Explainable Multimodal Deep Learning Framework for Longitudinal Prediction of Neurodegenerative Disease Progression with Clinical Validation
DOI:
https://doi.org/10.70715/jitcai.2026.v3.i5.088Keywords:
Multimodal Deep Learning, Alzheimer's Disease, Parkinson's Disease, Clinical Validation, Longitudinal PredictionAbstract
Neurodegenerative diseases, particularly Alzheimer's Disease and Parkinson's Disease, are rapidly increasing as one of the leading causes of disability, cognitive decline, and death among the elderly population worldwide. Accurately predicting long-term disease progression remains a significant research challenge due to the disease's slow progression, multifaceted biological characteristics, and patient-specific clinical presentation. Most existing machine learning and deep learning models rely on a single data source, cannot effectively analyze time-dependent pathological changes, and have non-interpretable decision-making processes, thereby limiting their practical clinical use. To overcome this limitation, the current study proposes an Explainable Multimodal Deep Learning Framework that predicts long-term progression in neurodegenerative diseases by integrating neuroimaging, clinical information, cognitive assessments, demographic characteristics, and biomarker data. Experimental results indicate that the proposed model achieved 94.8% Accuracy, 93.9% Precision, 94.3% Recall, 94.1% F1 Score, and 96.2% area under the curve (AUC). The average accuracy in five-fold cross-validation was 94.8%, confirming the model's stability and ability to generalize. In addition, 96.3%, 94.8% and 92.6% accuracy were achieved in predicting disease progression at one year, three years and five years, respectively. Clinical Validation showed 94.5% agreement with expert physician evaluations and high acceptability in the Explainability Assessment. The results demonstrate that the proposed interpretable multimodal deep learning framework is more accurate, more transparent, and more clinically acceptable than existing methods. This research provides a strong foundation for the development of future personalized medicine, early risk identification, and artificial intelligence-based clinical decision support systems.
Downloads
References
[1] S. Reports, “Scientific Reports Article in Press Dynamic context-aware multi-modal deep learning for longitudinal prediction of Parkinson ’ s disease progression IN Dynamic Context-Aware Multi-Modal Deep Learning IN,” 2025.
[2] S. Toumaj and A. Heidari, “Artificial Intelligence Review Article in Press Explainable artificial intelligence in neurology: a holistic exploration of models for diagnosis, progression tracking, and treatment planning IN Explainable Artificial Intelligence in Neurology: A Holistic Exploration of Models for Diagnosis, Progression IN,” 2026. DOI: https://doi.org/10.1007/s10462-026-11606-6
[3] H. Saleh, N. Elrashidy, M. Abd, and A. O. A. S. El-sappagh, “Genetic algorithm-based hybrid deep learning model for explainable Alzheimer ’ s disease prediction using temporal multimodal cognitive data,” Int. J. Data Sci. Anal., vol. 20, no. 2, pp. 1073–1103, 2025. DOI: https://doi.org/10.1007/s41060-024-00514-z
[4] S. Gujjeti, N. Madhavi, B. Venkateswarlu, B. Spandana, and G. S. Murthy, “NeuroCrossAttention fusion for multimodal explainable early diagnosis of neurodegenerative diseases,” 2026. DOI: https://doi.org/10.1007/s10791-026-10200-2
[5] R. Farha, B. Ojeme, and F. Khalifa, “Counterfactual, Longitudinal, and Multimodal Explainable AI for MRI-Based Alzheimer ’ s Diagnosis: A Structured Review,” pp. 1–33, 2026. DOI: https://doi.org/10.3390/jdad3020026
[6] J. Jayapandian and M. Senthil, “An Explainable Federated Temporal Multimodal Ensemble Deep Learning Model for Early Diagnosis and Progression Prediction of Parkinson ’ s and Alzheimer ’ s Diseases Using X -FedTME-Net,” vol. 16, no. 1, pp. 1–14, 2026. DOI: https://doi.org/10.5875/g0qvad40
[7] R. A. Alotaibi et al., “Development and Validation of Explainable Artificial Intelligence Models for Early Prediction of Neurodegenerative Disorders in Middle Eastern Populations: A Multimodal Approach Integrating Clinical, Genetic and Neuroimaging Data,” pp. 771–778, 2026. DOI: https://doi.org/10.4103/ATMR.ATMR_78_25
[8] A. Ravichandran and T. K. Murugan, “Explainable multimodal feature fusion networks for Parkinson ’ s disease prediction,” no. February, 2026. DOI: https://doi.org/10.3389/fdgth.2026.1771281
[9] A. Jabbar, M. K. Jabbar, and A. Ali, “Dynamic Preclinical Detection and Progression Prediction of Neurodegenerative Diseases Using Multi-Modal Deep Learning Dynamic Preclinical Detection and Progression Prediction of Neurodegenerative Diseases Using Multi-Modal Deep Learning,” pp. 0–22, 2026. DOI: https://doi.org/10.21203/rs.3.rs-7455494/v1
[10] S. El Sappagh, J. M. Alonso, S. M. R. Islam, and A. M. Sultan, “OPEN A multilayer multimodal detection and prediction model based on explainable artificial intelligence for Alzheimer ’ s disease,” Sci. Rep., pp. 1–26, 2021. DOI: https://doi.org/10.1038/s41598-021-82098-3
[11] S. L. Warren, “Functional and Clinical: An Explainable Deep Learning Model for Multimodal Alzheimer ’ s Disease Classification,” pp. 1–11, 2026. DOI: https://doi.org/10.1002/brb3.71240
[12] M. R. Shaikh, A. Jeyabose, and R. V. Arjunan, “Deep learning for Alzheimer ’ s disease: advances in classification, segmentation, subtyping, and explainability,” 2025. DOI: https://doi.org/10.1186/s12938-025-01482-6
[13] V. Dentamaro, D. Impedovo, L. Musti, G. Pirlo, and P. Taurisano, “Enhancing early Parkinson ’ s disease detection through multimodal deep learning and explainable AI: insights from the PPMI database,” Sci. Rep., no. 0123456789, pp. 1–18, 2024. DOI: https://doi.org/10.1038/s41598-024-70165-4
[14] G. Lee, K. Nho, B. Kang, K. Sohn, and D. Kim, “Predicting Alzheimer ’ s disease progression using multi-modal deep learning approach,” no. December 2018, pp. 1–12, 2019.
[15] S. J. Id et al., “Explainable AI-based Alzheimer ’ s prediction and management using multimodal data,” pp. 1–26, 2023.
[16] A. H. M. Fahad et al., “Explainable AI-Driven Identification of Multimodal Biomarkers for Early Prediction of Cognitive Decline,” pp. 1–28, 2026. DOI: https://doi.org/10.3390/aimed1020012
[17] L. De Palma, V. I. D. Alessandro, F. Attivissimo, A. Maria, and L. Lanzolla, “A Machine Learning Pipeline for Prognostic Modeling of Alzheimer ’ s Disease Using Multimodal Data,” pp. 1–22, 2026. DOI: https://doi.org/10.3390/s26051523
[18] K. Laxmikantha, “The Explainable Attention-Guided Multimodal Ensemble Framework for Alzheimer ’ s Disease Prediction and Severity Estimation,” vol. 16, no. 3, pp. 36345–36351, 2026. DOI: https://doi.org/10.48084/etasr.18269
[19] M. L. Raza et al., “Advancements in deep learning for early diagnosis of Alzheimer ’ s disease using multimodal neuroimaging: challenges and future directions,” no. May, pp. 1–19, 2025. DOI: https://doi.org/10.3389/fninf.2025.1557177
[20] S. Jahan, R. S. Adib, S. M. Huda, A. S. M. S. Hosen, D. Ghimire, and M. I. J. I. N. Park, “Federated Explainable AI-Based Alzheimer ’ s Disease Prediction With Multimodal Data,” IEEE Access, vol. 13, no. February, pp. 43435–43454, 2025. DOI: https://doi.org/10.1109/ACCESS.2025.3547343
[21] E. Lydia and S. Betam, “Scientific Reports Article in Press Advancing biomedical data analytics using explainable neural network-based learning model for progressive neurodegenerative disorder diagnosis IN AR IN,” 2026.
[22] R. Zhang, D. Chen, Y. Qin, H. Han, and H. Yu, “Longitudinal multi-modal data prediction model for mild cognitive impairment by deep survival analysis,” vol. 3, 2026. DOI: https://doi.org/10.21203/rs.3.rs-8233936/v1
[23] A. Tsiakiri et al., “Explainable Machine Learning Reveals Time-Dependent Cognitive Risk in Minor Neurocognitive Disorder: Implications for Health Promotion and Early Risk Stratification,” pp. 1–23, 2026. DOI: https://doi.org/10.3390/biomedicines14040880
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Md. Ariful Islam, Md Anas Biswas, Alif Laila, Dr. Md. Saiful Hai, Sheikh Urvana Akter Mim (Author)
This work is licensed under a Creative Commons Attribution 4.0 International License.
