Can one’s fitness tracker gauge their risk of death over years? It seems so. That’s the overall finding from a study conducted by researchers at the University of Illinois that employed around 100,000 participants in the UK Biobank, a massive biomedical database that has in-depth health and genetic information for over half a million people in the United Kingdom. During the study, which was recently published in the journal PLOS, participants used wrist-worn fitness trackers with triaxial accelerometer sensors. Each participant walked for 6 steady minutes a day for a week between 2006 and 2010. And these small bursts of activity revealed some big information.
So how did they calculate mortality risk from the data? They first characterized the participants’ motions during normal daily activities to establish baselines. To create a predictive model, they then incorporated the participants’ walking intensity and duration data with demographic information from the UK Biobank, taking into account age, sex, geography, and death for about 2% of the study’s cohorts. The authors write, “With accurate death records for five years available for the 100,000 participants who wore sensor devices…The accuracy achieved was similar to activity monitors measuring total activity and even similar to physical measures such as gait speed during observed walks.”
One big takeaway from the study is that intensity may matter as much, if not more, than the number of steps taken when it comes to walking; a person’s gait speed — how long it takes them to walk from point A to point B — serves as a key predictor of five-year mortality. The study notes that “measuring physical activity via walking intensity has become a standard practice for certain clinical settings.” Put plainly: “[Studies] have shown intensity to be correlated with survival, as persons who engage in more moderate-to-vigorous activity and less sedentary activity have lower mortality rates.”
While the study relies on wrist-worn trackers, its authors posit that smartphones with accelerometers are likely accurate enough to gather the needed data. And that “our scalable methods offer a feasible pathway towards national screening for health risk.” But the possibilities extend far beyond the UK’s shores. The study notes that “inexpensive smartphones are already widespread worldwide, even in the poorest countries. The global smartphone penetration rate is estimated to have reached over 78% in 2020…. Cheap phones could have a major impact in addressing health equity if proper models can be developed.” And so the technology to gather large-scale health information for people in communities almost anywhere in the world may already be in their hands.
