EUVIMEDEUVIMED entdecken
Open Access

Supervised machine learning on electrocardiography features to classify sleep in noncritically ill children

Eris van Twist, Anne M Meester, Arnout B G Cramer, Matthijs de Hoog, Alfred C Schouten, Sascha C A T Verbruggen, Koen F M Joosten, Maartje Louter, Dirk C G Straver, David M J Tax, Rogier C J de Jonge, Jan Willem Kuiper

Journal of Clinical Sleep Medicine · 2025

DOI: 10.5664/jcsm.11358 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Clinical Sleep Medicine, 2025. Verfasst von Eris van Twist und 11 weiteren Autor:innen. Beteiligte Einrichtung: Department of Neonatal and Pediatric Intensive Care, Division of Pediatric Intensive Care, Erasmus MC Sophia Children's Hospital, Rotterdam, The Neth…. Hauptthemen laut MEDLINE: Electrocardiography, Supervised Machine Learning, Polysomnography, Sleep. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 50 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

STUDY OBJECTIVES: Despite frequent sleep disruption in the pediatric intensive care unit, bedside sleep monitoring in real time is currently not available. Supervised machine learning applied to electrocardiography data may provide a solution, because cardiovascular dynamics are directly modulated by the autonomic nervous system during sleep. METHODS: This retrospective study used hospital-based polysomnography recordings obtained in noncritically ill children between 2017 and 2021. Six age categories were defined: 6-12 months, 1-3 years, 3-5 years, 5-9 years, 9-13 years, and 13-18 years. Features were derived in time, frequency, and nonlinear domain from preprocessed electrocardiography data. Sleep classification models were developed for 2, 3, 4, and 5 states using logistic regression, random forest, and XGBoost classifiers during 5-fold nested cross-validation. Models were additionally validated across age categories. RESULTS: A total of 90 noncritically ill children were included with a median (Q1, Q3) recording length of 549.0 (494.8, 601.3) minutes. The 3 models obtained an area under the receiver operator characteristic curve of 0.72-0.78 with minimal variation across classifiers and age categories. Balanced accuracies were 0.70-0.72, 0.59-0.61, 0.50-0.51, and 0.41-0.42 for 2, 3, 4, and 5 states, respectively. Generally, the XGBoost model obtained the highest balanced accuracy (P < .05), except for 5 states for which logistic regression excelled (P = .67). CONCLUSIONS: Electrocardiography-based machine learning models are a promising and noninvasive method for automated sleep classification directly at the bedside of noncritically ill children aged 6 months-18 years. Models obtained moderate-to-good performance for 2- and 3-state classification. CITATION: van Twist E, Meester AM, Cramer ABG, et al. Supervised machine learning on electrocardiography features to classify sleep in noncritically ill children. J Clin Sleep Med. 2025;21(2):261-268.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

ElectrocardiographySupervised Machine LearningPolysomnographySleepMachine LearningHumansChildRetrospective StudiesAdolescentMaleFemaleChild, PreschoolInfant

Stichwörter der Autor:innen

algorithmautonomic nervous systemcardiovascular dynamicscircadian rhythmelectrocardiographymachine learningpediatric intensive care unitpolysomnographysleep classificationsleep stage

Autor:innen und Institutionen

  • Department of Neonatal and Pediatric Intensive Care, Division of Pediatric Intensive Care, Erasmus MC Sophia Children's Hospital, Rotterdam, The Netherlands.
  • Department of Clinical Technology, Faculty of Mechanical Engineering, Delft University of Technology, Delft, The Netherlands.
  • Department of Biomechanical Engineering, Faculty of Mechanical Engineering, Delft University of Technology, Delft, The Netherlands.
  • Department of Neurology and Clinical Neurophysiology, Erasmus MC, Rotterdam, The Netherlands.
  • Pattern Recognition Laboratory, Delft University of Technology, Delft, The Netherlands.

Zitieren

APA

van Twist, E., Meester, A. M., Cramer, A. B. G., de Hoog, M., Schouten, A. C., Verbruggen, S. C. A. T., Joosten, K. F. M., Louter, M., Straver, D. C. G., Tax, D. M. J., de Jonge, R. C. J., & Kuiper, J. W. (2025). Supervised machine learning on electrocardiography features to classify sleep in noncritically ill children. Journal of Clinical Sleep Medicine. https://doi.org/10.5664/jcsm.11358

Vancouver

van Twist E, Meester AM, Cramer ABG, de Hoog M, Schouten AC, Verbruggen SCAT, et al. Supervised machine learning on electrocardiography features to classify sleep in noncritically ill children. Journal of Clinical Sleep Medicine. 2025. doi:10.5664/jcsm.11358

BibTeX
@article{vanTwist2025,
  author = {van Twist, Eris and Meester, Anne M and Cramer, Arnout B G and de Hoog, Matthijs and Schouten, Alfred C and Verbruggen, Sascha C A T and Joosten, Koen F M and Louter, Maartje and Straver, Dirk C G and Tax, David M J and de Jonge, Rogier C J and Kuiper, Jan Willem},
  title = {Supervised machine learning on electrocardiography features to classify sleep in noncritically ill children},
  journal = {Journal of Clinical Sleep Medicine},
  year = {2025},
  doi = {10.5664/jcsm.11358}
}
Kostenlos starten →