Related Experiment Video
Updated: Jun 25, 2025
Multi-Modal Home Sleep Monitoring in Older Adults
Published on: January 26, 2019
Automated sleep staging on reduced channels in children with epilepsy
Renee Proost1, Elisabeth Heremans2, Lieven Lagae1
1Pediatric Neurology Department, University Hospitals Leuven, KU Leuven, Leuven, Belgium.
Insights
This study validated an automated sleep staging algorithm in children. The algorithm showed high accuracy in children without epilepsy and with well-controlled epilepsy, and acceptable performance in those with drug-resistant epilepsy.
Area of Science:
- Pediatric Neurology
- Sleep Medicine
- Biomedical Engineering
Background:
- Accurate sleep staging is crucial for diagnosing sleep disorders and neurological conditions in children.
- Traditional manual sleep scoring from video-electroencephalogram (EEG) is time-consuming and subjective.
- Automated sleep staging algorithms offer a potential solution for efficient and objective sleep analysis.
Purpose of the Study:
- To validate an automated sleep staging algorithm (SeqSleepNet) using in-hospital video-EEG in pediatric populations.
- To compare the algorithm's performance across children without epilepsy, with well-controlled epilepsy (WCE), and with drug-resistant epilepsy (DRE).
Main Methods:
- Overnight video-EEG, electrooculogram (EOG), and chin electromyogram (EMG) were recorded in 176 children (4-18 years).
- Manual sleep staging served as the ground truth.
- An end-to-end hierarchical recurrent neural network (SeqSleepNet) performed automated sleep staging using C4-A1 EEG, EOG, and EMG channels.
Main Results:
- The automated algorithm achieved 5-class sleep staging accuracies of 84.7% (no epilepsy), 83.5% (WCE), and 80.8% (DRE).
- Kappa values were 0.79, 0.77, and 0.73 for the respective groups.
- F1 scores indicated high performance for Wake (0.91), N2 (0.83), N3 (0.84), and REM (0.86) sleep, with lower accuracy for N1 (0.50).
Conclusions:
- The SeqSleepNet algorithm demonstrates high accuracy for sleep staging in children without epilepsy and with WCE.
- Performance in children with DRE was acceptable but lower, potentially due to factors like N1 sleep prevalence and epileptiform discharges.
- The algorithm reliably detects REM sleep, even in children with DRE where it is significantly affected.
Objectives:
This study aimed to validate a sleep staging algorithm using in-hospital video-electroencephalogram (EEG) in children without epilepsy, with well-controlled epilepsy (WCE), and with drug-resistant epilepsy (DRE).
Methods:
Overnight video-EEG, along with electrooculogram (EOG) and chin electromyogram (EMG), was recorded in children between 4 and 18 years of age. Classical sleep staging was performed manually as a ground truth. An end-to-end hierarchical recurrent neural network for sequence-to-sequence automatic sleep staging (SeqSleepNet) was used to perform automated sleep staging using three channels: C4-A1, EOG, and chin EMG.
Results:
In 176 children sleep stages were manually scored: 47 children without epilepsy, 74 with WCE, and 55 with DRE. The 5-class sleep staging accuracy of the automatic sleep staging algorithm was 84.7% for the children without epilepsy, 83.5% for those with WCE, and 80.8% for those with DRE (Kappa of 0.79, 0.77, and 0.73 respectively). Performance per sleep stage was assessed with an F1 score of 0.91 for wake, 0.50 for N1, 0.83 for N2, 0.84 for N3, and 0.86 for rapid eye movement (REM) sleep.
Conclusion:
We concluded that the tested algorithm has a high accuracy in children without epilepsy and with WCE. Performance in children with DRE was acceptable, but significantly lower, which could be explained by a tendency of more time spent in N1, and by abundant interictal epileptiform discharges and intellectual disability leading to less recognizable sleep stages. REM sleep time, however, significantly affected in children with DRE, can be detected reliably by the algorithm.Clinical trial registration: ClinicalTrials.gov, identifier NCT04584385.
Related Concept Videos
01:22Stages of Sleep
Before sleep begins, in wakefulness, the brain exhibits primarily beta waves, which are high in frequency and low in amplitude, indicating alertness...
01:07Narcolepsy