Novel Models for Predicting Skin Cancer Risk
Posted: Friday, November 2, 2018
Based on the early findings of a study presented at the 2018 Annual Society of Human Genetics (ASHG) Annual Meeting in San Diego (Abstract 10), novel models that combine data on individuals’ lifetime sun exposure and their genetics may improve predictions of their risk for skin cancer. The investigators eventually hope to obtain risk estimates that are accurate enough to be used by both individuals and clinicians.
“We aimed to validate previously known skin cancer risk factors in a large cohort, add detail to these and explore potential new ones, and find out whether and how these factors might interact with genetic risk,” stated Pierre Fontanillas, PhD, of the personal genomics and biotechnology company 23andMe, in an ASHG press release.
In a large-scale phenotyped and genotyped cohort, the research team evaluated and extended prediction risk models for all three skin cancer types: basal cell carcinoma, squamous cell carcinoma, and melanoma. More than 210,000 research participants of European descent responded to an online survey, which included 70 questions on topics such as personal history of skin cancer, factors relating to susceptibility and ultraviolet exposure, as well as details of skin cancer incidence in family history.
Based on their findings. Dr. Fontanillas and colleagues concluded that multiple factors could be combined into statistical models that were more informative than those based on a single factor alone. The best-performing models incorporated a genetic risk score composed of data on up to 50 genetic variants, along with survey data on family history, skin pigmentation and sensitivity, number of moles, estimated current sun exposure, sunbathing frequency before the age of 30, and body mass index. The new models achieved a high predictive accuracy (AUC between 0.81 and 0.85).
Moving forward, the research team plans to expand their sample to groups with non-European ancestry and explore other methods of calculating genetic risk score and measuring sun exposure.
