Genetic risk scores enhance the diagnostic value of plasma biomarkers of brain amyloidosis.

Blood-based biomarkers offer strong potential to revolutionize diagnosis, trial enrollment, and treatment monitoring in Alzheimer's disease (AD). However, further advances are needed before these biomarkers can achieve wider deployment beyond selective research studies and specialty memory clinics, including the development of frameworks for optimal interpretation of biomarker profiles. We hypothesized that integrating Alzheimer's disease genetic risk score (AD-GRS) data would enhance the diagnostic value of plasma AD biomarkers by better capturing extant disease heterogeneity. Analyzing 962 individuals from a population-based sample, we observed that an AD-GRS was independently associated with amyloid PET levels (an early marker of AD pathophysiology) over and above APOE ε4 or plasma p-tau181, Aβ42/40, GFAP, or NfL. Among individuals with a high or moderately high plasma p-tau181, integrating AD-GRS data significantly improved classification accuracy of amyloid PET positivity, including the finding that the combination of a high AD-GRS and high plasma p-tau181 outperformed p-tau181 alone in classifying amyloid PET positivity (88% vs. 68%; p = 0.001). A machine learning approach incorporating plasma biomarkers, demographics, and the AD-GRS was highly accurate in predicting amyloid PET levels (90% training set; 89% test set), and Shapley value analyses (an explainer method based in cooperative game theory) indicated that the AD-GRS and plasma biomarkers had differential importance in explaining amyloid deposition across individuals. Polygenic risk for AD dementia appears to account for a unique portion of disease heterogeneity which could noninvasively enhance the interpretation of blood-based AD biomarker profiles in the population.