NeuroOmics-Net: An interpretable multimodal deep learning framework for Alzheimer's disease diagnosis and progression prediction using neuroimaging, EEG, and genomic data

2026-07-27

PRE

R. Kavitha *

K. Premalatha

DOI：10.1016/j.compbiomed.2026.111879

Original

Original request for help

Save

Abstract

En 中文

• NeuroOmics-Net fuses sMRI, EEG, and gene expression for AD diagnosis. • Hierarchical encoders, cross-omics attention, and graph learning combine. • Achieves 94.3% accuracy and 0.975 AUC across NC, MCI, and AD classes. • Predicts sMCI-to-pMCI conversion with 93.7% accuracy via DPGL module. • Reveals hippocampal, theta-alpha EEG, and APOE pathway biomarkers.

NeuroOmics-Net: An interpretable multimodal deep learning framework for Alzheimer's disease diagnosis and progression prediction using neuroimaging, EEG, and genomic data

Abstract

Journal

Organization

Cited Papers

Citing Papers