The Explainable Attention-Guided Multimodal Ensemble Framework for Alzheimer’s Disease Prediction and Severity Estimation

K. Laxmikantha; P. S. Ashokkumar

doi:10.48084/etasr.18269

Authors

K. Laxmikantha Department of CSE, KS Institute of Technology, Bengaluru, Visvesvaraya Technological University, Belagavi, Karnataka, India
P. S. Ashokkumar Department of CSE, ACS College of Engineering, Bengaluru, Visvesvaraya Technological University, Belagavi, Karnataka, India

Volume: 16 | Issue: 3 | Pages: 36345-36351 | June 2026 | https://doi.org/10.48084/etasr.18269

Received: 19 February 2026 | Revised: 31 March 2026 and 13 April 2026 | Accepted: 26 April 2026 | Online: 6 June 2026

Corresponding author: K. Laxmikantha

Abstract

Globally, Alzheimer's Disease (AD) is a major cause of cognitive impairment. Despite the contribution made by machine-learning techniques to the evolution of diagnostic techniques, the existing systems rely mainly on one-modality inputs and are defined as opaque black-box models, thus restricting their clinical usefulness and predictive accuracy. In this paper, the Explainable Attention-Guided Feature-Weighted Multimodal Ensemble Framework (EAFW-MEF) framework is proposed for the evaluation of five types of AD and the severity estimation of the disease in continuous form. The framework integrates clinical data, psychological tests, and MRI-based volumetric biomarkers of the OASIS-3 dataset through a novel explainability-based fusion plan. In contrast with data-level fusion, the EAFW-MEF models global SHAP importance scores to guide an attentional score-driven weighting procedure through which cycling the multimodal features before the model is trained can be recalibrated. The classification is done in a hybrid stacked ensemble utilizing Random Forest, XGBoost, and LightGBM whose outputs are combined with an interpretable logistic regression meta-learner. In addition to classification, the study gives rise to the Alzheimer RiskSeverity Index, which provides a continuous estimate of disease severity at the current visit and can support clinical stratification. Experimental findings point to better performance, with a stratified 10-fold cross-validation accuracy of 99.12% and, therefore, exceeding the current state-of-the-art multimodal methods.

Keywords:

Alzheimer’s disease, multimodal learning, explainable artificial intelligence, SHAP, ensemble learning, disease severity estimation

References

A. A. Soladoye, N. Aderinto, D. Osho, and D. B. Olawade, "Explainable machine learning models for early Alzheimer’s disease detection using multimodal clinical data," International Journal of Medical Informatics, vol. 204, Dec. 2025, Art. no. 106093.

F. H. Al-bakri et al., "A Feature-Augmented Explainable Artificial Intelligence Model for Diagnosing Alzheimer’s Disease from Multimodal Clinical and Neuroimaging Data," Diagnostics, vol. 15, no. 16, Aug. 2025, Art. no. 2060.

M. L. Raza et al., "Advancements in deep learning for early diagnosis of Alzheimer’s disease using multimodal neuroimaging: challenges and future directions," Frontiers in Neuroinformatics, vol. 19, May 2025.

A. S. Alatrany, W. Khan, A. Hussain, H. Kolivand, and D. Al-Jumeily, "An explainable machine learning approach for Alzheimer’s disease classification," Scientific Reports, vol. 14, no. 1, Feb. 2024, Art. no. 2637.

S. Muksimova, S. Umirzakova, J. Baltayev, and Y. I. Cho, "Multi-Modal Fusion and Longitudinal Analysis for Alzheimer’s Disease Classification Using Deep Learning," Diagnostics, vol. 15, no. 6, Mar. 2025.

F. Leony and C. Lin, "Multimodal fusion architectures for Alzheimer’s disease diagnosis: An experimental study," Journal of Biomedical Informatics, vol. 166, June 2025, Art. no. 104834.

S. Jahan et al., "Explainable AI-based Alzheimer’s prediction and management using multimodal data," PLOS ONE, vol. 18, no. 11, 2023, Art. no. e0294253.

V. Viswan, N. Shaffi, M. Mahmud, K. Subramanian, and F. Hajamohideen, "Explainable Artificial Intelligence in Alzheimer’s Disease Classification: A Systematic Review," Cognitive Computation, vol. 16, no. 1, pp. 1–44, Jan. 2024.

L. G. Amato et al., "Personalized modeling of Alzheimer’s disease progression estimates neurodegeneration severity from EEG recordings," Alzheimer’s & Dementia: Diagnosis, Assessment & Disease Monitoring, vol. 16, no. 1, 2024, Art. no. e12526.

G. H. Koksalmis, B. Soykan, L. J. Brattain, and H.-H. Huang, "Artificial Intelligence for Personalized Prediction of Alzheimer’s Disease Progression: A Survey of Methods, Data Challenges, and Future Directions." arXiv, Apr. 29, 2025.

R. Zhang, J. Sheng, Q. Zhang, J. Wang, and B. Wang, "A review of multimodal fusion–based deep learning for Alzheimer’s disease," Neuroscience, vol. 576, pp. 80–95, June 2025.

B. Huang, F. Yang, M. Yin, X. Mo, and C. Zhong, "A Review of Multimodal Medical Image Fusion Techniques," Computational and Mathematical Methods in Medicine, vol. 2020, no. 1, 2020, Art. no. 8279342.

T. Jo, K. Nho, and A. J. Saykin, "Deep Learning in Alzheimer’s Disease: Diagnostic Classification and Prognostic Prediction Using Neuroimaging Data," Frontiers in Aging Neuroscience, vol. 11, Aug. 2019.

S. Li and H. Tang, "Multimodal Alignment and Fusion: A Survey." arXiv, Oct. 11, 2025.

A. D. Arya et al., "A systematic review on machine learning and deep learning techniques in the effective diagnosis of Alzheimer’s disease," Brain Informatics, vol. 10, no. 1, July 2023, Art. no. 17.

T. Shaik, X. Tao, L. Li, H. Xie, and J. D. Velásquez, "A survey of multimodal information fusion for smart healthcare: Mapping the journey from data to wisdom," Information Fusion, vol. 102, Feb. 2024, Art. no. 102040.

V. H. Jasodanand et al., "AI-driven fusion of multimodal data for Alzheimer’s disease biomarker assessment," Nature Communications, vol. 16, no. 1, Aug. 2025, Art. no. 7407.

P. Mahajan, S. Uddin, F. Hajati, and M. A. Moni, "Ensemble Learning for Disease Prediction: A Review," Healthcare, vol. 11, no. 12, June 2023.

A. A. Khan, O. Chaudhari, and R. Chandra, "A review of ensemble learning and data augmentation models for class imbalanced problems: Combination, implementation and evaluation," Expert Systems with Applications, vol. 244, June 2024, Art. no. 122778.

N. Hettikankanamage, N. Shafiabady, F. Chatteur, R. M. X. Wu, F. Ud Din, and J. Zhou, "eXplainable Artificial Intelligence (XAI): A Systematic Review for Unveiling the Black Box Models and Their Relevance to Biomedical Imaging and Sensing," Sensors (Basel, Switzerland), vol. 25, no. 21, Oct. 2025, Art. no. 6649.

A. Prinston Pinto, Dattathreya, P. Prasada, and S. A. Rag, "Multimodal Coherence-Correlation Fusion of EEG and ECoG Signals for Enhanced Epileptic Seizure Detection Using Discrete Lyapunov Wavelet Transform," IEEE Access, vol. 13, pp. 163820–163831, 2025.

D. Muhammad and M. Bendechache, "Unveiling the black box: A systematic review of Explainable Artificial Intelligence in medical image analysis," Computational and Structural Biotechnology Journal, vol. 24, pp. 542–560, Dec. 2024.

V. Vimbi, N. Shaffi, and M. Mahmud, "Interpreting artificial intelligence models: a systematic review on the application of LIME and SHAP in Alzheimer’s disease detection," Brain Informatics, vol. 11, no. 1, Apr. 2024, Art. no. 10.

Z. Sadeghi et al., "A review of Explainable Artificial Intelligence in healthcare," Computers and Electrical Engineering, vol. 118, Aug. 2024, Art. no. 109370.

S. A. Martin, F. J. Townend, F. Barkhof, and J. H. Cole, “Interpretable machine learning for dementia: A systematic review,” Alzheimer’s & Dementia, vol. 19, no. 5, pp. 2135–2149, 2023.

M. Champendal, H. Müller, J. O. Prior, and C. S. dos Reis, "A scoping review of interpretability and explainability concerning artificial intelligence methods in medical imaging," European Journal of Radiology, vol. 169, Dec. 2023, Art. no. 111159.

H. C. Bharath, N. Pradeep, R. Shashidhar, P. Nooji, and J. Meghana, "An Explainable Deep Learning Model for Classification and Analysis of Alzheimer’s Disease for Clinical Trust," Engineering, Technology & Applied Science Research, vol. 15, no. 6, pp. 28762–28768, Dec. 2025.

S. El-Sappagh, J. M. Alonso, S. M. R. Islam, A. M. Sultan, and K. S. Kwak, "A multilayer multimodal detection and prediction model based on explainable artificial intelligence for Alzheimer’s disease," Scientific Reports, vol. 11, no. 1, Jan. 2021, Art. no. 2660.

A. R. W. Sait and R. Nagaraj, "A Feature-Fusion Technique-Based Alzheimer’s Disease Classification Using Magnetic Resonance Imaging," Diagnostics, vol. 14, no. 21, Oct. 2024.

F. Hajamohideen et al., "Four-way classification of Alzheimer’s disease using deep Siamese convolutional neural network with triplet-loss function," Brain Informatics, vol. 10, no. 5, Feb. 2023.

P. J. LaMontagne et al., "OASIS-3: Longitudinal Neuroimaging, Clinical, and Cognitive Dataset for Normal Aging and Alzheimer Disease." medRxiv, Dec. 15, 2019.

Y. Mustafa and T. Luo, "Diagnosing Alzheimer’s Disease using Early-Late Multimodal Data Fusion with Jacobian Maps," in 2023 IEEE International Conference on E-health Networking, Application & Services (Healthcom), Sept. 2023, pp. 49–55.

A. Massalimova and H. A. Varol, "Input Agnostic Deep Learning for Alzheimer’s Disease Classification Using Multimodal MRI Images," in 2021 43rd Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC), Aug. 2021, pp. 2875–2878.

S. Rahman, M. M. Rahman, S. Bhatt, R. Sundararajan, and M. Faezipour, "NeuroNet-AD: A Multimodal Deep Learning Framework for Multiclass Alzheimer’s Disease Diagnosis," Bioengineering, vol. 12, no. 10, Oct. 2025.

L. Han, "AD-Diff: enhancing Alzheimer’s disease prediction accuracy through multimodal fusion," Frontiers in Computational Neuroscience, vol. 19, Mar. 2025.

G. Castellano, A. Esposito, E. Lella, G. Montanaro, and G. Vessio, "Automated detection of Alzheimer’s disease: a multi-modal approach with 3D MRI and amyloid PET," Scientific Reports, vol. 14, no. 1, Mar. 2024, Art. no. 5210.