Early Detection of Parkinson’s Disease Using Center of Pressure Data and Machine Learning
Rabie Fadil, Asenath Huether, Robert Brunnemer, Andrew P. Blaber, Jau‐Shin Lou, Kouhyar Tavakolian
Abstract
Parkinson's disease (PD) is a progressive neurodegenerative disorder resulting in abnormal body movements. Postural instability is one of the primary motor symptoms of PD and contributes to falls. Measurement of postural sway through center of pressure (COP) data might be an objective indicator of Parkinson's disease. The goal of this work is to use machine learning to evaluate if different features of postural sway can differentiate PD patients from healthy controls. Time domain, frequency domain, time-frequency, and structural features were extracted from COP data collected from 19 PD patients and 13 healthy controls (HC). The calculated parameters were input to various machine-learning models to classify PD and HC. Random Forest outperformed the rest of the classifiers in terms of accuracy, false negative rate, F1-score, and precision. Time domain features had the best performance in differentiating PD from HC compared to other feature groups.