Smartphone fitness tracker data could predict death risk over the next 5 years

CHAMPAIGN, Ill. — Smartphone fitness trackers can predict a person’s risk of death over the next five years, according to new research. The technology opens the door for easier health screenings, according to scientists at the University of Illinois at Urbana-Champaign.

The findings are based on 100,000 participants in the UK Biobank who wore activity monitors on their wrist with motion sensors for one week. They extract information on intensity from short bursts of activity, a daily version of a walking test.

The team was able to successfully validate predictive models using only six minutes a day of steady walking, combined with traditional demographic characteristics. The equivalent of gait speed calculated from this passively collected data was a predictor of five-year mortality independent of age and sex.

“Mortality is the most definitive outcome, with accurate death records for five years available for the 100,000 participants who wore sensor devices,” study authors write in their paper. “We analyzed this dataset to extract walking sessions during daily living, then used characteristic motions to predict mortality risk. The accuracy achieved was similar to activity monitors measuring total activity and even similar to physical measures such as gait speed during observed walks. Our scalable methods offer a feasible pathway towards national screening for health risk.”

The predictive models described in PLOS Digital Health used only walking intensity to simulate smartphone monitors.

“Our results show passive measures with motion sensors can achieve similar accuracy to active measures of gait speed and walk pace,” the authors say in a media release. “Our scalable methods offer a feasible pathway towards national screening for health risk.”

PhoneWalk
Measuring health with carried smartphone, from characteristic motion of human body computed from phone sensor. (CREDIT: Qian Cheng)

“I have spent a decade using cheap phones for clinical models of health status. These have now been tested on the largest national cohort to predict life expectancy at population scale,” adds Bruce Schatz from the University of Illinois at Urbana-Champaign.

Healthcare infrastructure implementation could benefit tremendously from the devices, the researchers believe. Large-scale population data could delineate health risks without intruding into people’s daily lives.

“Digital health offers potential solutions if sensor devices of adequate accuracy for predictive models could be widely deployed,” Prof. Schatz tells SWNS.

The only current devices are smartphones with embedded accelerometers, limiting their use when they are carried during normal activities.

“So measuring walking intensity is possible, but the total activity measure with 24 hour wearable devices is not,” study authors write. “The accuracy achieved was similar to activity monitors measuring total activity and even similar to physical measures such as gait speed during observed walks. Our scalable methods offer a feasible pathway towards national screening for health risk.”

South West News Service writer Mark Waghorn contributed to this report.

YouTube video

Leave a Reply

Your email address will not be published. Required fields are marked *