Related Experiment Video
Updated: Nov 19, 2025
Physical Activity Measurement in Children Accepting Table Tennis Training
Published on: July 27, 2022
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.
Insights
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.
Purpose:
To adapt and validate a previously developed decision tree for youth to identify bedrest for use in preschool children.
Methods:
Parents of healthy preschool (3-6-year-old) children (n = 610; 294 males) were asked to help them to wear an accelerometer for 7 to 10 days and 24 hours/day on their waist. Children with ≥3 nights of valid recordings were randomly allocated to the development (n = 200) and validation (n = 200) groups. Wear periods from accelerometer recordings were identified minute-by-minute as bedrest or wake using visual identification by two independent raters. To automate visual identification, chosen decision tree (DT) parameters (block length, threshold, bedrest-start trigger, and bedrest-end trigger) were optimized in the development group using a Nelder-Mead simplex optimization method, which maximized the accuracy of DT-identified bedrest in 1-min epochs against synchronized visually identified bedrest (n = 4,730,734). DT's performance with optimized parameters was compared with the visual identification, commonly used Sadeh's sleep detection algorithm, DT for youth (10-18-years-old), and parental survey of sleep duration in the validation group.
Results:
On average, children wore an accelerometer for 8.3 days and 20.8 hours/day. Comparing the DT-identified bedrest with visual identification in the validation group yielded sensitivity = 0.941, specificity = 0.974, and accuracy = 0.956. The optimal block length was 36 min, the threshold 230 counts/min, the bedrest-start trigger 305 counts/min, and the bedrest-end trigger 1,129 counts/min. In the validation group, DT identified bedrest with greater accuracy than Sadeh's algorithm (0.956 and 0.902) and DT for youth (0.956 and 0.861) (both P<0.001). Both DT (564±77 min/day) and Sadeh's algorithm (604±80 min/day) identified significantly less bedrest/sleep than parental survey (650±81 min/day) (both P<0.001).
Conclusions:
The DT-based algorithm initially developed for youth was adapted for preschool children to identify time spent in bedrest with high accuracy. The DT is available as a package for the R open-source software environment ("PhysActBedRest").
