A study on Parkinson’s Disease Diagnosis Using Probabilistic Neural Network

Parkinson s disease (PD) is a neurological illness. It occurs when nerve cells in a part of the brain called the “substantia nigra’” die or become impaired. These cells are responsible for producing a chemical known as dopamine, which allows messages to be sent to the parts of the brain that coordinate movements. By means of the depletion of dopamine-producing cells, these parts of the brain are unable to function normally. PD affects human movements such as walking, talking, and writing negatively. It is one of the most common movement disorders all around the world and usually affects people over the age of 50. In this study, the probabilistic neural network which was used for Parkinson’s disease diagnosis and results of the study were compared with the results of the previous studies reported focusing on Parkinson’s disease diagnosis and using same dataset. We obtained the classification accuracy with probabilistic neural network 95%. Probabilistic neural network provide the highest classification accuracy so far and the classification accuracy was obtained via 10-fold cross validation.