# Continuous Accelerometry-Based Tremor Detection During Daily Living

## TL;DR

A new algorithm detects Parkinsonian tremors in real-time during daily activities using a wrist-worn accelerometer, offering more precise and adaptive monitoring than current methods.

## Contribution

The algorithm enables second-scale tremor detection and distinguishes tremor from voluntary movement using a commercial wearable device.

## Key findings

- The algorithm detects tremors on a second scale, outperforming the industry standard which detects on a minute scale.
- Tremor detection is highly correlated with DBS intensity, showing decreased tremor as DBS intensity increases.
- The algorithm distinguishes between voluntary physical activity and tremor with high accuracy.

## Abstract

We developed an automated algorithm which detects Parkinsonian tremor during daily living activities using a commonly available commercial wearable accelerometer.

What are the main findings?
Detects tremors on a second scale, whereas the currently known industry standard detects tremors on a minute scale.Distinguishes between voluntary physical activity and tremor.The output was highly correlated with the DBS intensity, such that detected tremor decreased as DBS intensity increased.

Detects tremors on a second scale, whereas the currently known industry standard detects tremors on a minute scale.

Distinguishes between voluntary physical activity and tremor.

The output was highly correlated with the DBS intensity, such that detected tremor decreased as DBS intensity increased.

What are the implications of the main findings?
Results from pilot testing our algorithm demonstrate the feasibility of practically implementing continuous tremor detection for Parkinson’s patients with deep brain stimulation (DBS) using a commercially available, convenient, wrist-worn watch.Continuous tremor estimates on a seconds resolution will enable adaptation of brain stimulation based on the patient’s current tremor state.

Results from pilot testing our algorithm demonstrate the feasibility of practically implementing continuous tremor detection for Parkinson’s patients with deep brain stimulation (DBS) using a commercially available, convenient, wrist-worn watch.

Continuous tremor estimates on a seconds resolution will enable adaptation of brain stimulation based on the patient’s current tremor state.

As a step towards advancing adaptive DBS control for Parkinson’s disease, we have developed an automated algorithm that detects tremor continuously on a seconds-resolution time scale from a wearable accelerometer and present the feasibility study test results. Triaxial acceleration data were wirelessly streamed from an Apple Watch as well as acquired from an internal accelerometer in the implanted DBS device itself. The algorithm first determines if there is any high-power voluntary activity, such as walking, using the arm, or transitioning from sitting to standing; then, it identifies peaks in the 4–7 Hz Parkinsonian tremor frequency band. Peak detection for tremor activity was more accurate using the Apple Watch than the IPG. Peak and harmonic detection were also more accurate using continuous wavelet transforms than short-time Fourier transform. According to the repeated measures correlation, our detection algorithm correlated strongly with DBS intensity (Subject RZCH: r = −0.93, p = 3.6 × 10−5; 6KOZ: r = −0.97, p = 1.6 × 10−5, NU5U: r = −0.94, p = 0.057). Pearson’s correlation coefficient between our tremor detection algorithm and the currently accepted industry metric was found to be 0.57 (t-value = 8.5, dof = 148, p < 1 × 10−6). Our algorithm is distinctive in the capability to detect Parkinsonian tremor, with a high degree of clinical relevance, during daily living activities and is able to discriminate tremor from walking, using a convenient, commercial wrist-worn accelerometer.