A Wavelet-Based Approach To Monitoring Parkinson's Disease Symptoms

2016/12/14 by Avishai Wagner, Wagner, Avishai, Naama Fixler +3
Health Professions · Mathematics · Medicine · #Balance, Gait, and Falls Prevention #Neurological disorders and treatments #Parkinson's Disease Mechanisms and Treatments #stat.AP

paper · pdf · doi:10.48550/arxiv.1701.03161

ICASSP 2017

arxiv created 2017/02/06 · arxiv updated 2017/02/08

Abstract

Parkinson's disease is a neuro-degenerative disorder affecting tens of millions of people worldwide. Lately, there has been considerable interest in systems for at-home monitoring of patients, using wearable devices which contain inertial measurement units. We present a new wavelet-based approach for analysis of data from single wrist-worn smart-watches, and show high detection performance for tremor, bradykinesia, and dyskinesia, which have been the major targets for monitoring in this context. We also discuss the implication of our controlled-experiment results for uncontrolled home monitoring of freely behaving patients.

Citations

• Orthonormal bases of compactly supported wavelets

Related

• Reducing a complex two-sided smartwatch examination for Parkinson's Disease to an efficient one-sided examination preserving machine learning accuracy
• Parkinson's Disease Assessment from a Wrist-Worn Wearable Sensor in Free-Living Conditions: Deep Ensemble Learning and Visualization
• Granular Motor State Monitoring of Free Living Parkinson's Disease Patients via Deep Learning
• TreCap: A wearable device to measure and assess tremor data of visually guided hand movements in real time
• High Frequency Remote Monitoring of Parkinson's Disease via Smartphone: Platform Overview and Medication Response Detection