Related Experiment Video
Updated: Dec 18, 2025
Measuring Neural Mechanisms Underlying Sleep-Dependent Memory Consolidation During Naps in Early Childhood
Published on: October 2, 2019
The relationship between machine-learning-derived sleep parameters and behavior problems in 3- and 5-year-old
Nevin Hammam1, Dorna Sadeghi1, Valerie Carson2
1Department of Pediatrics, University of Alberta, Edmonton, AB, Canada.
Insights
Machine learning identified distinct sleep patterns in preschoolers. Children with sleep-disordered breathing (SDB) and more non-moving sleep showed fewer behavior problems.
Area of Science:
- Pediatric Sleep Medicine
- Machine Learning in Health
- Child Psychology
Background:
- Accelerometer-based sleep duration assessment is common but lacks detailed sleep stage information.
- Machine learning (ML) offers potential for identifying distinct sleep patterns from accelerometer data.
- Understanding sleep patterns is crucial for child development and behavior.
Purpose of the Study:
- To investigate associations between ML-identified sleep patterns and behavior problems in preschool children.
- To explore if these associations differ in children with and without sleep-disordered breathing (SDB).
Main Methods:
- Utilized data from the CHILD Cohort (n=330 at 3 years, n=304 at 5 years).
- Applied Hidden Markov Model (HMM) for ML analysis of accelerometer sleep data.
- Assessed parent-reported behavior problems using the Child Behavior Checklist.
Main Results:
- Identified 4 hidden sleep states at 3 years and 6 at 5 years using HMM.
- Children with SDB showed reduced externalizing and internalizing behavior problems with increased time in the non-moving sleep state (HMM-0).
- No significant associations were found between ML-sleep states and behavior problems in the general preschool population.
Conclusions:
- ML-derived sleep states were not linked to behavior problems in the general preschool population.
- Greater duration of non-moving sleep in children with SDB correlated with fewer behavioral issues.
- Further validation of ML-sleep states using polysomnography is recommended.
Study Objectives:
Machine learning (ML) may provide insights into the underlying sleep stages of accelerometer-assessed sleep duration. We examined associations between ML-sleep patterns and behavior problems among preschool children.
Methods:
Children from the CHILD Cohort Edmonton site with actigraphy and behavior data at 3-years (n = 330) and 5-years (n = 304) were included. Parent-reported behavior problems were assessed by the Child Behavior Checklist. The Hidden Markov Model (HMM) classification method was used for ML analysis of the accelerometer sleep period. The average time each participant spent in each HMM-derived sleep state was expressed in hours per day. We analyzed associations between sleep and behavior problems stratified by children with and without sleep-disordered breathing (SDB).
Results:
Four hidden sleep states were identified at 3 years and six hidden sleep states at 5 years using HMM. The first sleep state identified for both ages (HMM-0) had zero counts (no movement). The remaining hidden states were merged together (HMM-mov). Children spent an average of 8.2 ± 1.2 h/day in HMM-0 and 2.6 ± 0.8 h/day in HMM-mov at 3 years. At age 5, children spent an average of 8.2 ± 0.9 h/day in HMM-0 and 1.9 ± 0.7 h/day in HMM-mov. Among SDB children, each hour in HMM-0 was associated with 0.79-point reduced externalizing behavior problems (95% CI -1.4, -0.12; p < 0.05), and a 1.27-point lower internalizing behavior problems (95% CI -2.02, -0.53; p < 0.01).
Conclusions:
ML-sleep states were not associated with behavior problems in the general population of children. Children with SDB who had greater sleep duration without movement had lower behavioral problems. The ML-sleep states require validation with polysomnography.
Related Concept Videos
01:15REM Sleep Behavior Disorder
RBD is significantly associated with...
01:24Substance Use Disorders Affecting Sleep
Understanding the concepts of physical dependence,...