Automatic Recognition of Parkinson's Disease from Sustained Phonation Tests Using ANN and Adaptive Neuro-Fuzzy Classifier

Neurological disorders contain Parkinson's disease (PD), eNeurological disorders contain Parkinson's disease (PD), epilepsy and Alzheimer's; influence the lives of patients and their families. PD creates cognitive and state of mind disturbances. Generally, the diagnosis is based on medical history and neurological inspection conducted by interviewing and observing the patient in person using the Unified Parkinson's Disease Rating Scale (UPDRS). In this study, we aimed to discriminate between healthy people and people with PD. For that reason, Parkinson dataset that contains biomedical voice of human is used. Artificial Neural Networks (ANN) are widely used in biomedical field for modeling, data analysis, and diagnostic classification. Two types of the ANNs were used for classification: Multilayer Perceptrons (MLP) and Radial Basis Function (RBF) Networks. The other method is Adaptive Neuro-Fuzzy Classifier (ANFC) with linguistic hedges. This method is also used for feature selection from the dataset. Adaptive Neuro-Fuzzy Classifier with linguistic hedges gave the best recognition results with %95.38 training and %94.72 testing classifying performance indeed.