Scientists have designed a smartphone app that may help in the fight against obesity. While apps that aim to assist with weight loss are not new, this app — known as SlipBuddy — takes a unique three-pronged approach to combat overeating.
Progress has been made to address the obesity epidemic. After decades of increases in obesity, rates have started to level off among children and adolescents and slowed down over time among adults. Obesity remains a threat to health, and while rates vary between states, overall, they remain high nationwide.
Making lifestyle changes, such as altering nutrition, increasing physical activity, and participating in talking therapies, have been shown to be effective in helping with weight loss, and, as a result, preventing chronic diseases.
However, these interventions can prove expensive and require several visits over the course of many months with trained professionals.
The rise of smartphones over the past decade has provided a new way to deliver low-cost obesity interventions.
The current weight loss app market has been shown to include
Other research has demonstrated that behavioral strategies often found in evidence-based weight loss interventions are only observed in a minority of weight loss apps.
“Mobile technology, which is ubiquitous today,” notes Carolina Ruiz, an associate professor of computer science at Worcester Polytechnic Institute (WPI) in Massachusetts, “has the capacity to deliver evidence-based weight loss interventions with lower cost and user burden than traditional intervention models.”
Although mobile apps hold a strong position in the obesity battle, many of them require users to list every food they have eaten in a day and log all physical activity, which is a labor-intensive task that often causes users to give up tracking their data altogether.
Moving beyond the realms of tracking to include more personalized interventions, evidence-based theories, and advanced technologies could improve the impact of mobile apps on the obesity epidemic.
Ruiz conducted the new research — to try to tackle some of the drawbacks of weight loss apps — together with Bengisu Tulu, an associate professor in WPI’s Foisie Business School, and Sherry Pagoto, a professor of allied health sciences at the University of Connecticut in Mansfield.
Their new findings were presented at the Annual Symposium for the American Medical Informatics Association, held in Washington, D.C.
The paper reported on a study of 16 participants over the age of 18 years who were overweight and had been recruited to test the app. At the end of the 1-month study, nine of the subjects had lost an average of 5 pounds, three had maintained the same weight, and four had gained 2 pounds, on average.
SlipBuddy offers a unique three-pronged approach to overeating, and, ultimately, aims to alter the user’s behavior — instead of just tracking metrics. The app integrates behavioral strategies and technologies such as machine learning, text mining, and mobile devices.
“I’m very hopeful that what we’re doing will make a big difference,” notes Tulu. “Most weight loss apps,” she adds, “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.”
First, rather than the user recording everything they eat — which is often underreported — they are only required to log times when they think they overindulged.
Next, the app collects information to identify triggers for the unhealthful behavior, such as watching TV, socializing, or commuting, and uses machine learning to forecast when the user has a higher chance of overeating.
Finally, at times when the likelihood of overeating is high, SlipBuddy will suggest some healthful activities that prevent overindulging. For example, going out for a walk could help to sever the connection between watching TV and eating.
Technologists design many weight loss apps without enough input from clinical psychiatrists and psychologists, explains Tulu. However, the work carried out by this team differs by aiming to incorporate clinical tools.
“This is truly an interdisciplinary project that pushes the boundaries in obesity research.”
“The use of machine learning algorithms to uncover accurate predictive patterns of behavior,” adds Ruiz, “allows our app to deliver user-centric, evidence-based, personalized approaches to prevent overeating, which will have a positive impact on combating obesity.
Ruiz and colleagues are expected to conduct a more extensive study in 2018 and report that the app could be available for release for Android and iOS in 2019.