Yan Pang1, Jake Christenson1, Feng Jiang2, Tim Lei1, Remy Rhoades3, Drew Kern4, John A Thompson4, Chao Liu5. 1. Department of Electrical Engineering, University of Colorado Denver, Denver, Colorado, USA. 2. Department of Mathematical and Computer Sciences, Metropolitan State University of Denver, Denver, Colorado, USA. 3. Department of Neurosurgery, University of Colorado Anschutz, Denver, Colorado, USA. 4. Department of Neurosurgery, University of Colorado Anschutz, Denver, Colorado, USA; Department of Neurology, University of Colorado Anschutz, Denver, Colorado, USA. 5. Department of Electrical Engineering, University of Colorado Denver, Denver, Colorado, USA. Electronic address: chao.liu@ucdenver.edu.
Abstract
BACKGROUND: Classification of parkinsonian symptoms, including tremor and bradykinesia, require the application of validated clinical rating scales which are inherently subjective. In this study, we assessed an objective measure of parkinsonian symptomology using automated analysis of hand gestures. NEW METHOD: We constructed and evaluated a hand and finger motion capture apparatus and analysis pipeline that recorded hand/finger motion of control subjects and patients with Parkinson's disease. The detailed three-dimensional (3D) motion features of each finger joint was extracted by using Discrete Wavelet Transform (DWT). The severity of tremor for each finger joint was quantitated by analyzing the motion changes in the frequency domain on four types of motion from five patients and twenty-two control subjects. RESULTS: The proposed approach could distinguish the behavior of patients with Parkinson's disease and control subjects by analyzing the detailed motion features of their hands/fingers. COMPARISON WITH EXISTING METHODS: Previously established methods to quantitate finger movement dynamics focus on speed and amplitude. In contrast, our approach measures unsupervised motion features, in real-time, using wavelet analysis, of each individual finger joint during active free movement. CONCLUSIONS: The proposed study provides an objective assessment of tremor and bradykinesia in Parkinson's disease. Accordingly, this may help movement disorder clinicians to detect, diagnose and monitor treatment efficacy in Parkinson's disease.
BACKGROUND: Classification of parkinsonian symptoms, including tremor and bradykinesia, require the application of validated clinical rating scales which are inherently subjective. In this study, we assessed an objective measure of parkinsonian symptomology using automated analysis of hand gestures. NEW METHOD: We constructed and evaluated a hand and finger motion capture apparatus and analysis pipeline that recorded hand/finger motion of control subjects and patients with Parkinson's disease. The detailed three-dimensional (3D) motion features of each finger joint was extracted by using Discrete Wavelet Transform (DWT). The severity of tremor for each finger joint was quantitated by analyzing the motion changes in the frequency domain on four types of motion from five patients and twenty-two control subjects. RESULTS: The proposed approach could distinguish the behavior of patients with Parkinson's disease and control subjects by analyzing the detailed motion features of their hands/fingers. COMPARISON WITH EXISTING METHODS: Previously established methods to quantitate finger movement dynamics focus on speed and amplitude. In contrast, our approach measures unsupervised motion features, in real-time, using wavelet analysis, of each individual finger joint during active free movement. CONCLUSIONS: The proposed study provides an objective assessment of tremor and bradykinesia in Parkinson's disease. Accordingly, this may help movement disorder clinicians to detect, diagnose and monitor treatment efficacy in Parkinson's disease.