A Decision Support System for Parkinsonʹʹs Disease Diagnosis using Classification and Regression Tree

Parkinsonʹs disease (PD) is a progressive disorder of the nervous system that affects movement. It develops gradually, often starting with a barely noticeable tremor in just one hand. But while tremor may be the most well-known sign of Parkinsonʹs disease, the disorder also commonly causes a slowing or freezing of movement. Parkinsonʹs disease is the second most common Neurodegenerative action only surpassed by Alzheimerʹs disease. However, a proper diagnosis at an early stage can result in significant life saving. A system for automated medical diagnosis would enhance the accuracy of the diagnosis and reduce the cost effects. The present study compares the accuracy of several machine learning methods including Bayesian Networks, Regression, Classification and Regression Trees (CART), Support Vector Machines (SVM), and Artificial Neural Networks (ANN) for proposing a decision support system for diagnosis of parkinsonʹs disease. The proposed system achieved an accuracy of 93.7% using classification and regression tree. Sensitivity analysis via classification and regression tree was also used to find importance of input variables.