Parkinson disease classification: a comparative analysis on classification techniques

Nazri Mohd Nawi (Universiti Tun Hussein Onn Malaysia (UTHM))
Mokhairi Makhtar (Universiti Sultan Zainal Abidin)
Zehan Afizah Afip (Universiti Tun Hussein Onn Malaysia (UTHM))
Mohd Zaki Salikon (Universiti Tun Hussein Onn Malaysia (UTHM))

Indonesian Journal of Electrical Engineering and Computer Science
Vol 18, No 3: June 2020

Parkinson’s disease (PD) among Alzheimer’s and epilepsy are one of the most common neurological disorders which appreciably affect not only live of patients but also their households. According to the current trend of aging social behaviour, it is expected to see a rise of Parkinson’s disease. Even though there is no cure for PD, a proper medication at the early stage can help significantly in alleviating the symptoms. Since, the traditional method for identifying PD is rather invasive, expansive and complicated for self-use, there is a high demand for using classification method on PD detection. This paper compares the performance of Neural Network and decision tree for classifying and discriminating healthy people for people with Parkinson’s disease (PD) by distinguishing dysphonia. The simulation results demonstrate that Neural Network outperformed decision tree by giving accurate results with 87% accuracy as compared to decision tree with only 84% accuracy in determining the classification of healthy and people with Parkinson’s.