Multimodel Deep Learning Framework for Early Detection of Parkinson's Disease
Journal of Information Technology and Digital World · 05.06.2026 · 8 (3) · 140-154
DOI: 10.36548/jitdw.2026.3.001 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Information Technology and Digital World, online erschienen am 05.06.2026. Verfasst von Sheebha S.N. und 2 weiteren Autor:innen. Die Arbeit nennt 11 Literaturangaben.
Abstract (Originalsprache)
Parkinson’s Disease (PD) is a progressively occurring neurodegenerative disease that impacts motor functions and coordination. However, early diagnosis of PD is extremely important, and the current diagnosis methods available do not have any level of comprehensiveness or objectivity. This study explores the use of a multimodal approach to detect Parkinson’s disease at its early stages through deep learning methods. Magnetic Resonance Imaging (MRI) images are extracted using Sobel filter, K-Means segmentation, and VGG19 feature extraction, while Spiral drawings are processed through edge detection using Canny edge detection and contour-based features. Some of the models used include SVM, AdaBoost, Random Forest, and logistic regression, and the final model uses a combination of these classifiers and a score-level fusion model of both modalities. The proposed stacked ensemble model achieved 96.41% accuracy, 96% Precision, 96% recall, 96% f1-score, and a ROC-AUC of 0.99, which is significantly better than single modality baselines.
Zitieren
APA
S.N., S., S., H., & W., A. B. (2026). Multimodel Deep Learning Framework for Early Detection of Parkinson's Disease. Journal of Information Technology and Digital World, 8(3), 140-154. https://doi.org/10.36548/jitdw.2026.3.001
Vancouver
S.N. S, S. H, W. AB. Multimodel Deep Learning Framework for Early Detection of Parkinson's Disease. Journal of Information Technology and Digital World. 2026;8(3):140-154. doi:10.36548/jitdw.2026.3.001
BibTeX
@article{SN2026,
author = {S.N., Sheebha and S., Harini and W., Agnes Belsia},
title = {Multimodel Deep Learning Framework for Early Detection of Parkinson's Disease},
journal = {Journal of Information Technology and Digital World},
year = {2026},
volume = {8},
number = {3},
pages = {140--154},
doi = {10.36548/jitdw.2026.3.001}
}
EUVIMED