Disease risk prediction accuracy

multitrait polygenic scores improve disease risk prediction accuracy in silico (compared with optimal single-genome-wide association studies PGSs) (AUC gains 1.56% to 5.45%).

“Multitrait PGSs significantly improved risk prediction for eight diseases, with area under the receiver operating characteristic curve gains ranging from 1.56% to 5.45% compared with optimal single-genome-wide association studies PGSs.”

In silicocompared with optimal single-genome-wide association studies PGSs

Leveraging pleiotropy to improve genetic risk prediction across diseases

Genetics in medicine : official journal of the American College of Medical Genetics·Mar 5, 2026