Prediction of Parkinson's Disease by Analyzing fMRI Data and using Supervised Learning

Abstract

Parkinson's disease is the second most common neurodegenerative disorder after Alzheimer's disease. Almost 10 million people are estimated to have the disorder of Parkinson's disease. However, Parkinson's symptoms appear gradually and get worse over time. Therefore, the detection of Parkinson's disease at an early stage might significantly improve lifestyle by giving proper treatment. In recent years, the use of Functional Imaging in neurodegenerative diseases has increased. As Functional Imaging seems very efficient in the case of brain disorders, we used Functional Magnetic Resonance Imaging (fMRI) data for conducting our research. Furthermore, SVM classifier was used for the classification and prediction of Parkinson's disease. Using our proposed method, we have achieved 100% sensitivity, specificity, and accuracy considering seven subjects. However, one subject was exceptional whereas we have achieved 99.76% accuracy, 100% specificity, and 99.53% sensitivity. Finally, this process is a well-structured model for predicting the early stages of PD. It may help the doctors for diagnosis of the disease at its early stages and the patients should receive better treatment.