Parkinson’s Disease Diagnosis using Supervised Machine Learning Techniques

Many people throughout the world suffering with Parkinson’s disease (PD), which is more common in people over 50. Even now, in the era of numerous technologies and developments, early disease identification is still difficult. This makes it necessary for machine learning-based automatic techniques that aid clinicians in accurately detecting this medical condition in its early stages. Finding the best method for classification is difficult since it depends on how the algorithm is applied to the dataset. In order to compare and determine by these classification algorithms is the most effective and accurate for classifying PD, seven machine learning (ML) techniques-including decision tree, logistical regression, K nearest neighbour, Naive Bayes, random forest, Support vector machine and XBoost-have been used on a dataset based on 24 variables. The highest performing classifiers, with a classification accuracy of 95.38% obtained by Xboost and RF.