Classification Algorithms for Analyzing Parkinson's Disease Patient

Parkinson's disease is a neurodegenerative disorder characterized by motor and non-motor symptoms; it is difficult to detect and treat promptly. We aimed to classify Parkinson's disease patients versus healthy control subjects. We used for experimentation a real dataset that contains Gait characteristics extracted using inertial motion sensors from a smartphone (iPhone 5S). Sixty people participated in this experiment, 53 of whom were people with Parkinson's disease. We implemented feature selection methods to reduce dimensionality. Furthermore, we implemented four classification algorithms and evaluated them based on their accuracy, sensitivity, and specificity. The Support Vector Machine algorithm obtained an overall accuracy of 97.5%, a sensitivity of 95.3%, and a specificity of 99.8%.