Related Experiment Video
Updated: May 12, 2026
Assessing the Accuracy of Fitness Smartwatch Data for Cardiovascular and Physical Activity Monitoring: A Validation Study in Digital Health
Published on: February 21, 2025
Machine Learning-Based Stepping Filter Improves Estimates of Moderate-to-Vigorous-Intensity Physical Activity from
Josh Cherian1, Emily C Hector2, Shyh-Huei Chen3
1Department of Biomedical Engineering, Wake Forest University School of Medicine, Winston-Salem, NC, USA.
Introduction:
In this proof-of-concept study involving older adults with varying levels of function, we sought to answer the question: can the application of a simple stepping classification algorithm reduce non-stepping sources of acceleration from wrist-worn ActiGraph data prior to the application of acceleration cut points to quantify time spent in moderate-to-vigorous-intensity physical activity (MVPA)?
Methods:
Participants completed a series of known tasks including stepping tasks, cycling tasks, and home chores repeated across 2 days while wearing an ActivPAL (PAL Technologies LLC, Glasgow, Scotland) activity monitor on the thigh - which provides an accurate measurement of stepping behavior - and an ActiGraph GT3X+ wrist worn device. A stepping classifier was trained for each monitor, and we examined time spent in MVPA prior to and following removal of non-stepping behaviors. Thirty participants (72.51 ± 6.93 years; 50% female) completed the study.
Results:
Across both visits, the ActiGraph reported participants engaged in 48.47 ± 17.15 min of MVPA, and the ActivPAL recorded 14.00 ± 6.44 min, an approximately 3.5-fold difference. After application of the classifier-based filter, the ActiGraph recorded a mean MVPA duration of 20.57 ± 10.27 min of MVPA (a reduction of 60%), and the ActivPAL recorded 11.80 ± 5.27 min of MVPA (a reduction of 14%), a 1.74-fold difference.
Conclusion:
These results suggest that identifying and removing non-stepping behaviors prior to scoring accelerometer data via intensity thresholds may help to reduce inflated MVPA duration attributable to non-stepping wrist movement. Future work should focus on producing strong population-specific step classification algorithms and explore their application to existing and future studies focused on PA behavior.
