Here’s a summary of the provided text, focusing on the key points:
Problem: Current activity trackers and their algorithms are not accurate for people with obesity. Hip-worn trackers misread energy burn due to gait changes and device tilt, while wrist-worn trackers, though promising for comfort and adherence, haven’t been rigorously tested or calibrated for this population. This lack of accurate tracking hinders the ability to tailor interventions and improve health outcomes for individuals with obesity.
Solution: A new algorithm has been developed that is inclusive of body mass index (BMI) and can accurately estimate energy burn in people with obesity.
Key Findings & Features of the New Algorithm:
High Accuracy: the new model rivals gold-standard methods for measuring energy burn and achieves over 95% accuracy in real-world situations.
Minute-by-Minute Estimation: It can estimate how much energy someone with obesity is using every minute.
Motivation: The research was inspired by an observation that a person with obesity who worked exceptionally hard in an exercise class had their efforts underestimated by the leaderboard.
Validation Methods: The study used two groups:
One group wore a fitness tracker and a metabolic cart (a mask measuring oxygen and carbon dioxide to calculate energy burn).
Another group wore a fitness tracker and a body camera to visually confirm the algorithm’s estimations.
Rethinking Success: The study highlights the need to re-evaluate how gyms, trackers, and exercise programs measure success to ensure that the efforts of all individuals, regardless of their body type or exercise modifications, are recognized.
Publication: The findings will be published on June 19 in Nature Scientific Reports*.
Funding: The study received funding from several national institutes, including the National Institute of Diabetes and Digestive and Kidney Diseases, the National Science foundation, the National Institute of Biomedical Imaging and Bioengineering, and the National Institutes of Health’s National Center for Advancing Translational Sciences.