According to recent studies, passive smartphone monitoring of people’s walking activity can be used to build population-level models of health and mortality risk. PLOS Digital Health study. Read a summary of findings from Bruce Schatz, University of Illinois, Urbana-Champaign, USA, and his colleagues below, or full article of PLOS Digital Health.
Previous studies have used measures of physical fitness, such as the walk test and self-reported walking pace, to predict individual mortality risk. These metrics focus on quality rather than quantity of movement. For example, measuring an individual’s walking speed has become standard practice in certain clinical settings. The rise of passive smartphone activity monitoring opens up the possibility of population-level analysis using similar metrics.
Study design and results
Researchers studied 100,000 participants in the UK’s Biobank National Cohort who wore activity monitors with motion sensors for one week. While the wrist sensor is worn differently than the smartphone sensor is carried, both motion sensors are used to extract information about walking intensity from short bursts of walking, the everyday living version of the walking test. I can do it.
The team was able to successfully validate a predictive model of mortality risk by combining a steady six-minute walk per day collected by sensors with traditional demographic characteristics. . The walking speed equivalent calculated from this passively collected data was a predictor of 5-year mortality independent of age and sex (pooled C-index 0.72). The predictive model used only gait intensity to simulate smartphone monitors.
“Our results show that passive measurements using motion sensors can achieve similar accuracy as active measurements of walking speed and walking pace,” the authors say. “Our scalable method provides a viable pathway towards nationwide screening for health risks.”
“I’ve spent 10 years using cheap phones on clinical models of health conditions,” Schatz says. .”