Analyzing the effect of APOE on Alzheimer’s disease progression using an event-based model for stratified populations

Alzheimer’s disease (AD) is the most common form of dementia and phenotypically heterogeneous. APOE a triallelic gene which correlates with phenotypic heterogeneity in AD. In this work, we determined effect alleles on progression timeline AD using discriminative event-based model (DEBM). Since DEBM data-driven model, stratification into smaller subgroups would lead to more inaccurate models as compared fitting entire dataset. Hence our secondary aim propose evaluate novel approaches split different steps group-aspecific group-specific parts, where dataset used train parts only data from specific group DEBM. We performed simulation experiments benchmark accuracy proposed select optimal approach. Subsequently, chosen approach was applied baseline 417 cognitively normal, 235 mild impaired who convert within 3 years, 342 patients Alzheimers Disease Neuroimaging Initiative (ADNI) gain new insights carriership ?4 carrier group, predicted high confidence that CSF Amyloid?42 cognitive score Assessment Scale (ADAS) are early biomarkers. Hippocampus earliest volumetric biomarker become abnormal, closely followed by Phosphorylated Tau181 (PTAU) biomarker. homozygous ?3 similar ordering among However, volume fusiform gyrus identified one While findings groups fit current understanding AD, finding ?2 did not. The predicted, relatively low confidence, Neurogranin biomarkers along Mini-Mental State Examination (MMSE). Amyloid ?42 found abnormal after PTAU. presented could aid disease, selecting homogeneous presymptomatic subjects at-risk developing symptoms for clinical trials.