AI Can Identify Early Skin Cancer Risk Patterns, Study Finds
NEW DELHI, India — Artificial intelligence can help identify early risk patterns for melanoma, potentially improving early detection and targeted screening, according to a new study.
The research analyzed registry data covering Sweden’s entire adult population, including information on age, sex, medical diagnoses, medication use, and socioeconomic status.
Out of more than 6 million individuals studied, 38,582, or 0.64%, developed melanoma over a five-year period.
“Our study shows that data which is already available within healthcare systems can be used to identify individuals at higher risk of melanoma,” said Martin Gillstedt, a doctoral student at the University of Gothenburg’s Sahlgrenska Academy.
Gillstedt said such decision-support tools are not yet part of routine healthcare but noted that the findings demonstrate how registry data could be used more strategically in the future.
Researchers compared multiple AI models and found significant differences in performance. The most advanced model correctly identified individuals who later developed melanoma in about 73% of cases, compared with about 64% when only age and sex were considered.
By combining diagnoses, medication history, and sociodemographic data, researchers were able to identify smaller high-risk groups, where the likelihood of developing melanoma within five years was about 33%.
“Our analyses suggest that selective screening of small, high-risk groups could lead to both more accurate monitoring and more efficient use of healthcare resources. This would involve bringing population data into precision medicine and supplementing clinical assessments,” said Sam Polesie, associate professor of dermatology and venereology at the University of Gothenburg.
The researchers said further studies and policy decisions will be needed before such AI-based methods can be implemented in healthcare. However, the findings suggest that models trained on large-scale registry data could play a key role in personalized risk assessments and future melanoma screening strategies. (Source: IANS)
