The new research saw scientists follow 100,000 participants from the UK Biobank National Cohort who wore activity monitors with motion sensors for a week. Despite the fact that the tested wrist sensors were worn differently than how smartphone sensors are worn, their two motion sensors were used to extract information about the intensity of short bursts of walking.
The researchers were able to successfully derive predictive models of mortality risk using just six minutes a day of regular walking collected by the sensors. They further combined this data with traditional demographic characteristics. The measures acquired from these passively collected data were predictive of 5-year mortality independent of age and sex. Predictive models only used walking intensity to simulate smartphone screens.
Measuring health with a smartphone
“Our results show that passive measurements with motion sensors can achieve similar accuracy to active measurements of walking speed and walking rhythm,” the authors state. “Our scalable methods offer a feasible route to national health risk screening.”
Schatz adds: “I spent a decade using inexpensive phones for clinical models of health status. These have now been tested on the largest national cohort to predict life expectancy at scale. Population”.
Other sensors and monitoring devices
Sensors for monitoring user health have been around for quite some time. In 2018, researchers at Tufts University School of Engineering developed a 2mm x 2mm sensor that tracked nutritional data in real time. Information about everything from salt, glucose, and even alcohol consumption could be collected easily and efficiently by the device. Additionally, it was able to transmit the data wirelessly through the use of radio frequency technology.