Related Experiment Video
Updated: Nov 19, 2025
06:51
Physical Activity Measurement in Children Accepting Table Tennis Training
Published on: July 27, 2022
2.2K
Identifying bedrest using waist-worn triaxial accelerometers in preschool children
J Dustin Tracy1, Thomas Donnelly2, Evan C Sommer3
1Economic Science Institute, Chapman University, Orange, California, United States of America.
Plos One
|January 28, 2021
Summary
This study adapted a decision tree (DT) algorithm for accurately identifying bedrest in preschool children using accelerometers. The optimized DT algorithm demonstrated high accuracy, outperforming other methods for sleep detection in young children.
Area of Science:
- Pediatric sleep research
- Biomedical engineering
- Actigraphy data analysis
Background:
- Accurate measurement of sleep and bedrest in preschool children is crucial for understanding their health and development.
- Existing methods for analyzing accelerometer data, such as the decision tree (DT) algorithm, were primarily developed for older age groups.
- Adapting and validating these tools for younger populations is essential for reliable sleep research in early childhood.
Purpose of the Study:
- To adapt and validate a previously developed decision tree (DT) algorithm for identifying bedrest in preschool children (ages 3-6).
- To optimize key parameters of the DT algorithm for accurate minute-by-minute classification of bedrest versus wake periods.
- To compare the performance of the adapted DT algorithm against visual identification, a common sleep detection algorithm (Sadeh's), and a youth-specific DT algorithm.
Main Methods:
- Parents of 610 healthy preschool children recorded accelerometer data for 7-10 days, 24 hours/day.
- Data from 400 children (200 development, 200 validation groups) with valid recordings were used.
- The DT parameters (block length, thresholds) were optimized using a Nelder-Mead simplex method in the development group.
- Performance was evaluated against visual identification and compared with Sadeh's algorithm and a youth DT in the validation group.
Main Results:
- The optimized DT algorithm achieved high accuracy (0.956) in identifying bedrest compared to visual identification in preschool children.
- The DT algorithm significantly outperformed Sadeh's algorithm (0.902) and the youth DT (0.861) (P<0.001).
- Both accelerometer-based methods identified less bedrest/sleep duration than parental surveys, highlighting potential discrepancies in subjective vs. objective measures.
Conclusions:
- The adapted DT-based algorithm provides a highly accurate method for identifying bedrest in preschool children using accelerometer data.
- The optimized DT algorithm offers a reliable and validated tool for sleep research in young children.
- The 'PhysActBedRest' R package is available for researchers to implement this validated algorithm.
