Functional and Clinical: An Explainable Deep Learning Model for Multimodal Alzheimer's Disease Classification
Open Access
- 30 January 2026
- journal article
- Published by Wiley in Brain and Behavior
- Vol. 16 (2) , e71240
Abstract
Purpose: Functional magnetic resonance imaging (fMRI) and deep learning models can classify Alzheimer's disease (AD) with high accuracy. These models are highly adaptable and work with a plethora of architectures, data types, and AD stages. However, fMRI deep learning models lack clinical application due to issues with small datasets, explainability, and reliability (e.g., data leakage). Methods: In this study, we address these issues using multimodal and explainable artificial intelligence (XAI) methods. Specifically, we overcome data size limitations by supplementing fMRI data with clinical tests, use a strict leave‐one‐out cross‐validation regime to control for data leakage, and apply perturbation ranking to explain the importance of features in our model. Our 3D convolutional neural network model was trained and validated on 52 participants from ADNI using five clinical tests and fMRI of the default mode network. Findings: The resulting multimodal model classified AD from controls with an accuracy of 90% and outperformed the same architecture without clinical data (58% accuracy). Our feature rankings showed that clinical tests changed in importance within our model depending on the diagnostic group. For example, our model found the MoCA to be highly important for classifying controls but not for AD. This trend of feature importance was seen across almost all fMRI and clinical features. Conclusion: Our model was highly accurate and highlighted the importance of combining fMRI and clinical data for AD classification. These findings have implications for the refinement of multimodal deep learning models; however, our small sample and need for external validation are also noted.Keywords
This publication has 52 references indexed in Scilit:
- A survey on deep learning in medical image analysisMedical Image Analysis, 2017
- The first step for neuroimaging data analysis: DICOM to NIfTI conversionJournal of Neuroscience Methods, 2016
- The Alzheimer's Disease Neuroimaging Initiative phase 2: Increasing the length, breadth, and depth of our understandingAlzheimer's & Dementia, 2015
- Evidence of the Sensitivity of the MoCA Alternate Forms in Monitoring Cognitive Change in Early Alzheimer's DiseaseDementia and Geriatric Cognitive Disorders, 2013
- Conn : A Functional Connectivity Toolbox for Correlated and Anticorrelated Brain NetworksBrain Connectivity, 2012
- The measurement of everyday cognition: Development and validation of a short form of the Everyday Cognition scalesAlzheimer's & Dementia, 2011
- G*Power 3: A flexible statistical power analysis program for the social, behavioral, and biomedical sciencesBehavior Research Methods, 2007
- The Montreal Cognitive Assessment, MoCA: A Brief Screening Tool For Mild Cognitive ImpairmentJournal of the American Geriatrics Society, 2005
- Development of cognitive instruments for use in clinical trials of antidementia drugs: additions to the Alzheimer's Disease Assessment Scale that broaden its scope. The Alzheimer's Disease Cooperative Study.1997
- Measurement of Functional Activities in Older Adults in the CommunityJournal of Gerontology, 1982