Abstract
Parkinson's disease (PD) is a neurodegenerative disorder that affects both non-motor and motor functions as the disease progresses. Patients with PD experience a phenomenon known as "wearing-off," where symptoms re-emerge before the next scheduled medicine intake, leading to discomfort. Consequently, it is crucial for PD patients and clinicians to closely monitor and document changes in symptoms to ensure appropriate treatment. In this study, we propose an ensemble learning approach that utilizes wearable data to predict PD patients' wear-off. Therefore, medical practitioners can devise tailored treatment strategies to effectively manage Parkinson's disease and its associated symptoms. Our experiments involved a combination of ensemble machine learning models (Random Forest, Support Vector Machine, and XGBClassifier) along with two deep learning-based models (convolutional neural network and long short-term memory), resulting in an impressive accuracy of approximately 93.2% . Code is available at : {https://github.com/mdhosen/Parkinson-detection}.
