Understanding the role of APOE Gene Polymorphisms in Minimal Atrophy Alzheimer’s Disease by mixture of expert models

Alzheimer’s disease (AD) is a heterogeneous disease. Exploring the characteristics of each AD subtype key to disentangling heterogeneity. Minimal atrophy (MAD) common that yields conflicting results. In order evaluate this aspect across relatively large populations, total 192 and 228 cognitively normal (CN) subjects were processed by automated segmentation scheme FreeSurfer, which generates regional cortical thickness measures. A machine learning driven approach, mixture expert models, combines unsupervised modeling mixtures distributions with supervised classifiers, was applied approximates non-linear boundary between CN piece-wise linear boundary. Multiple thicknes patterns discovered, includes: bilateral parietal/frontal AD, left temporal dominant MAD, diffuse AD. MAD had highest proportions ApoE4 ApoE2. Further analysis revealed ApoE genotype, stage their interactions can partially explain observations in MAD.