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

## TL;DR

This paper introduces a wavelet-based method for analyzing wearable sensor data to effectively monitor key Parkinson's disease symptoms like tremor, bradykinesia, and dyskinesia in at-home settings.

## Contribution

It presents a novel wavelet-based analysis technique for single wrist-worn devices, demonstrating high detection accuracy for Parkinson's symptoms.

## Key findings

- High detection performance for tremor, bradykinesia, and dyskinesia
- Effective analysis using data from wrist-worn smart-watches
- Implications for at-home, uncontrolled patient monitoring

## 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.