New analysis exhibits {that a} smartphone can precisely predict the danger of dying

The researchers suppose their strategies present a viable pathway for screening well being dangers on the nationwide degree.

The researchers conclude that passive smartphone monitoring of population-level strolling exercise gives a option to implement nationwide well being and mortality danger screening.

Passive smartphone monitoring of individuals’s strolling exercise can be utilized to create population-level well being and mortality danger fashions, in line with a brand new research by Bruce Schatz of the College of Illinois at Urbana-Champaign and colleagues. The analysis, which discovered that smartphone sensors might precisely predict a person’s 5-year mortality danger, was just lately printed within the journal. PLOS Digital Well being.

Earlier analysis has used bodily health assessments and self-reported strolling speeds to estimate mortality danger for particular people. These measures concentrate on the standard of motion reasonably than the amount; for instance, assessing a person’s gait velocity has change into frequent follow in some medical settings. The rise of passive smartphone exercise monitoring makes population-level evaluation potential utilizing comparable metrics.

Health measurement phone

Measuring well being with a carried smartphone, based mostly on the attribute motion of the human physique calculated from a cellphone sensor. Credit score: Qian Cheng (CC-BY 4.0)

Within the new research, researchers studied 100,000 contributors from the UK Biobank Nationwide Cohort who wore exercise displays with movement sensors for 1 week. Though the heart beat sensor is used otherwise to how sensors in smartphones are worn, its movement sensors can be utilized each to extract details about gait depth from quick bursts of strolling, a each day life model of a strolling take a look at

The crew was in a position to efficiently validate predictive fashions of mortality danger utilizing simply 6 minutes per day of regular strolling collected by the sensor, mixed with conventional demographic traits. Utilizing the passively collected information, the researchers have been in a position to calculate the equal of strolling velocity. This worth was a predictor of 5-year mortality no matter age and intercourse with one[{” attribute=””>accuracy of about 70% (pooled C-index 0.72). The predictive models 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. “Our scalable methods offer a feasible pathway towards national screening for health risk.”

Schatz adds, “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.”

Reference: “Population analysis of mortality risk: Predictive models from passive monitors using motion sensors for 100,000 UK Biobank participants” by Haowen Zhou, Ruoqing Zhu, Anita Ung and Bruce Schatz, 20 October 2022, PLOS Digital Health.
DOI: 10.1371/journal.pdig.0000045

About the author


Leave a Comment