A study of more than 100,000 adults found that motion sensor data from just 6 minutes of walking was enough to predict five-year mortality risk as accurately as other leading methods
20 October 2022
By Grace Wade
Data from just 6 minutes of walking, collected via motion sensors in smartphones, may be enough to predict someone’s risk of dying in the next five years.
Previous studies have estimated mortality risk using daily physical activity level, measured by wearable motion sensors in devices like fitness watches. Yet despite the growing popularity of smart watches and fitness trackers, they are still mostly worn by an affluent minority.
Most people own smartphones with similar sensors, but calculating mortality risk from activity data they gather is difficult because people don’t tend to carry their phones all day, says Bruce Schatz at the University of Illinois Urbana-Champaign.
To find an alternative predictor that is measurable with smartphones, Schatz and his colleagues looked at data from 100,655 participants in the UK Biobank study, which has been collecting information on the health of middle-aged and senior adults living in the UK for more than 15 years. As part of that study, participants wore motion sensors on their wrists for one week. About 2 per cent of the participants died during the following five years.
The researchers ran motion sensor and death data on about one-tenth of participants through a machine learning model, which developed an algorithm that estimated five-year mortality risk using acceleration during a 6-minute walk.
“For many diseases, specifically heart or lung diseases, there’s a very characteristic pattern where people slow down when they’re out of breath and speed up again in short doses,” says Schatz.
They then tested the model using data from the other participants and determined its c-index score – a metric commonly used in biostatistics to assess accuracy – was 0.72, which is comparable to other metrics of estimating life expectancy, like daily physical activity or health risk questionnaires.
“This predictor is as strong as or stronger than traditional risk factors,” says Ciprian Crainiceanu at Johns Hopkins University in Maryland.
While this study used wrist-worn motion sensors, smartphones are also capable of measuring acceleration during short walks, says Schatz, who is currently planning a larger study using smartphones. “If people carry phones around, you could do a weekly or daily prediction and that’s something you cannot get by any other method,” he says.
Journal reference: PLoS Digital Health , DOI: 10.1371/journal.pdig.0000045
Sign up to our free Health Check newsletter for a round-up of all the health and fitness news you need to know, every Saturday
More on these topics: