Skip to Content

A Health-Tracking App You Might Actually Stick With

Researchers built a mobile health app that tracks your activity and eating habits so it can nudge you with goals that fit your routine.
July 28, 2015

A group of researchers has created an app that may make it easier to actually make health and fitness changes and stick with them. It logs where and when its users are active and stationary, as well as what they’re eating. Called MyBehavior, the app also offers users a list of activity- and food-oriented suggestions each day, along with details about the calories they’d save or burn with them.

Plenty of smartphone apps already track physical activity and calories—many of them, like ones from Fitbit and Jawbone, by working with a wristband or smartwatch—but it can be a struggle to make radical changes to your routine. Tanzeem Choudhury, an associate professor of information science at Cornell and one of the researchers behind MyBehavior, says the app tries to come up with achievable goals that blend in with a person’s habits rather than bombarding him with information. It can also adapt as the person’s routine changes over time, she says.

Choudhury and colleagues at Cornell University and Michigan State University have been working on MyBehavior for more than two years, and recently conducted a 14-week study with 16 people using the app on Android smartphones. On average, Choudhury says, the researchers found that people using the app burned 45 more calories per day and ate 150 fewer calories per day, or about 1,365 calories per week.

Choudhury says the group hopes to roll out MyBehavior publicly in September, around the time that the researchers present a paper on their study at the ubiquitous-computing conference UbiComp in Japan. 

The app automatically tracks running, walking, and sitting with the phone’s accelerometer and GPS, using that data with its algorithms to generate suggestions that you’re likely to try. For instance, if you walk to work several times a week and go to the gym just once a week, the app would mostly keep trying to get you to take those walks, telling you how many calories you’d burn by doing so and noting how often you’ve done so over the past week, though it would also sometimes bug you to go to the gym more. If you’re sitting at the office for six hours each day, it might suggest you take a few minutes to walk around each hour, too, and let you know how many calories you’ll burn from doing that.

To log food, users can take a picture of what they’re eating and upload it to MyBehavior’s server so a group of Amazon Mechanical Turk workers can label it (they work from a list of most frequently selected foods by users of the MyFitnessPal mobile app) and determine, on average, how many calories it has, along with its similarity to other recent foods you’ve eaten. The app can use that data to give suggestions for other foods you may want to eat—if you eat a lot of McDonald’s burgers, for instance, it might suggest you avoid them and tell you that something else you like to eat (a chicken dish, perhaps) is a better option.

MyBehavior considers your activity and meals over the last week. Choudhury thinks that’s enough history to get to know a person’s routine, while also being able to adapt to changes you might make and giving you new food and activity suggestions as a result.

“That adaptive nature helps you climb the ladder at your own pace,” Choudhury says.

Keep Reading

Most Popular

Large language models can do jaw-dropping things. But nobody knows exactly why.

And that's a problem. Figuring it out is one of the biggest scientific puzzles of our time and a crucial step towards controlling more powerful future models.

The problem with plug-in hybrids? Their drivers.

Plug-in hybrids are often sold as a transition to EVs, but new data from Europe shows we’re still underestimating the emissions they produce.

Google DeepMind’s new generative model makes Super Mario–like games from scratch

Genie learns how to control games by watching hours and hours of video. It could help train next-gen robots too.

How scientists traced a mysterious covid case back to six toilets

When wastewater surveillance turns into a hunt for a single infected individual, the ethics get tricky.

Stay connected

Illustration by Rose Wong

Get the latest updates from
MIT Technology Review

Discover special offers, top stories, upcoming events, and more.

Thank you for submitting your email!

Explore more newsletters

It looks like something went wrong.

We’re having trouble saving your preferences. Try refreshing this page and updating them one more time. If you continue to get this message, reach out to us at customer-service@technologyreview.com with a list of newsletters you’d like to receive.