Your smartphone could be used to estimate your risk of dying in the next five years

A study of more than 100,000 adults found that motion sensor data from just 6 minutes of walking is enough to predict five-year mortality risk as accurately as other leading methods


October 20, 2022

Closeup on smartphone in back pocket of woman's jeans, blank screen with clipping path for you to add your own message or design.  On the background of the beach and the sea;  Shutterstock ID 453083140;  An order: -;  Work: -;  Client: -;  Miscellaneous: -

Data your smartphone collects while out walking may be enough to estimate your mortality risk over the next five years


Data from just 6 minutes of walking, collected via motion sensors in smartphones, may be enough to predict a person’s risk of dying over the next five years.

Previous studies have estimated mortality risk using daily physical activity levels measured by wearable motion sensors in devices such as fitness watches. But despite the growing popularity of smartwatches and fitness trackers, they are still mostly worn by a wealthy minority.

Also Read :  You could stay in a 'Ghostbusters'-themed firehouse on Halloween

Most people own smartphones with similar sensors, but calculating mortality risk from the activity data they collect is difficult because people don’t carry their phones with them all day, says Bruce Schatz of the University of Illinois Urbana-Champaign.

To find an alternative predictor measurable with smartphones, Schatz and his colleagues examined data from 100,655 participants in the UK Biobank study, which has been collecting information on the health of middle-aged and older adults living in the UK for more than 15 years Years. As part of this study, participants wore motion sensors on their wrists for a week. About 2 percent of the participants died in the following five years.

Also Read :  Flipkart Big Billion Days Sale 2022 best smartphone offers you can avail right now

Researchers ran motion sensor and death data from about a tenth of the participants through a machine learning model that developed an algorithm that estimated five-year mortality risk based on acceleration during a 6-minute walk.

“In many diseases, especially heart or lung diseases, there is a very characteristic pattern in which people slow down when they are short of breath and speed up again with short doses,” says Schatz.

They then tested the model on data from the other participants and determined that its c-index score — a metric commonly used in biostatistics to assess accuracy — was 0.72, which is comparable to other metrics used to estimate life expectancy. such as B. Daily physical activity or health risk questionnaires.

Also Read :  Blood test uses artificial intelligence and biomarkers to prenatally detect fetal congenital heart defects

“This predictor is as strong or stronger than traditional risk factors,” says Ciprian Crainiceanu of Johns Hopkins University in Maryland.

While this study used wrist-worn motion sensors, smartphones can also measure acceleration during short walks, says Schatz, who is currently planning a larger study using smartphones. “If people are carrying cell phones, you could do a weekly or daily forecast, and that’s something you can’t do with any other method,” he says.

Magazine reference: PLoS Digital Health DOI: 10.1371/journal.pdig.0000045

Sign up for our free health check-Newsletter for a roundup of all the health and fitness news you need to know, every Saturday

More on these topics:


Leave a Reply

Your email address will not be published.