Parkinson's Disease Detection Using Machine Learning
International Journal of Drug Delivery Technology · 23.05.2026 · 16 (31s)
DOI: 10.25258/ijddt.16.31s.73 ↗Kurz gefasst
Fachartikel in der Zeitschrift International Journal of Drug Delivery Technology, online erschienen am 23.05.2026. Verfasst von Syed Amirah Rizwan und 1 weiteren Autor:innen.
Abstract (Originalsprache)
For this project, machine learning techniques are applied in order to build an accurate and early detection system for Parkinson's disease. The dataset consisting of clinical data along with patient information is pre-processed and separated into training and test sets. SVMs and XGBoost techniques are applied in this case to optimize the models based on several evaluation criteria. Finally, the developed models can greatly improve the early detection of Parkinson's disease leading to timely treatment. Finally, in order to evaluate and optimize the developed models, several performance metrics are used. In particular, accuracy, precision, recall, F1 score, ROC-AUC, and confusion matrix are some of the key metrics used in the evaluation process of the developed models. Alongside these performance metrics, feature importance analysis is carried out to identify the key factors behind Parkinson's disease detection. Feature importance visualizations are created for both models for a better interpretation of their decisions.
Zitieren
APA
Rizwan, S. A., & Shrivastava, R. (2026). Parkinson's Disease Detection Using Machine Learning. International Journal of Drug Delivery Technology, 16(31s). https://doi.org/10.25258/ijddt.16.31s.73
Vancouver
Rizwan SA, Shrivastava R. Parkinson's Disease Detection Using Machine Learning. International Journal of Drug Delivery Technology. 2026;16(31s). doi:10.25258/ijddt.16.31s.73
BibTeX
@article{Rizwan2026,
author = {Rizwan, Syed Amirah and Shrivastava, Ritesh},
title = {Parkinson's Disease Detection Using Machine Learning},
journal = {International Journal of Drug Delivery Technology},
year = {2026},
volume = {16},
number = {31s},
doi = {10.25258/ijddt.16.31s.73}
}
EUVIMED