Smart watches

Algorithm measures gait quality through smartwatches, could help reduce falls

Participants aged 46 to 77 had to wear a device on their dominant wrists for seven days. Credit: Shutterstock

A new algorithm written by researchers from Neuroscience Research Australia (NeuRA) and UNSW Sydney could help promote the health of older adults and at-risk populations. By pairing with a wearable technology device such as a smartwatch, the Watch Walk algorithm provides an accurate measurement of walking stability and speed and can be used in the future to provide real-time feedback. on how to improve individual gait stability to reduce the risk of falls.

Falls are one of the biggest health and economic problems in Australia, with around 30% of adults over the age of 65 experiencing at least one fall per year. In 2020, treating injuries from falls in older adults costs the economy $2.3 billion.

In a two-stage study, conducted by researchers at NeuRA and UNSW Medicine & Health and published in Scientific reports, 101 participants aged 19 to 81 wore a sensor on their wrist and were recorded performing specific movements at home in addition to walking and running in a laboratory environment. The researchers then used the generated data to create a digital gait biomarker algorithm that could measure gait quality with greater precision, using a combination of lab-assessed and real-world data.

In the second stage of the study, the validity of the digital gait biomarkers was tested on 78,822 participants from the UK Biobank database. Participants aged 46 to 77 were instructed to wear a device on their dominant wrist for seven days and a total of 11,646 four-second motion recordings were then categorized into “Walking”, “Running”, ” Stationary” or “Unspecified arm”. Activities. The Watch Walk algorithm was found to measure these activities with high accuracy (93%; 98%; 86%; and 74% respectively).

Evaluate walking in real environments

Digital gait biomarkers are quantitative measures of aspects of an individual’s gait, such as posture, cadence, gait speed and stride length, which offer information about overall health, functional decline and can often predict their likelihood of falling. However, a limitation of conventional measurements of digital biomarkers of gait is that they are generally geared toward walking on fixed-length treadmills and walkways and do not accurately assess gait of walking activities in real-world environments. .

Lloyd Chan, Ph.D. candidate for NeuRA and UNSW Medicine & Health and one of the paper’s lead authors, said this is the first time that an algorithm for measuring gait quality has been widely tested in real environments and will be marketed.

“We know that the way people walk is a predictor of their health. For example, people who walk more slowly, infrequently, in small steps or for shorter distances are generally more likely to experience a fall. Our aim was to capture that data through looking at how individuals walk naturally in their daily lives, and then testing extensively on over 70,000 people,” he said.

Watch Walk works by measuring walking with a smartwatch’s built-in accelerometer, the same technology that lights up the screen when a smartphone or watch is moved.

“Our findings build on advances in wrist-worn accelerometer technology that were previously limited to step count and sleep measurements. As a measurement tool, Watch Walk offers many possibilities. Individuals can get reliable information about their gait and track their improvement over time. In the future, we hope to be able to analyze how people walk and predict their risk of disease or death,” Chan said. .

Professor Stephen Lord, Senior Principal Investigator at NeuRA and UNSW Medicine & Health, said: “The growth of wearable device technology over recent years has provided an accessible and accessible method of preventing falls in older people. Watch Walk demonstrates that this technology can also be very accurate in real-world settings.”

A Watch Walk application is currently in development and should be released at the end of 2023.

More information:
Lloyd LY Chan et al, Large Scale Development and Validation of Wrist-Worn Digital Gait Biomarkers Watch Walk, Scientific reports (2022). DOI: 10.1038/s41598-022-20327-z

Provided by the University of New South Wales

Quote: Algorithm Measures Gait Quality Through Smartwatches, Could Help Reduce Falls (October 11, 2022) Retrieved November 11, 2022 from gait-smart-falls.html

This document is subject to copyright. Except for fair use for purposes of private study or research, no part may be reproduced without written permission. The content is provided for information only.