Enhancing Parkinson’s disease identification using ensemble classifier and data augmentation techniques in machine learning

Abstract

Parkinson’s disease (PD) is a devastating neurological syndrome that affects millions of people worldwide. For the successful treatment and control of PD, it is essential to detect it early and diagnose it accurately. Machine learning (ML) algorithms have shown promising results in identifying PD based on various clinical and non-invasive measures. This paper proposes an ensemble classifier-based method to identify PD using ML algorithms. We consider two classes of PD, namely, healthy controls and PD patients. Our approach involves the use of feature selection, feature extraction, and classification techniques to develop a robust and accurate model. We use a dataset that includes clinical measures and necessary features from patients with PD and healthy controls. Our outcomes demonstrate the effectiveness of the proposed method in accurately identifying PD and highlight the importance of ML algorithms in assisting with early detection and diagnosis of PD.