Scientists at Northwestern University have developed a new algorithm designed to improve the accuracy of fitness trackers for individuals with obesity. These devices, which are popular for monitoring physical activity and calorie expenditure, often provide inaccurate readings for this group due to differences in walking gait, speed, and energy burn.
The new algorithm was created by Nabil Alshurafa and his team at the HABits Lab. It is specifically tuned for people with obesity and aims to bridge a critical gap in fitness technology. "People with obesity could gain major health insights from activity trackers, but most current devices miss the mark," said Alshurafa, who is an associate professor of behavioral medicine at Northwestern University Feinberg School of Medicine.
Existing algorithms used by fitness trackers are typically designed for individuals without obesity. As a result, hip-worn trackers may misread energy burn due to changes in gait and device tilt among those with higher body weight. Wrist-worn models offer better comfort and accuracy across different body types but 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 tested their lab's algorithm against 11 state-of-the-art algorithms using research-grade devices.
The motivation behind this research came from Alshurafa's personal 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," he said.
The newly developed model rivals gold-standard methods of measuring energy burn by using data from commercial fitness trackers. It can estimate energy use every minute with over 95% accuracy in real-world situations. This advancement allows more individuals with obesity to track their daily activities effectively.
The study involved two groups of participants: one group wore a fitness tracker and metabolic cart during physical activities to measure energy burn; another group wore a fitness tracker and body camera while living their daily lives to confirm algorithm accuracy visually.
Alshurafa emphasized the need to rethink how gyms, trackers, and exercise programs measure success so that everyone's efforts are recognized: "We celebrate ‘standard’ workouts as the ultimate test, but those standards leave out so many people."
The study will be published on June 19 in Nature Scientific Reports under the title “Developing and comparing a new BMI inclusive energy burn algorithm on wrist-worn wearables.” Other contributors include Boyang Wei, Christopher Romano, Bonnie Nolan, Mahdi Pedram, and Whitney A. Morelli.
Funding was provided by several institutions including 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).