Authors : Dhiraj Jha; Apsara Das Shreshtha; Utsha Sarker; Lucky Nandani Thakur; Archy Biswas

Volume/Issue : Volume 11 - 2026, Issue 2 - February

Google Scholar : https://tinyurl.com/35dky47p

Scribd : https://tinyurl.com/yc7d3ju9

DOI : https://doi.org/10.38124/ijisrt/26feb1296

Note : A published paper may take 4-5 working days from the publication date to appear in PlumX Metrics, Semantic Scholar, and ResearchGate.

Abstract : Alzheimer's disease, Parkinson's disease and other neurodegenerative neurological diseases are disease examples of neurodegenerative disorders, which are a major global health burden. Extreme measures and effective treatment require an early and accurate diagnosis. To address this need, our study presents the development of a comprehensive multimodal deep-learning architecture of clinical biomarkers, digital biomarkers, structural and functional neuroimaging data as well as behavioural assessments. The proposed architecture is able to fuse disparate modalities using sophisticated fusion techniques and attention based mechanism in a successful way. Evaluation on a large dataset that includes 850 participants comprising 148 healthy controls, 182 patients with mild cognitive impairment, 340 patients with Alzheimer's disease and 180 patients with Parkinson's disease shows an overall classification accuracy of 96.8 per cent and an area under the curve of 0.959. Compared to the traditional MRI-only models, the multimodal fusion model is more accurate 8.8 per cent improvement and extremely better when compared to the single modality baselines. Explainable AI techniques namely SHAP and Grad-CAM identify important regions of neuroanatomical biomarkers that are predictive of disease progress or provide clinically understandable prognostication. These results support the therapeutic usefulness of multimodal deep learning for risk assessment, automated early diagnosis and personalised therapeutic plan for neurodegenerative illnesses.

Keywords : Deep Learning, Multimodal Learning & Neurodegenerative Disorders, Alzheimer's Disease, Parkinson's Disease, Medical Image Analysis, Early Diagnosis, Attention Mechanisms, Explainable AI.

References :

1. World Health Organization, Global patient safety report 2024: Executive summary. Geneva, Switzerland: World Health Organization, 2025. [Online]. Available: https://iris.who.int/handle/10665/380067
2. P. Scheltens et al., “Alzheimer’s disease,” The Lancet, vol. 397, no. 10284, pp. 1577–1590, Apr. 2021.
3. T. Vo, A. K. Ibrahim, and H. Zhuang, “A multimodal multi-stage deep learning model for the diagnosis of Alzheimer’s disease using EEG measurements,” Neurology International, vol. 17, no. 6, p. 91, Jun. 2025.
4. J. Jankovic, “Parkinson’s disease: Clinical features and diagnosis,” J. Neurol. Neurosurg. Psychiatry, vol. 79, no. 4, pp. 368–376, Apr. 2008.
5. A. Sar et al., “Multi-modal deep learning framework for early detection of Parkinson’s disease using neurological and physiological data for high-fidelity diagnosis,” Scientific Reports, vol. 15, no. 1, p. 34835, Oct. 2025.
6. H. Braak and E. Braak, “Neuropathological staging of Alzheimer-related changes,” Acta Neuropathologica, vol. 82, no. 4, pp. 239–259, Sep. 1991.
7. B. Dubois et al., “Preclinical Alzheimer’s disease: Definition, natural history, and diagnostic criteria,” Alzheimer’s & Dementia, vol. 12, no. 3, pp. 292–323, Mar. 2016.
8. S. Benredjem et al., “Parkinson’s disease prediction: An attention-based multimodal fusion framework using handwriting and clinical data,” Diagnostics, vol. 15, no. 1, p. 4, Dec. 2024.
9. R. G. Cumming, “Alcohol, smoking, and cataracts: The Blue Mountains Eye Study,” Arch. Ophthalmol., vol. 115, no. 10, pp. 1296–1303, Oct. 1997.
10.  R. C. Petersen, “Mild cognitive impairment as a diagnostic entity,” J. Intern. Med., vol. 256, no. 3, pp. 183–194, Sep. 2004.
11.  Y. LeCun, Y. Bengio, and G. Hinton, “Deep learning,” Nature, vol. 521, no. 7553, pp. 436–444, May 2015.
12.  H. Wang et al., “Research progress on human genes involved in the pathogenesis of glaucoma (Review),” Molecular Medicine Reports, May 2018. [Online]. Available: http://www.spandidos-publications.com/10.3892/mmr.2018.9071
13.  T. Baltrušaitis, C. Ahuja, and L.-P. Morency, “Multimodal machine learning: A survey and taxonomy,” IEEE Trans. Pattern Anal. Mach. Intell., vol. 41, no. 2, pp. 423–443, Feb. 2019.
14.  A. Vaswani et al., “Attention is all you need,” in Proc. Adv. Neural Inf. Process. Syst. (NeurIPS), 2017.
15.  G. Y. Li, X. Feng, and S. H. Yun, “In vivo optical coherence elastography unveils spatial variation of human corneal stiffness,” IEEE Trans. Biomed. Eng., vol. 71, no. 5, pp. 1418–1429, May 2024.
16.  A. Kumar et al., “Feature fusion based deep learning model for Alzheimer’s neurological disorder classification,” Neuroscience Informatics, vol. 5, no. 2, p. 100196, Jun. 2025.
17.  K. J. Ciuffreda and B. Tannen, “Future directions in neuro-optometry,” Concussion, vol. 5, no. 4, p. CNC80, Dec. 2020.
18.  J. A. Almutairi, “Understanding how age and biological sex influence the development of Alzheimer’s disease,” [Details incomplete – please provide journal/publisher/year].
19.  S. Krishnaiah et al., “Smoking and its association with cataract: Results of the Andhra Pradesh Eye Disease Study from India,” Investig. Ophthalmol. Vis. Sci., vol. 46, no. 1, pp. 58–63, Jan. 2005.
20.  K. He, X. Zhang, S. Ren, and J. Sun, “Deep residual learning for image recognition,” in Proc. IEEE Conf. Comput. Vis. Pattern Recognit. (CVPR), Las Vegas, NV, USA, 2016, pp. 770–778.
21.  M. L. Raza et al., “Advancements in deep learning for early diagnosis of Alzheimer’s disease using multimodal neuroimaging: Challenges and future directions,” Front. Neuroinformatics, vol. 19, p. 1557177, May 2025.
22.  A. Dosovitskiy et al., “An image is worth 16×16 words: Transformers for image recognition at scale,” in Proc. Int. Conf. Learn. Represent. (ICLR), 2021.
23.  J. Yosinski, J. Clune, A. Nguyen, T. Fuchs, and H. Lipson, “Understanding neural networks through deep visualization,” in Proc. ICML Deep Learning Workshop, 2015.
24.  R. Caruana et al., “Intelligible models for healthcare: Predicting pneumonia risk and hospital 30-day readmission,” in Proc. 21st ACM SIGKDD Int. Conf. Knowl. Discov. Data Mining, Sydney, Australia, 2015, pp. 1721–1730.
25.  C. R. Jack Jr. et al., “NIA-AA research framework: Toward a biological definition of Alzheimer’s disease,” Alzheimer’s & Dementia, vol. 14, no. 4, pp. 535–562, Apr. 2018.
26.  M. T. Ribeiro, S. Singh, and C. Guestrin, “‘Why should I trust you?’ Explaining the predictions of any classifier,” in Proc. 22nd ACM SIGKDD Int. Conf. Knowl. Discov. Data Mining, San Francisco, CA, USA, 2016, pp. 1135–1144.
27.  J. Venugopalan, L. Tong, H. R. Hassanzadeh, and M. D. Wang, “Multimodal deep learning models for early detection of Alzheimer’s disease stage,” Scientific Reports, vol. 11, no. 1, p. 3254, Feb. 2021.
28.  S. E. Andrew, D. T. Ramsey, J. G. Hauptman, and D. E. Brooks, “Density of corneal endothelial cells and corneal thickness in eyes of euthanatized horses,” Am. J. Vet. Res., vol. 62, no. 4, pp. 479–482, Apr. 2001.
29.  D. I. Friedman and K. B. Digre, “Headache medicine meets neuro-ophthalmology: Exam techniques and challenging cases,” Headache, vol. 53, no. 4, pp. 703–716, Apr. 2013.
30.  E. M. Helveston, “Visual training: Current status in ophthalmology,” Am. J. Ophthalmol., vol. 140, no. 5, pp. 903–910, Nov. 2005.
31.  N. Srivastava and R. Salakhutdinov, “Multimodal learning with deep Boltzmann machines,” in Proc. Adv. Neural Inf. Process. Syst. (NeurIPS), 2012