Put the cookie down—Researchers create app to predict and intervene in users' over

December 12, 2017 by Sharon Gaudin, Worcester Polytechnic Institute
Carolina Ruiz, left, associate professor of computer science at Worcester Polytechnic Institute (WPI), and Bengisu Tulu, associate professor in WPI's Foisie Business School, are the developers (with Sherry Pagoto, professor of allied health sciences at the University of Connecticut) of a smartphone app known as SlipBuddy, which integrates behavioral strategies and technologies like mobile devices, machine learning, and text mining to help users avoid overeating. Credit: Worcester Polytechnic Institute (WPI)

Researchers at Worcester Polytechnic Institute (WPI) and the University of Connecticut (UConn) are collaborating on a smartphone app aimed at helping users manage their overeating challenges in three key ways: by tracking eating patterns, providing interventions, and helping change behavior. The app—and its distinctive methodology—showed tremendous promise in an early pilot study.

A paper on the research was recently presented at the annual symposium for the American Medical Informatics Association, a nonprofit organization that focuses on the development of information technology to benefit healthcare. The WPI/UConn research report noted that a user study of 16 participants, all over the age of 18, overweight, and not necessarily trying to lose weight, showed positive results. At the end of the month-long pilot, nine of the participants lost an average of five pounds, three weighed the same, and four gained an average of two pounds.

The paper's co-authors include the project's principal investigators: Bengisu Tulu, associate professor in WPI's Foisie Business School; Carolina Ruiz, associate professor of computer science at WPI; and Sherry Pagoto, professor of allied health sciences at the University of Connecticut and director of UConn's Center for mHealth and Social Media.

The research team's three-pronged approach is an important differentiator in a crowded marketplace. According to a 2017 report in the International Journal of Obesity, there are nearly 29,000 weight-related apps on the market, with most focused only on tracking physical activity, calories, and body weight. The drawback with most weight-loss apps is that they are burdensome to use and don't focus on actually trying to change the user's behavior.

The WPI/UConn app, dubbed SlipBuddy, is built to do just that. In addition to tracking stress and eating, it's a personalized intervention system built through the integration of behavioral strategies and technologies like mobile devices, machine learning, and text mining. The work is aimed at helping users identify what triggers them to overeat and inserting new stimuli that, instead, trigger healthy behaviors.

The app's name, SlipBuddy, recognizes that it's easy to "slip up" when trying to change unhealthy behaviors. Its reminders help users keep accountable to a "buddy" that suggests better behaviors in a nonjudgmental way.

SlipBuddy is designed to keep user interaction simple. Users are asked to check in three times a day to note their stress levels, fatigue, and hours of sleep, and whenever they feel they've overaten. Over time, as the app collects information (which is stored as anonymized data on a WPI server), the system uses machine learning to find patterns that can be used to predict when the user is likely to overeat. The app uncovers user-specific triggers, like late-night eating, watching TV, or sleepless nights. When the app predicts that the likelihood of overeating is high, it suggests interventions—for example, taking a walk, turning off the TV, or engaging in other activities that can help users reduce stress without resorting to eating.

"Mobile technology, which is ubiquitous today, has the capacity to deliver evidence-based weight loss interventions with lower cost and user burden than traditional intervention models," Ruiz said.

Put the cookie down -- Researchers create app to predict and intervene in users' over
At the whiteboard, Tulu and Ruiz explore enhancements to the SlipBuddy app, which could be ready for release as early as 2019. Credit: Worcester Polytechnic Institute

Obesity affects health and mortality rates worldwide. According to the World Health Organization (WHO), at least 2.8 million people die each year as a result of being overweight or obese. And the problem is getting worse. The number of obese people worldwide has nearly tripled since 1975. Obesity-related health conditions include some of the leading causes of preventable death, such as heart disease, stroke, type 2 diabetes, and certain types of cancer. The global rate of obesity is highest in the Americas, the WHO noted, with 62 percent of the population overweight and 26 percent obese.

"I'm very hopeful that what we're doing will make a big difference," said Tulu. "Most weightloss apps are all about tracking something—tracking your calories, tracking your blood glucose, tracking your steps. This goes beyond that. We're using machine learning to make this about intervention."

The researchers are currently working on enhancing the app's graphical user interface, integrating more intervention tools into the system, and fine-tuning the machine learning algorithms. A larger user study is expected later in 2018.

"It's not an easy thing to build," said Tulu. "Most weight-loss apps are developed by technologists, with not enough input from clinical psychologists or psychiatrists. The task is not trivial. We're working out how to integrate clinical tools into our app. It's an open question we're trying to find answers to."

In addition to work by the three , the app has been the focus of two undergraduate Major Qualifying Projects and two National Science Foundation-funded Research Experience for Undergraduate summer programs.

"This is truly an interdisciplinary project that pushes the boundaries in obesity research," said Ruiz. "The use of machine learning algorithms to uncover accurate predictive patterns of behavior allows our app to deliver user-centric, evidence-based, personalized approaches to prevent overeating, which will have a positive impact on combating obesity."

The app was built for the Android platform, but eventually will be available for iOS devices, as well. While it is still in the research phase, the researchers say the app could be ready for release as early as 2019.

About Worcester Polytechnic Institute

Explore further: Mindfulness training shows promise for maintaining weight loss

Related Stories

Mindfulness training shows promise for maintaining weight loss

November 23, 2017
Can mindfulness training help overweight people shed pounds and keep them off? McGill University researchers surveyed the growing body of studies investigating that question, and came away encouraged.

Researchers link binge eating and weight-loss challenges

December 5, 2017
Someone who binge eats consumes an objectively large amount of food while feeling a loss of control over eating. When episodes occur weekly for several months, the action moves into the realm of binge-eating disorder. So ...

Tracking calories has never been easier

October 27, 2017
(HealthDay)—Gone are the days of hunting through calorie and carbohydrate counting books to find the information you need to plan weight loss menus.

Evaluating mobile weight loss apps on use of evidence-based behavioral strategies

October 8, 2013
In a new study published by the American Journal of Preventive Medicine, UMass Medical School behavioral psychologist and weight loss expert Sherry Pagoto, PhD, and colleagues find that mobile apps to help people lose weight ...

Smartphone app helps fight obesity, study says

May 12, 2013
Using a simple smartphone application to photograph one's meals is a useful slimming aid for the overweight, according to an experiment reported on Sunday.

Eating in social settings may be greatest temptation for dieters

March 7, 2017
For people trying to lose weight or maintain a lower body weight, the temptation to overeat is stronger when eating in a social setting, according to research presented at the American Heart Association's Epidemiology and ...

Recommended for you

Large restaurant portions a global problem, study finds

December 12, 2018
A new multi-country study finds that large, high-calorie portion sizes in fast food and full service restaurants is not a problem unique to the United States. An international team of researchers found that 94 percent of ...

A correlation between obesity and income has only developed in the past 30 years

December 11, 2018
It is well known that poorer Americans are more likely to be obese or suffer from diabetes; there is a strong negative correlation between household income and both obesity and diabetes. This negative correlation, however, ...

BMI is a good measure of health after all, new study finds

December 11, 2018
A new study from the University of Bristol supports body mass index (BMI) as a useful tool for assessing obesity and health.

Simple tips to curb overindulgence can help stop pounds piling on at Christmas

December 10, 2018
A study by the University of Birmingham and Loughborough University has shown that regular weighing at home and simple tips to curb excess eating and drinking can prevent people from piling on the pounds at Christmas.

Obesity intervention needed before pregnancy

December 6, 2018
New research from the University of Adelaide's Robinson Research Institute supports the need for dietary and lifestyle interventions before overweight and obese women become pregnant.

Gene that lets you eat as much as you want holds promise against obesity

December 4, 2018
It sounds too good to be true, but a novel approach that might allow you to eat as much food as you want without gaining weight could be a reality in the near future.

0 comments

Please sign in to add a comment. Registration is free, and takes less than a minute. Read more

Click here to reset your password.
Sign in to get notified via email when new comments are made.