Falls are a significant health issue in Australia – in 2019-2020 they were the largest contributor to hospitalised injuries and the leading cause of deaths due to injury.
But people aged 65 and over are more likely to be hospitalised or die due to a fall compared to any other age, so Australian researchers have created an algorithm that could be used to help improve their walking stability and reduce the risk of falls.
When paired with a wearable technology device, like a smartwatch, The Walk Watch algorithm accurately measures walking steadiness and speed.
The algorithm was developed in a new study published in Scientific Reports.
One of the lead authors of the paper, Lloyd Chan, PhD candidate at Neuroscience Research Australia (NeuRA) and the University of New South Wales Medicine & Health, says this is the first time an algorithm for measuring gait quality has been widely tested in real-world environments and will be made commercially available.
“We know that the way people walk is a predictor of their health. For example, people who walk more slowly, infrequently, in smaller steps or for shorter distances are typically more likely to suffer a fall,” says Chan.
“Our goal was to capture this data through looking at how people naturally walk in their daily lives – and then test this broadly on over 70,000 individuals.”
Read more: Mind and Muscles – How to age well.
Digital gait biomarkers are measurements of a person’s gait – such as posture, cadence, walking speed and length of stride – that can provide insight into their overall health, functional decline, and can predict their likelihood to fall.
But conventional digital gait biomarker measurements are usually geared towards walking on treadmills in the lab and so they don’t accurately assess gait from walking activities in real-world environments.
Also, studies have shown that wearable devices positioned on the lower back and ankle can provide reliable digital gait biomarkers, but these placements can be awkward for the people wearing them.
Devices worn on the wrists are much more convenient, but measurements can be less reliable due to arm movements and being situated further from a person’s centre of mass.
This study aimed to address both of these issues.
In the first stage, 101 participants between 19 and 81 years old, wore the UK Biobank wrist sensor and were recorded performing structured mobility routines in their homes and while walking and running in a lab setting.
Using this new data, the researchers then developed a digital gait biomarker extraction algorithm – Watch Walk – that could measure the gait quality of the individuals wearing the wrist sensor device.
In the second stage of the study, they then tested the validity of the digital gait biomarkers on 78,822 participants aged 46 to 77 years from the UK Biobank database.
Participants wore a sensor on their dominant wrist for seven days, producing a total of 11,646 four-second recordings of movement. These recordings were then classified into ‘walking, running, stationary or unspecified arm’ activities and the Watch Walk algorithm was found to measure these activities with a 93%, 98%, 86%, and 74% precision, respectively.
The authors acknowledge that the digital gait biomarkers were not validated in participants who use walking aids, and walking speed accuracy was lower for walks slower than 0.7 metres/second and faster than 1.8 m/s – so further studies are still needed.
“Our findings build on advances in wrist-worn accelerometer technology, which have previously been more limited to measurements of step count and sleep,” explains Chan.
“As a measurement tool, Watch Walk has so many possibilities. Individuals can gain reliable feedback on their gait and track their improvement over time.
“In the future, we hope to be able to analyse how people walk and predict their risk of disease or mortality,” says Chan.
A Watch Walk app is currently in development and slated for release in late 2023.