Researchers believe that by analyzing how people walk, smartphones may be able to predict how soon they will die.
Over 100,000 participants wore activity monitors for one week in a new study, but researchers only needed six minutes of walking data per day to predict someone’s risk of dying within the next five years.
When combined with the wearer’s demographic information, the phone’s gait speed could be gathered and used in an algorithm to predict mortality rates; approximately 2% of the middle-aged and senior adults in the study died in the following years.
“Our findings show that passive motion sensors can achieve similar accuracy to active measures of gait speed and walk rate,” the authors write. “Our scalable methods provide a feasible path toward national health risk screening.”
While the study participants wore motion sensors on their wrists, the researchers claim that the same data could be collected using inexpensive phones because their accelerometers are good enough to collect the data and “even the cheapest flip phones incorporating motion sensors.”
The researchers also suggest that this could be useful in poorer countries, as roughly 48% of people in Sub-Saharan Africa own smartphones. In the United Kingdom, 92% of people own a smartphone.
In general, there are two methods for measuring physical activity: self-reporting via a questionnaire or walking a predetermined distance, and passive data collection via sensors. The former are “problematic to scale for population level assessment, due to the logistic difficulty of getting large numbers of people to perform the required tasks on a routine basis,” according to the researchers.
Sensor-based research, on the other hand, has a significant advantage in that it does not require people to change their daily activities.
The study was published in the journal PLOS Digital Health.