Millions Rely On Fitness Trackers. A New Study Shows They’re Failing A Key Group

Northwestern researchers developed an open-source algorithm to make fitness tracking more accurate for people with obesity

For millions of Americans living with obesity, fitness trackers often fail at the very thing they promise: accurately measuring effort. Why? Most are powered by algorithms built for people without obesity. Now, scientists at Northwestern University say they’ve addressed that flaw with a new open-source algorithm designed specifically for people with obesity.

It’s an important finding, considering that almost one in three Americans use a wearable device to track their health and fitness, according to a 2023 Health Information National Trends Survey.

The issue, researchers say, lies in the algorithms powering most popular fitness trackers. Built around data from average-weight users, they often fail to account for differences in gait, speed and energy expenditure in people with obesity. Researchers found that hip-worn trackers often miscalculate energy burn due to gait differences and device tilt in people with obesity. Similarly, wrist-worn devices are typically more comfortable and easier to wear consistently, but until now, they haven’t been rigorously validated for individuals with higher BMIs.

“People with obesity could gain major health insights from activity trackers, but most current devices miss the mark,” said Nabil Alshurafa, an associate professor of behavioral medicine at Northwestern University Feinberg School of Medicine.“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 at Northwestern’s HABits Lab developed and tested the new algorithm, benchmarking it against 11 other models using research-grade devices. They also used wearable cameras to capture every moment when wrist sensors failed to reflect calorie burn accurately.

The study was published June 19 in Nature Scientific Reports. The next step is a planned activity-tracking app, set to launch later this year for both iOS and Android.

The study was personal for Alshurafa, who had attended 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.”

For the study, the team recruited two groups of participants. In the first, 27 individuals wore a fitness tracker along with a metabolic cart – a device that calculates energy burn by measuring oxygen intake and carbon dioxide output. Participants completed a series of physical activities, allowing researchers to compare calorie burn estimates from the smartwatch against the metabolic cart readings.

In the second group, 25 participants wore a fitness tracker and a body camera while going about their daily routines. The camera footage allowed researchers to visually confirm when the algorithm over- or underestimated calorie burn.

The study also challenged assumptions about what effort looks like. At times, Alshurafa asked participants to do as many pushups as they could 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 post Millions Rely on Fitness Trackers. A New Study Shows They’re Failing a Key Group appeared first on Athletech News.