Polygenic Hazard Score for Predicting Age-associated Risk of Alzheimer's Disease in European Populations: Development and Validation

ObjectivesPolygenic hazard score (PHS) models can be used to predict the age-associated risk for complex diseases, including Alzheimers disease (AD). In this study, we present an improved PHS model for AD that incorporates a large number of genetic variants and demonstrates enhanced predictive accuracy for age of onset in European populations compared to alternative models. MethodsWe used the genotyped European Alzheimer & Dementia Biobank (EADB) sample (n=42,120) to develop and evaluate the performance of the PHS model. We developed a PHS model building on 720 genetic variants, including Apolipoprotein E (APOE) {varepsilon}2 and {varepsilon}4 alleles. We used Elastic Net-regularized Cox regression approach to develop the PHS model. ResultsThe new PHS model (EADB720) improved prediction accuracy compared to alternative models in European populations, with the Odds Ratio OR80/20 from the highest quintile of risk (80th risk percentile and above) to the lowest quintile of risk (20th risk percentile and below) varying between 5.10 and 13.15 within the range of age of onset from 65 - 85 years. Our model also improved risk stratification across {varepsilon}3/3 individuals of European ancestry (OR80/20 ranges from 1.95 to 3.52). It was also successfully validated in independent datasets (HUSK, DemGene and ADNI) by achieving OR80/20 up to 10.00 in each independent dataset. ConclusionOur EADB720 model significantly improves the accuracy of age-associated risk of AD across European populations (pval<0.03). Accurately predicting the age of onset of AD is of large clinical importance to implementing new AD medication and early intervention in clinical settings.