Fitness trackers have become a common tool for monitoring daily activity and calorie expenditure. Though, these devices frequently enough provide inaccurate readings for individuals with obesity, who may exhibit differences in gait, speed, and energy expenditure. Now, a team at Northwestern University has developed a new algorithm to address this issue.

The new algorithm significantly improves the accuracy of smartwatches in monitoring calorie burn for people with obesity during various physical activities. According to Nabil Alshurafa, associate professor of behavioral medicine at Northwestern University Feinberg School of medicine, this technology fills a crucial void in fitness technology.His lab, HABits Lab, created and tested the open-source algorithm, specifically designed for dominant-wrist wearables used by people with obesity. The algorithm is clear, rigorously testable, and designed to be built upon by other researchers. An activity-monitoring app for iOS and Android is planned for release later this year.

“People with obesity could gain major health insights from activity trackers, but most current devices miss the mark,” said Alshurafa.

Existing activity-monitoring algorithms are typically designed for individuals without obesity. Alshurafa noted that hip-worn trackers often misinterpret energy expenditure due to gait variations and device tilt in people with higher body weight. While wrist-worn models offer better comfort and potential accuracy across different body types, they have not been rigorously tested or calibrated for people with obesity.

“Without a validated algorithm for wrist devices, we’re still in the dark about exactly how much activity and energy people with obesity really get each day — slowing our ability to tailor interventions and improve health outcomes,” said Alshurafa.His team compared their algorithm against 11 state-of-the-art algorithms using research-grade devices and wearable cameras to identify instances where wrist sensors inaccurately measured calorie burn.

The findings were published on June 19 in Nature Scientific Reports.

Inspiration from an Exercise Class

Alshurafa’s motivation for creating the algorithm stemmed from an experience attending an exercise class with his mother-in-law, who has obesity.

“She worked harder than anyone else, yet when we glanced at the leaderboard, her numbers barely registered,” Alshurafa said. “That moment hit me: fitness shouldn’t feel like a trap for the people who need it most.”

“That moment hit me: fitness shouldn’t feel like a trap for the people who need it most.”

Algorithm Achieves High Accuracy

The new model, which utilizes data from commercial fitness trackers, rivals gold-standard methods for measuring energy expenditure. It can estimate energy use in people with obesity every minute with over 95% accuracy in real-world scenarios, according to Alshurafa.This advancement promises to make it easier for individuals with obesity to monitor their daily activities and energy expenditure.

The study involved two groups of participants. in one group of 27, participants wore a fitness tracker and a metabolic cart, which measures oxygen intake and carbon dioxide exhalation to calculate energy expenditure and resting metabolic rate. Participants engaged in various physical activities to measure energy burn.Researchers then compared the fitness tracker results with those from the metabolic cart.

In the second group of 25 participants, individuals wore a fitness tracker and a body camera while going about their daily lives. The body camera allowed researchers to visually confirm instances where the algorithm overestimated or underestimated calorie expenditure.

Alshurafa recounted challenging participants to perform as many pushups as possible in five minutes.”Many couldn’t drop to the floor, but each one crushed wall-pushups, their arms shaking with effort,” he said. “we celebrate ‘standard’ workouts as the ultimate test, but those standards leave out so many people. These experiences showed me we must rethink how gyms, trackers and exercise programs measure success — so no one’s hard work goes unseen.”

The study is titled, “Developing and comparing a new BMI inclusive energy burn algorithm on wrist-worn wearables.”

Other Northwestern authors include lead author Boyang Wei, and Christopher Romano and Bonnie Nolan.This work also was done in collaboration with Mahdi Pedram and Whitney A. Morelli, formerly of Northwestern.

Funding for the study was provided by the National Institute of Diabetes and Digestive and Kidney diseases (grants K25DK113242-01A1 and R01DK129843-01), the National Science Foundation (grant 1915847), the National Institute of Biomedical Imaging and Bioengineering (grant R21EB030305-01) and the National Institutes of Health’s National center for Advancing Translational Sciences (grant UL1TR001422).