Validating the Longitudinal Assessment of Sedentary Behavior in a Randomized Controlled Trial via a Deep-Learning Algorithm
Journal for the Measurement of Physical Behaviour · 01.01.2026 · 9 (1)
DOI: 10.1123/jmpb.2025-0086 ↗Kurz gefasst
Randomisierte kontrollierte Studie in der Zeitschrift Journal for the Measurement of Physical Behaviour, erschienen am 01.01.2026. Verfasst von Jasmine Morales und 18 weiteren Autor:innen. Beteiligte Einrichtung: Hebert Wertheim School of Public Health, University of California, San Diego, La Jolla, CA, USA. Die Arbeit nennt 41 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar. Gefördert von: NIA NIH HHS, NIDDK NIH HHS, NHLBI NIH HHS.
Abstract (Originalsprache)
Background
Sedentary behavior (SB) is a risk factor for cardiometabolic disease. Existing cut points of hip-worn accelerometers to quantify SB underestimate sedentary bout durations by ignoring posture. To address this, we previously developed Convolutional Neural Network Hip Accelerometer Posture (CHAP), a deep-learning algorithm that predicts sitting and breaks from sitting. In this study, we applied CHAP to a randomized controlled trial to externally validate its accuracy for classifying sitting versus nonsitting and estimating intervention-related changes in SB.
Methods
CHAP was applied to 30-Hz triaxial hip-worn ActiGraph-GT3X+ (AG) accelerometer data from free-living postmenopausal women who are overweight (≥55 years) in the Rise for Health RCT ( n = 406). CHAP-predicted SB accuracy (e.g., sensitivity) and daily pattern metrics (e.g., total sedentary time) were compared with a ground-truth device activPAL (AP) and standard cut-point method (AG100) at two timepoints for intervention arms—Healthy Living (control), Reduce Sitting, and Increase Transitions.
Results
CHAP’s SB accuracy metrics were above 84.8%. Mean (standard error, p values) intervention effect estimates (mean change, intervention minus controls) from generalized estimating equation models for (a) total sedentary time were AP 65.1 min/day (16.2, p < .001), CHAP 38.2 min/day (15.4, p = .013), and AG100 0.28 min/day (13.9, p = .98; Reduce Sitting); (b) breaks from SB were AP 22/day (4.3, p < .001), CHAP 4/day (1.5, p = .003), and AG100
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Hebert Wertheim School of Public Health, University of California, San Diego, La Jolla, CA, USA.
- Moores Cancer Center, University of California, San Diego, La Jolla, CA, USA.
- Department of Computer Science and Engineering, University of California San Diego, La Jolla, CA, USA.
- Halicioglu Data Science Institute, University of California San Diego, La Jolla, CA, USA.
- Center for Children's Healthy Lifestyles & Nutrition, Children's Mercy Hospital, Kansas City, MO, USA.
- Kaiser Permanente Washington Health Research Institute, Seattle, WA, USA.
Förderung
- NIA NIH HHS
- NIDDK NIH HHS
- NHLBI NIH HHS
Zitieren
APA
Morales, J., Zablocki, R. W., Hartman, S. J., Kumar, A., Kumar, A., Carlson, J. A., Greenwood-Hickman, M. A., Hibbing, P. R., Staudenmayer, J., Di, C., Zou, J., Nguyen, S., LaCroix, A. Z., Dillon, L., Ryu, H., Shao, L., Shi, W., Tuz-Zahra, F., & Natarajan, L. (2026). Validating the Longitudinal Assessment of Sedentary Behavior in a Randomized Controlled Trial via a Deep-Learning Algorithm. Journal for the Measurement of Physical Behaviour, 9(1). https://doi.org/10.1123/jmpb.2025-0086
Vancouver
Morales J, Zablocki RW, Hartman SJ, Kumar A, Kumar A, Carlson JA, et al. Validating the Longitudinal Assessment of Sedentary Behavior in a Randomized Controlled Trial via a Deep-Learning Algorithm. Journal for the Measurement of Physical Behaviour. 2026;9(1). doi:10.1123/jmpb.2025-0086
BibTeX
@article{Morales2026,
author = {Morales, Jasmine and Zablocki, Rong W and Hartman, Sheri J and Kumar, Arun and Kumar, Animesh and Carlson, Jordan A and Greenwood-Hickman, Mikael Anne and Hibbing, Paul R and Staudenmayer, John and Di, Chongzhi and Zou, Jingjing and Nguyen, Steve and LaCroix, Andrea Z and Dillon, Lindsay and Ryu, Howon and Shao, Lucy and Shi, Weiwei and Tuz-Zahra, Fatima and Natarajan, Loki},
title = {Validating the Longitudinal Assessment of Sedentary Behavior in a Randomized Controlled Trial via a Deep-Learning Algorithm},
journal = {Journal for the Measurement of Physical Behaviour},
year = {2026},
volume = {9},
number = {1},
doi = {10.1123/jmpb.2025-0086}
}
EUVIMED