Researchers at the University of California San Diego have developed a machine learning model that identifies individuals with skin cancer with 89 per cent accuracy across diverse populations. The new approach combines genetic ancestry, lifestyle, and social determinants of health to help reduce disparities in skin cancer risk.
Skin cancer is among the most common cancers in the United States, with more than 9,500 new cases diagnosed every day and approximately two deaths from skin cancer occurring every hour. Traditional risk-prediction tools, however, have historically performed best in people of European ancestry. This leaves significant gaps in early detection for other populations.
As a result, skin cancer in people of non-European ancestry is frequently diagnosed at later stages when it is more difficult to treat, leading to worse overall outcomes.
A nationwide initiative
To address this disparity, the researchers analysed data from more than 400,000 participants in the National Institutes of Health’s All of Us Research Program, a nationwide initiative with substantial representation from African, Hispanic/Latino, Asian, and mixed-ancestry populations.
The study, published in Nature Communications, found the new model achieved 89 per cent accuracy in identifying individuals with skin cancer across all groups. This included 90 per cent accuracy for individuals of European ancestry and 81 per cent accuracy for people of non-European ancestry.
The model is designed as a clinical case-finding aid to help doctors identify which individuals should be prioritised for full-body skin exams by a dermatologist. The researchers suggest this could enable earlier diagnosis in individuals with darker skin tones, potentially alleviating current disparities in skin cancer outcomes.
