We’ll all die eventually – but what if you knew when you’d be at risk of dying, just based on the way you walk? A new study shows that measurements made with wrist-worn motion sensors can be used to predict a person’s risk of death up to five years afterward. As one of the largest validations of wearable technology to date, the research raises the possibility that a motion detection system in smartphones could one day be used to survey a patient’s health without the need for in-person visits to the doctor’s office.
the study, Published Thursday in the magazine Digital Health PLOS, was run using data from more than 100,000 Britons from the massive British Biobank project, which began collecting health and biometric information from participants in 2006 and will follow them for another 14 years. From a week of wrist sensor data, researchers at the University of Illinois at Urbana-Champaign have built a model that reduces a person’s acceleration and distance traveled into six-minute chunks. According to the study author Bruce Schatza researcher in computer science at the University of Illinois, scientists chose this period to imitate Six-minute walk testA measure of heart and lung function commonly taken during a medical appointment that instructs participants to walk at a normal pace for six minutes and compares the total distance traveled to standards according to their age.
Schatz told The Daily Beast that the test is a “very good external measure of what’s going on internally,” and can be easily replicated with an accelerometer on your wrist sensor or a cheap phone. “I know for a fact that these kinds of models will work with cheap phones.”
The researchers’ model predictions of future death were correct 72 percent of the time after one year, and 73 percent after five years — a similar accuracy rate found in A study published last year which analyzed the same set of data but used hours, not minutes, of data. This new study, Schatz argued, is a more promising demonstration of passive monitoring technology such as phone and wrist sensors because his team’s model requires less data and provides a greater degree of user privacy.
“If you log all the data, it is true that people have distinct paths and you can tell who the individual is. But it is entirely possible to participate in the signal, which is good enough to do the vital things but it completely hides who the person is,” he said.
“I know for a fact that these types of models will work with cheap phones.“
– Bruce Schatz, University of Illinois
However, the use of everyday technology to passively monitor patients can pose problems if users are unable to give ongoing informed consent, situations that can be complicated by degenerative diseases or a lack of technological knowledge. These ethical issues remain speculative, Schatz said, but are worth concerted thought from scientists as the research progresses.
While the sensors used in the study were nearly identical to those found in both cell phones and simple smartphones, future work should validate this model in a large sample when users carry phones in their pockets, rather than wearing sensors on their wrists. Downloading an app that can measure your health as you go about your daily tasks can be a convenient and painless way to keep people healthy for longer.
“If you want to raise the bar for public health for the entire population, this type of project is really important,” Schatz said.
“Social media enthusiast. Beer nerd. Evil communicator. Pop culture lover. Prone to fits of apathy.”