Importance of Attribute Selection for Parkinson Disease

Abstract

Parkinson disease is a neurological disorder occurring at older ages. It is one of the most painful, dangerous and untreated diseases. In this study, a new application based on assessing the importance of attributes using the ranking techniques was carried out for diagnosis of this disease. The effects of the attributes on the Parkinson disease are determined by utilizing Stability Selection method. The selected attributes dataset and all attributes dataset have been sent as input data to the Random Forest and Logistic Regression algorithms in order to investigate the best model which is to be effective in the diagnosis of this disease. This study including the model which presented the best performance might be a powerful tool for effective diagnosis of this disease.