EUVIMEDEUVIMED entdecken
Crossref

Early Prediction of Neurodegenerative Disorders Using Multimodal Deep Learning

Dhiraj Jha, Apsara Das Shreshtha, Utsha Sarker, Lucky Nandani Thakur, Archy Biswas

International Journal of Innovative Science and Research Technology · 03.03.2026 · 2455

DOI: 10.38124/ijisrt/26feb1296 ↗

Kurz gefasst

Fachartikel in der Zeitschrift International Journal of Innovative Science and Research Technology, online erschienen am 03.03.2026. Verfasst von Dhiraj Jha und 4 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 31 Literaturangaben.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

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.

Zitieren

APA

Jha, D., Shreshtha, A. D., Sarker, U., Thakur, L. N., & Biswas, A. (2026). Early Prediction of Neurodegenerative Disorders Using Multimodal Deep Learning. International Journal of Innovative Science and Research Technology, 2455. https://doi.org/10.38124/ijisrt/26feb1296

Vancouver

Jha D, Shreshtha AD, Sarker U, Thakur LN, Biswas A. Early Prediction of Neurodegenerative Disorders Using Multimodal Deep Learning. International Journal of Innovative Science and Research Technology. 2026:2455. doi:10.38124/ijisrt/26feb1296

BibTeX
@article{Jha2026,
  author = {Jha, Dhiraj and Shreshtha, Apsara Das and Sarker, Utsha and Thakur, Lucky Nandani and Biswas, Archy},
  title = {Early Prediction of Neurodegenerative Disorders Using Multimodal Deep Learning},
  journal = {International Journal of Innovative Science and Research Technology},
  year = {2026},
  pages = {2455},
  doi = {10.38124/ijisrt/26feb1296}
}
Kostenlos starten →