Genetics Information with Functional Brain Networks for Dementia Classification

Mild cognitive impairment (MCI) precedes the Alzheimer’s disease (AD) continuum, making it crucial for therapeutic care to identify patients with MCI at risk of progression. We aim create generalized models who advance AD using high-dimensional-data resting state functional magnetic resonance imaging (rs-fMRI) brain networks and gene expression. Studies that integrate genetic traits clinical examination are limited, compared most current research methodologies, employing separate or multi-imaging features prognosis. Healthy controls (HCs) two phases (convertible stable MCI) along can be effectively diagnosed markers. The rs-fMRI-based connectome provides various information regarding is utilized in combination factors distinguish people from HCs. discriminating network nodes identified least absolute shrinkage selection operator (LASSO). common areas nodal detection middle temporal, inferior lingual, hippocampus, amygdala, frontal gyri. highest degree discriminative power demonstrated by graph metrics. Similarly, we propose an ensemble feature-ranking algorithm high-dimensional information. use a multiple-kernel learning support vector machine efficiently merge multipattern data. Using suggested technique HCs produced combined leave-one-out cross-validation (LOOCV) classification accuracy 93.07% area under curve (AUC) 95.13%, state-of-the-art terms diagnostic accuracy. Therefore, our proposed approach has high clinically relevant efficient identifying AD.