A new study published in the British Journal of Dermatology shows that combining genetic information with traditional clinical risk factors - like age, skin type, and history of sun exposure - can improve how accurately we identify people at higher risk of melanoma. While genetic risk scores performed better than any single clinical factor on their own, the biggest gains came from using both approaches together.
Abstract
Background:
Cutaneous melanoma is a common cancer, for which risk stratification has been proposed to aid early detection.
Objectives
To assess the performance of a polygenic risk score (PRS) in predicting risk for invasive cutaneous melanoma, alone and combined with clinical risk factors.
Methods
The PRS was derived from the most recent genome-wide association study (GWAS) meta-analysis of cutaneous melanoma, which included 28,849 melanoma cases and 78,922 controls from 20 studies from United Kingdom, United States, Australia, and Europe. Then it was tuned in the Canadian Longitudinal Studying on Aging (CLSA) cohort, which included 528 melanoma cases and 17,787 controls. The PRS was then tested independently against 14 self-reported clinical factors and a clinical prediction model (the MP16 model) in the QSkin prospective cohort, which included 16,282 participants with genetic data aged 40-69 years at baseline, among whom 359 participants were identified with new invasive melanomas during 10 years of follow up.
Results
The PRS outperformed any other single clinical risk factor in QSkin (c-index 0.643). The baseline risk model (age, sex, first 10 principal components) had a c-index of 0.603; adding PRS to the baseline model increased the c-index to 0.670 (likelihood ratio test (LRT) p=1.68 × 10-21). Adding PRS to the MP16 model significantly enhanced discrimination (MP16 c-index: 0.713, MP16 + PRS c-index: 0.729 (median LRT p = 5.56×10-11)), and predicted more true cases in the 1st and 2nd top deciles (111 for MP16 + PRS vs 104 for MP16 in the 1st decile, and 72 for MP16 + PRS vs 63 for MP16 in the 2nd decile). Across various screening thresholds (10% to 50%), the sensitivity and/or specificity is higher, and the net reclassification improvements (NRIs) were in the range of 0.01 to 0.05, comparing the MP16 + PRS model with the MP16 model.
Conclusions
Incorporating genetic risk information into existing clinical risk tools significantly improves prediction performance for melanoma.
Source:
H Wang, H Ghajari, G Jayasinghe, et al. Genetics vs clinical risk scores for melanoma prediction, British Journal of Dermatology, 2026;, ljag126, https://doi.org/10.1093/bjd/ljag126