Multimodal Machine Learning for Alzheimer's Disease Classification Using ADNI Biomarker Fusion

Authors

• Hesameddin Mostaghimi, Old Dominion University
• Hamid R. Okhravi, Macon & Joan Brock Virginia Health Sciences at Old Dominion University
• Bahar Niknejad, Macon & Joan Brock Virginia Health Sciences at Old Dominion University
• Daniel A. Cohen, Macon & Joan Brock Virginia Health Sciences at Old Dominion University
• Michel A. Audette, Old Dominion University
• Alzheimer's Disease Neuroimaging Initiative

Document Type

Article

Publication Date

2026

DOI

10.1016/j.aggp.2026.100296

Publication Title

Archives of Gerontology and Geriatrics Plus

Volume

3

Issue

3

Pages

100296

Abstract

Despite ongoing advances, accurate diagnosis of Alzheimer’s disease (AD) remains challenging due to its multifactorial nature, comorbidities, and clinical heterogeneity. Accordingly, approaches that combine multimodal data may improve AD classification by integrating complementary information. To investigate this, we evaluated classification performance using a preprocessed ADNI-3 dataset comprising a shared set of clinical/cognitive features along with four imaging modality-based cohorts: trimodal (MRI + amyloid PET + tau PET), MRI + amyloid PET, MRI + tau PET, and MRI-only. We trained a range of supervised machine learning (ML) and deep learning (DL) classifiers using stratified five-fold cross-validation and evaluated performance using accuracy, balanced accuracy, and macro-F1. Among ML model-cohort combinations, the highest-performing configuration was the gradient-boosted tree model CatBoost on MRI+tau PET (Macro-F1: 0.932 ± 0.043). For DL configurations, the highest performance was achieved by AutoencoderFusion on MRI+amyloid PET (Macro-F1: 0.899 ± 0.042). Our results indicate strong performance when combining clinical/cognitive and imaging data for AD classification in ADNI-3. While clinical/cognitive data provided the strongest classification signal, adding PET data yielded modest improvements among ML configurations.

Rights

© 2026 The Authors.

This is an open access article under the Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International (CC BY-NC-ND 4.0) License.

Data Availability

Article states: "The authors do not have permission to share data."

Original Publication Citation

Mostaghimi, H., Okhravi, H. R., Niknejad, B., Cohen, D. A., & Audette, M. A. (2026). Multimodal machine learning for Alzheimer’s disease classification using ADNI biomarker fusion. Archives of Gerontology and Geriatrics Plus, 3(3), Article 100296. https://doi.org/10.1016/j.aggp.2026.100296

Repository Citation

Mostaghimi, Hesameddin; Okhravi, Hamid R.; Niknejad, Bahar; Cohen, Daniel A.; Audette, Michel A.; and Alzheimer's Disease Neuroimaging Initiative, "Multimodal Machine Learning for Alzheimer's Disease Classification Using ADNI Biomarker Fusion" (2026). Electrical & Computer Engineering Faculty Publications. 601.
https://digitalcommons.odu.edu/ece_fac_pubs/601

ORCID

0000-0001-9961-6267 (Mostaghimi), 0009-0006-3684-5357 (Okhravi), 0000-0003-0011-1731 (Audette),