Gait metrics – measures such as walking speed, step length and doubled support time (i.e., the ratio of the gait cycle to when both feet are on the ground) – are known as important biomarkers To assess a person’s overall health, risk of falls, and progression of neurological or musculoskeletal conditions. Analyzing how a person walks, known as gait analysis, provides valuable, non-invasive insight into general well-being, injuries, and health concerns.
Historically, measuring gait required expensive, specialized laboratory equipment, making continuous tracking impractical. While smartphones now offer a portable option using their embedded inertial measurement units (IMUs), they demand precise placement – such as a thigh pocket or belt – for the most accurate results. In contrast, smartwatches are worn in a fixed location on the wrist. This provides a more practical and consistent platform for continuous tracking, expanding the tracking window even for phone-less scenarios like walking around the house.
Despite this significant logistics advantage, smartwatches have historically lagged smartphones in comprehensive gait metric evaluation. In our work, “Smartwatch-based walking metrics estimation“, we sought to bridge this gap. We demonstrated that consumer smartwatches are a highly feasible, accurate, and reliable platform to estimate a comprehensive suite of spatio-temporal gait metrics with performance comparable to smartphone-based methods.
