Scientists at Northwestern University have developed a new algorithm designed to improve the accuracy of fitness trackers for individuals with obesity. The technology aims to address the inaccuracies in measuring calories burned, which are often observed in current devices due to differences in walking gait, speed, and energy expenditure among people with obesity.
Nabil Alshurafa, an associate professor of behavioral medicine at Northwestern University Feinberg School of Medicine, highlighted the significance of this development. "People with obesity could gain major health insights from activity trackers, but most current devices miss the mark," he stated. Alshurafa's lab, HABits Lab, has created an open-source algorithm specifically tuned for this demographic.
The team plans to release an activity-monitoring app later this year compatible with both iOS and Android platforms. Current algorithms used by fitness trackers were primarily designed for individuals without obesity. As a result, hip-worn trackers often misinterpret energy burn due to changes in gait and device tilt associated with higher body weight. Wrist-worn models offer better comfort and adherence but lack rigorous testing or calibration for people with obesity.
Alshurafa emphasized the need for validated algorithms: "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." His team tested their algorithm against 11 state-of-the-art algorithms using research-grade devices.
The study will be published on June 19 in Nature Scientific Reports. The motivation behind this research stemmed from Alshurafa's personal experience during 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 recalled.
The new model utilizes data from commercial fitness trackers and rivals gold-standard methods of measuring energy burn. It can estimate energy usage per minute with over 95% accuracy in real-world situations. This advancement is expected to aid more individuals with obesity in tracking their daily activities and energy use.
The study involved two groups of participants wearing fitness trackers alongside other equipment like metabolic carts or body cameras to measure energy burn accurately. These methods allowed researchers to validate the new algorithm's effectiveness compared to existing standards.
Alshurafa noted that standard workouts might not suit everyone: "We celebrate ‘standard’ workouts as the ultimate test, but those standards leave out so many people."
Other contributors from Northwestern include lead author Boyang Wei, Christopher Romano, Bonnie Nolan, Mahdi Pedram, and Whitney A. Morelli. The study received funding from several institutions including the National Institute of Diabetes and Digestive and Kidney Diseases and the National Science Foundation.