Predicting the apolipoprotein E ε4 allele carrier status based on gray matter volumes and cognitive function.

Abstract

Apolipoprotein E (ApoE) ε4 carriers have a higher risk of developing Alzheimer's disease (AD) and show brain atrophy and cognitive decline even before diagnosis. To predict ApoE ε4 status using gray matter volume (GMV) obtained from magnetic resonance imaging images and demographic data with machine learning (ML) methods. We recruited 74 participants (25 probable AD, 24 amnestic mild cognitive impairment, and 25 cognitively normalolder people) with known ApoE genotype (22 ApoE ε4 carriers and 52 noncarriers) and scanned them with three-dimensional (3D) T1-weighted (T1W) and 3D double inversion recovery (DIR) sequences. We extracted GMV from regions of interestrelated to AD pathology and used them as features along with age and mini-mental state examination (MMSE) scores to train different ML models. We performed both receiver operating characteristiccurve analysis and the prediction analysis of the ApoE ε4 carrier with different ML models. The best model of ML analyses was a cubic support vector machine (SVM3) that used age, the MMSE score, and DIR GMVs at the amygdala, hippocampus, and precuneus as features (AUC=.88). This model outperformed models using T1W GMV or demographic data alone. Our results suggest that brain atrophy with DIR GMV and cognitive decline with aging can be useful biomarkers for predicting ApoE ε4 status and identifying individuals at risk of AD progression.