Detection and Classification of Early Stages of Parkinson’s Disease Through Wearable Sensors and Machine Learning
Aleksei Shcherbak, Ekaterina Kovalenko, Andrey Somov
Abstract
Parkinson’s disease (PD) is a neurodegenerative disease which is among the most spread and growing common neurodegenerative disorders. It significantly limits the physical and social activities of patients if not diagnosed timely. However, diagnosis of PD at an early stage is not a trivial task as a number of neurodegenerative diseases are characterized by similar symptoms. One of the more pressing concerns is the detection of early stages of PD, namely, stages 1 and 2 for assigning a proper therapy helping to notably reduce the disease progression. In these stages, symptoms might not be as distinguishable and might be more easily confused with other diseases. We report on an approach based on wearable sensors and machine learning to differentiate healthy controls from patients with stages 1 and 2 PD. For this reason, we designed 11 common exercises and collect the data via a wearable commercial off-the-shelf accelerometer, gyroscope, and magnetometer sensors. In total, we collected the data from 113 subjects. Data analysis using machine learning methods (feature extraction, dimensionality reduction, classification) helps greatly improve the accuracy of the PD diagnosis at an early stage. Our best results demonstrate f1-micro scores of 0.78 and 0.88 for PD stages 1 and 2, respectively.