Exploring Parkinson's Disease Pathophysiology Through Random Forest Analysis

Parkinson's disease (PD) is a serious neurological disorder characterized by symptoms such as shaking, stiffness, and difficulty walking. Diagnosing PD can be challenging due to its gradual symptoms. This study employs machine learning techniques (ML) to improve diagnosis and enhance the quality of life for individuals with PD. By analyzing a diverse medical dataset containing text, numbers, and images, the proposed approach aims to uncover hidden patterns through ML. The dataset is divided into two equal parts: healthy and those with Parkinson's disease, and validated using classifiers based on acoustic features. This novel data partitioning approach, focusing on acoustic scoring, facilitates early detection and improves therapeutic care of patients. Among the tested algorithms, the enhanced Random Forest classifier demonstrated superior performance, achieving an accuracy of 99.30%. These findings suggest this models, particularly those based on the Random Forest algorithm, offer significant potential for accurate and reliable PD prediction and better management of the disease.