Classification of Parkinson disease data with artificial neural networks

Abstract

Abstract An artificial neural network system has been developed to detect Parkinson’s Disease (PD). Three samples were taken from each patient and included in the system. The importance of the study is based on the development and use of a new subject-based ANN approach that takes into account the dependent nature of the data in a replicated measure-based design. In order to evaluate the performance of the proposed system, an audio replication-based experiment was performed to differentiate healthy people from PD patients. The UCI Experiment consisted of 80 subjects, half of whom were affected by PD. Although the proposed system has a reduced number of subjects, the system is able to distinguish people with PD from an acceptable degree of healthy people with an accuracy rate of 94.93% in an artificial neural network.