NeuroMoE++: Patient-Adaptive Multi-Level Multimodal Fusion With Mixture-of-Experts for Neurological Disorder Classification
- 1 August 2026
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Biomedical Engineering
- Vol. 73 (8) , 2784-2794
Abstract
Early diagnosis of neurological disorders (NDs) benefits from multiple complementary signals, including anatomical MRI, diffusion imaging, functional activation, and clinical or serum biomarkers. These modalities capture distinct aspects of neurodegeneration and have motivated recent multimodal learning approaches. However, most existing methods combine modalities only at the feature or decision level through late fusion, meaning that modalities are processed independently and never influence one another during feature extraction. As a result, subtle cross-modality patterns that are highly informative in prodromal stages remain underutilized. To address this limitation, we propose NeuroMoE++, a hierarchical end-to-end framework that enables explicit interaction across modalities while preserving their individual structure. After obtaining unimodal and cross-modality predictions, a subject-driven adaptive integration produces patient-specific decisions. This combination allows the model to capture complementary structure, leverage fused evidence when beneficial, and remain interpretable from a clinical standpoint. Experiments on real clinical datasets demonstrate that NeuroMoE++ substantially outperforms unimodal and late-fusion baselines, achieving 84.94% accuracy. These results highlight the value of explicit cross-modality reasoning for practical neurological diagnosis.Keywords
Funding Information
- National Science Foundation (CCF-2504152)
This publication has 36 references indexed in Scilit:
- Neuroimaging and fluid biomarkers in Parkinson’s disease in an era of targeted interventionsNature Communications, 2024
- A review of deep learning-based information fusion techniques for multimodal medical image classificationComputers in Biology and Medicine, 2024
- Deep learning integrates histopathology and proteogenomics at a pan-cancer levelCell Reports Medicine, 2023
- Early prediction of Alzheimer's disease and related dementias using real‐world electronic health recordsAlzheimer's & Dementia, 2023
- Evolution patterns of probable REM sleep behavior disorder predicts Parkinson’s disease progressionnpj Parkinson's Disease, 2022
- Dynamic Image for 3D MRI Image Alzheimer’s Disease Classification2020
- MDS clinical diagnostic criteria for Parkinson's diseaseMovement Disorders, 2015
- Preclinical Biomarkers of Parkinson DiseaseArchives of Neurology, 2011
- Reduced volume of the putamen in REM sleep behavior disorder patientsParkinsonism & Related Disorders, 2010
- T1ρ and T2ρ MRI in the evaluation of Parkinson’s diseaseJournal of Neurology, 2010