Support vector machine classification of Parkinson's disease, essential tremor and healthy control subjects based on upper extremity motion

Abstract

Patients with Parkinson's disease (PD), a chronic progressive neurodegenerative disorder, can have symptoms similar to essential tremor (ET), a 'benign' condition, making differential diagnoses sometimes challenging. In this paper we investigate the performance of a support vector machine classifier which may facilitate diagnosing PD and ET patients. Wireless inertial sensors were used to measure angular velocity and acceleration during multi-joint arm motion as well as during rest, postural and action tremor tasks from seven PD, seven ET and seven CO patients. Mean rest tremor was statistically significantly different between the PD and CO groups, while for the ET and CO groups mean postural tremor was statistically significantly different. Two SVMs were developed which operated on features extracted from the tremor acceleration signals. The misclassification rates of the SVMs were 9.5% for the tremor versus non-tremor SVM and 14.3% for the PD versus ET SVM.