Tracking America's physical activity, via smartphone

“We know that most Amer­i­cans are too seden­tary,” said North­eastern asso­ciate pro­fessor Stephen Intille, a founding fac­ulty member of the university’s new Per­sonal Health Infor­matics grad­uate pro­gram with dual appoint­ments in the Col­lege of Com­puter and Infor­ma­tion Sci­ence and Bouvé Col­lege of Health Sci­ences. “What we need is high quality infor­ma­tion about what drives deci­sions about phys­ical activity so we can design the next gen­er­a­tion of health interventions.”

Toward that end, Intille has teamed up with Genevieve Dunton, an assis­tant pro­fessor of pre­ven­tive med­i­cine at the Uni­ver­sity of Southern Cal­i­fornia, to gather infor­ma­tion about where, when, why and how teenagers get their phys­ical activity.

Tra­di­tional studies ask par­tic­i­pants to place an activity mon­itor on their hip, which uses an accelerom­eter to mea­sure motion. “What you get are data recording roughly how active a person is throughout the day, but you don’t get any infor­ma­tion other than this motion pat­tern,” Intille explained. But in order to develop informed inter­ven­tions, public health pro­fes­sionals also need to know things like where people are when they’re exer­cising or seden­tary, if they’re with other people and what they’re doing.

That’s why Intille and Dunton, with the sup­port of a two-​​year, $450,000 grant from the National Insti­tutes of Health, will develop and eval­uate a mobile phone app that sup­ple­ments the activity-​​monitor data. Using the loca­tion and motion tech­nolo­gies already embedded in mobile devices, Intille’s app will deter­mine appro­priate times throughout the day to ask study par­tic­i­pants about the con­texts that are influ­encing their activity.

“The fun­da­mental idea is there is a rela­tion­ship between the motion of your phone and the activity that you do and the use of the activity mon­itor.” The phone will rec­og­nize periods of increased or reduced phys­ical activity (for example, if you take it off while playing a high-​​impact sport or take a nap) and present ques­tions about what a par­tic­i­pant is doing during the “inter­esting” periods.

“It’s about cre­ating and eval­u­ating a tool that would help us aug­ment the type of infor­ma­tion that we get from stan­dard research tools so that researchers get that addi­tional con­tex­tual info about where and why teens are doing the activity,” said Intille. Dunton explained that the higher quality data will allow researchers to better under­stand the rela­tion­ship between phys­ical activity, seden­tary behav­iors, and the risk of meta­bolic, car­dio­vas­cular and other chronic diseases.

Intille’s lab at North­eastern focuses on sensor-​​driven mobile health tech­nology. Other studies to come out of it have used a sim­ilar approach, but this is the first time the app will be pro­grammed to rec­og­nize major activity changes.

“Pre­vious studies would ask ques­tions ran­domly throughout the day, but that’s not a very effi­cient way to do it,” Intille said. This is the first time the app will be pro­gramed to aug­ment an existing research tool by rec­og­nizing major activity changes and using a game-​​like inter­face that makes it easy for teens to fill in gaps by answering carefully-​​timed questions.

He hopes that the app will pro­vide a valu­able, low-​​cost tool for future studies that also inves­ti­gate phys­ical activity patterns.

“In the long term, we could poten­tially use this same type of tech­nology as an inter­ven­tion,” said Intille, who explained, for example, that users would receive pos­i­tive feed­back mes­sages through the phone when the app detects that they are being phys­i­cally active.