Comparative Analysis of Machine Learning Algorithms for Parkinson’s Disease Prediction

Parkinson’s Disease, a brain disorder which has symptoms like stiffness in the body, shaking, difficulty in walking, maintaining balance and body coordination. Parkinson’s Disease usually begins gradually and worsens over time. Its effects on an individual can be controlled if there is a possibility to detect it in its initial stages. Through various tests, it has been found out that in the most initial stage it affects the speech of an individual. In this work six Machine Learning models - K Nearest Neighbors, Gaussian Naïve Bayes, Logistic Regression, Support Vector Machine, Random Forest and Decision Tree have been compared based on six evaluation metrics – Recall, Accuracy, Precision, F1-Score, False Positive Rate and Area under ROC Curve.