The Prediction of Alzheimer’s Disease through Multi‐Trait Genetic Modeling

Abstract

AbstractBackgroundPrevious studies have indicated that prediction performance of a genetic risk score is improved when the score is built using information about multiple traits/risk factors associated with the target trait. To better capture the polygenic architecture of Alzheimer’s Disease, we developed a joint genetic score, MetaGRS.MethodWe incorporated genetic variants for AD and 24 other traits from two independent cohorts, NACC (n = 3,174, training set) and UPitt (n = 2,053, validation set).ResultOne standard deviation increase in the MetaGRS is associated with about a 57% increase in the AD risk (HR = 1.577, p = 7.17 E‐56), showing little difference from the HR for AD GRS alone (HR = 1.579, p = 1.20E‐56), suggesting similar utility of both models. We also conducted APOE stratified analyses to assess the role of the e4 allele on risk prediction. Similar to that of the combined model, our stratified results did not show a considerable improvement of the MetaGRS.ConclusionOur study showed that prediction power of the MetaGRS significantly outperformed that of the reference model without any genetic information, but was effectively equivalent to the prediction power of the AD GRS in both the full and stratified analyses. Our findings are broadly consistent with previous studies of Stroke and T2D.