Smartphone Fitness Tracker Predicts Risk of Dying

A person’s risk of death over the next five years can be predicted with a smartphone fitness tracker using accelerometer sensors that capture fitness data, according to new research conducted by a team at the University of Illinois at Urbana Champaign.

The study was successfully validated using only six minutes of steady walking per day over one week’s time, and it was determined by analyzing characteristics of motion from walking sessions of 103,683 participants in the UK Biobank. Participants wore activity monitors for a week.

Combined with traditional demographic characteristics, the researchers extracted information on intensity from short bursts of activity. Gait speed data was passively calculated and was a predictor of five-year mortality independent of age and sex. Those with lower mortality had moderate-to-vigorous walking motion and less sedentary activity.

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

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

Predictions based on the model rely on the intensity of short walks, which is supposed to be an effective representative for intensity of activities over whole days. This is similar to the base assumption of walk tests, according to a study published by the team in the journal PLOS.

MoveSpring and MyFitnessPal Apps identified with trackers

Several apps, such as MoveSpring and MyFitnessPal, also use these techniques. This has led scientists to hypothesize that sensors could reveal more than your physical activity. They could also possibly predict how likely you are to die.

Mobile device accelerometers track an individual’s movements by detecting the orientation of the smartphone. Their use during normal activities is limited since the only such current devices are smartphone devices with embedded accelerometers.

“While the wrist sensor is worn differently than how smartphone sensors are carried, their motion sensors can be used to extract information on walking intensity from short bursts of walking—a daily living version of a walk test,” researchers said in a statement.

Subjects filled out questionnaires about their current health status, and the predictive models used only walking intensity to simulate smartphone monitors.

Smartphone fitness tracker will benefit the health sector

Healthcare infrastructure implementation could benefit tremendously from the devices, says the US team. The technology opens the door for easier health screenings, and large-scale population data could delineate health risks without intruding into people’s daily lives.

Professor Schatz told SWNS, “Our scalable methods offer a feasible pathway towards national screening for health risk. Digital health [might offer] potential solutions if sensor devices of adequate accuracy for predictive models could be widely deployed.”

He added that “measuring walking intensity is possible, but…total activity measure with 24 hour wearable devices is not. The accuracy achieved was similar to activity monitors measuring total activity and even similar to physical measures such as gait speed during observed walks.”

“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 wrote in their paper. “We analyzed this dataset to extract walking sessions during daily living, [and] then used characteristic motions to predict mortality risk.”

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