for darker-skinned patients.
[Software engineer Avery Smith] co-authored a paper in JAMA Dermatology that warns of the potential racial disparities that could come from relying on machine learning for skin-cancer screenings.
Chief among the prohibitive issues, according to Smith and [co-author Adewole] Adamson, is that the data [the deep-learning network] relies on come from primarily fair-skinned populations in the United States, Australia, and Europe. If the algorithm is basing most of its knowledge on how skin lesions appear on fair skin, then theoretically, lesions on patients of color are less likely to be diagnosed. “If you don’t teach the algorithm with a diverse set of images, then that algorithm won’t work out in the public that is diverse,” says Adamson.
The ideal solution, then, would be to ensure a more equitable demographic participation in clinical trials, and in the case of machine learning, to save photo sets of skin conditions on diverse skin types for the algorithm to “learn” from.
Read full, original post: AI-Driven Dermatology Could Leave Dark-Skinned Patients Behind