Machine Learning Based Approaches for Prediction of Parkinson's Disease

Abstract

The prediction of Parkinson’s disease is most important and challenging problem for biomedical engineering researchers and doctors. The symptoms of disease are investigated in middle and late middle age. In this paper, minimum redundancy maximum relevance feature selection algorithms is used to select the most important feature among all the features to predict the Parkinson diseases. Here, it is observed that the random forest with 20 number of features selected by minimum redundancy maximum relevance feature selection algorithms provide the overall accuracy 90.3%, precision 90.2%, Mathews correlation coefficient values of 0.73 and ROC values 0.96 which is better in comparison to all other machine learning based approaches such as bagging, boosting, random forest, rotation forest, random subspace, support vector machine, multilayer perceptron, and decision tree based methods.