JMIR Publications

ABSTRACT

Background:

Digital health technologies (DHTs), such as accelerometry, offer low participant burden and provide quantitative metrics with ease of deployment, making them increasingly popular for gait monitoring. Remote gait monitoring delivers quantifiable, continuous health measures over extended periods, surpassing limited insights from single clinic or lab visits, thus offering a more comprehensive health perspective. Numerous gait algorithm implementations, inspired by prior research, aim to standardize these metrics across devices. The SciKit Digital Health (SKDH) package exemplifies this as a device-agnostic framework.

Objective:

This study introduces a series of literature-informed enhancements to the SKDH gait algorithm, improving its performance against reference standards and reducing the necessity for manual parameter adjustments across diverse populations.

Methods:

A step-wise refinement process was undertaken, examining each algorithmic component for potential enhancements and evaluating their cumulative impact on the complete gait algorithm and metrics generated.

Results:

Utilizing data from healthy adult and pediatric participants, the novel gait event estimation method significantly reduced the mean absolute error by over 50% compared to its predecessor. Post-updates, the intra-class correlation (ICC) values for final gait metric concordance with the in-lab reference improved markedly, from 0.50-0.74 to 0.81-0.90. Additionally, the systematic bias observed in the previous version’s gait speed estimation was rectified, narrowing the difference from reference from 0.065-0.230m/s to 0.00-0.03m/s.

Conclusions:

The findings from this study offer robust evidence supporting the validity of the enhancements made to the gait algorithm. They demonstrate that a single lumbar accelerometer can capture gait characteristics with high accuracy and reliability across various speeds and age groups.