Paper Title
Predictive Analytics for Parkinson’s Disease: A Machine Learning Perspective

Abstract
Parkinson's disease is the second most common age-related neurological disorder, and it has multiple physical and mental symptoms. Parkinson's disease is difficult to figure out because its symptoms, such as serious shaking, speech difficulty, slowness of movement, poor balance and coordination are similar to the symptoms of aging. Symptoms typically appear around the age of 50. While there is no cure for Parkinson's disease, certain medications may reduce symptoms and help patients to maintain their quality of life. It is important to detect and prevent the spread of this disease. Many studies have been conducted on the disease's analysis. The aim of this project is to predict Parkinson's disease using various Machine Learning (ML) models, including Support Vector Machine (SVM), Decision Tree (DT) and Random Forest (RF) based on voice signal features to differentiate between healthy people and Parkinson's disease patients. The dataset included 195 voice recordings from examinations conducted on 31 patients and is obtained from the machine learning repository at the University of California, Irvine (UCI). The experimental results demonstrate that utilizing RF yields optimal predictive accuracy for diagnosing Parkinson's disease, making it a seamless fit for healthcare diagnostics. Keywords - Parkinson's disease, Machine Learning, Support Vector Machine, Decision Tree, Random Forest