Machine Learning Models of Polygenic Risk for Enhanced Prediction of Alzheimer Disease Endophenotypes.

Neurol Genet

From the Departments of Radiology (N.B.G., R.K.G., C.R.J., V.J.L., P.V.), Neurology (J.G.-R., D.S.K., R.C.P., V.K.R.), and Quantitative Health Sciences (R.C.P.), Mayo Clinic Rochester, MN; and Departments of Quantitative Health Sciences (M.G.H.), Neuroscience (O.A.R.), and Clinical Genomics (O.A.R.), Mayo Clinic Florida, Jacksonville.

Published: February 2024

AI Article Synopsis

  • Alzheimer's disease (AD) has a complex genetic makeup, and traditional polygenic risk scores (PRS) derived from genome-wide association studies (GWAS) show limited effectiveness in predicting AD risk.
  • Researchers hypothesized that machine learning (ML) models would provide a better approach (ML-PRS) to assess genetic risk for AD compared to standard regression methods.
  • The study found that ML-PRS significantly outperformed traditional PRS in predicting amyloid PET burden and positivity, indicating greater accuracy in identifying individuals at risk for clinical AD.

Article Abstract

Background And Objectives: Alzheimer disease (AD) has a polygenic architecture, for which genome-wide association studies (GWAS) have helped elucidate sequence variants (SVs) influencing susceptibility. Polygenic risk score (PRS) approaches show promise for generating summary measures of inherited risk for clinical AD based on the effects of and other GWAS hits. However, existing PRS approaches, based on traditional regression models, explain only modest variation in AD dementia risk and AD-related endophenotypes. We hypothesized that machine learning (ML) models of polygenic risk (ML-PRS) could outperform standard regression-based PRS methods and therefore have the potential for greater clinical utility.

Methods: We analyzed combined data from the Mayo Clinic Study of Aging (n = 1,791) and the Alzheimer's Disease Neuroimaging Initiative (n = 864). An AD PRS was computed for each participant using the top common SVs obtained from a large AD dementia GWAS. In parallel, ML models were trained using those SV genotypes, with amyloid PET burden as the primary outcome. Secondary outcomes included amyloid PET positivity and clinical diagnosis (cognitively unimpaired vs impaired). We compared performance between ML-PRS and standard PRS across 100 training sessions with different data splits. In each session, data were split into 80% training and 20% testing, and then five-fold cross-validation was used within the training set to ensure the best model was produced for testing. We also applied permutation importance techniques to assess which genetic factors contributed most to outcome prediction.

Results: ML-PRS models outperformed the AD PRS ( = 0.28 vs = 0.24 in test set) in explaining variation in amyloid PET burden. Among ML approaches, methods accounting for nonlinear genetic influences were superior to linear methods. ML-PRS models were also more accurate when predicting amyloid PET positivity (area under the curve [AUC] = 0.80 vs AUC = 0.63) and the presence of cognitive impairment (AUC = 0.75 vs AUC = 0.54) compared with the standard PRS.

Discussion: We found that ML-PRS approaches improved upon standard PRS for prediction of AD endophenotypes, partly related to improved accounting for nonlinear effects of genetic susceptibility alleles. Further adaptations of the ML-PRS framework could help to close the gap of remaining unexplained heritability for AD and therefore facilitate more accurate presymptomatic and early-stage risk stratification for clinical decision-making.

Download full-text PDF

Source
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC10798228PMC
http://dx.doi.org/10.1212/NXG.0000000000200120DOI Listing

Publication Analysis

Top Keywords

amyloid pet
16
polygenic risk
12
machine learning
8
learning models
8
models polygenic
8
alzheimer disease
8
prs approaches
8
pet burden
8
pet positivity
8
standard prs
8

Similar Publications

Want AI Summaries of new PubMed Abstracts delivered to your In-box?

Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!