# A Vision-Based Algorithm for Assessing Head and Hand Tremor: Development and Validation Against IMU Sensors

## TL;DR

A new video-based algorithm for analyzing tremors in the head and hands was developed and validated against wearable sensors, showing promising results for remote monitoring.

## Contribution

A novel center-of-mass algorithm for 2D video tremor analysis with open-source implementation for accessible clinical use.

## Key findings

- Moderate-to-good agreement (ICC 0.70–0.80) was found between video-based and IMU-derived tremor power.
- Hand tremor frequency extraction was successfully validated on 30 participants.
- The algorithm is suitable for integration into telemedicine platforms due to its lightweight nature.

## Abstract

What are the main findings?
Development of a novel center-of-mass algorithm for 2D video tremor analysis.Moderate-to-good agreement (ICC 0.70–0.80) with IMU sensors for tremor power.Successful validation of hand tremor frequency extraction on 30 participants.

Development of a novel center-of-mass algorithm for 2D video tremor analysis.

Moderate-to-good agreement (ICC 0.70–0.80) with IMU sensors for tremor power.

Successful validation of hand tremor frequency extraction on 30 participants.

What are the implications of the main findings?
Contactless video analysis serves as a cost-effective alternative to wearable sensors.The lightweight algorithm is suitable for integration into telemedicine platforms.Open-source implementation enables accessible and remote clinical tremor monitoring.

Contactless video analysis serves as a cost-effective alternative to wearable sensors.

The lightweight algorithm is suitable for integration into telemedicine platforms.

Open-source implementation enables accessible and remote clinical tremor monitoring.

Tremor is the most prevalent human movement disorder, characterized by rhythmic oscillations of a body part. Accurate tremor assessment is essential for diagnosis, monitoring, and treatment evaluation. Traditional methods rely on accelerometry-based measurements, requiring direct sensor attachment, which may be impractical in some settings. We developed a novel algorithm for detecting tremors from video recordings based on the motion of the center of mass and implemented it in the open-source software TremAn3. Motion data were extracted from 2D video recordings of both hands and the head, and spectral analysis was then performed to quantify the tremor by calculating peak tremor power and peak power frequency. A total of 30 videos were recorded from 30 participants with essential or dystonic tremors. Simultaneously, acceleration signals were collected using inertial measurement units (IMUs) placed on the backs of the hands and forehead as a gold-standard reference. Agreement between video- and IMU-derived metrics was assessed using intraclass correlation coefficients (ICCs) and mean absolute error (MAE). For PP, video-based estimates showed moderate-to-good agreement (ICC: 0.70 left hand, 0.77 right hand, 0.80 head) with MAE of 8.12–10.80 dB. For PPF, agreement was moderate for the hands (ICC: 0.60 left, 0.67 right; MAE: 0.54–0.76 Hz) but poor for head PPF (ICC: 0.08; MAE: 2.06 Hz). Our results indicate that video analysis can serve as a viable alternative to traditional accelerometry for tremor quantification. This contactless method holds significant potential for telemedicine and research applications.