Radar-based sleep stage classification in children undergoing polysomnography: a pilot-study.

Autor: de Goederen R; Pediatric Intensive Care Unit, Erasmus MC, Sophia Children's Hospital, Rotterdam, the Netherlands; Department of Neonatology, Wilhelmina Children's Hospital, University Medical Center Utrecht Utrecht, the Netherlands., Pu S; Department of Electrical Engineering, Eindhoven University of Technology, the Netherlands., Silos Viu M; Section Bioelectronics, Department of Electrical Engineering, Mathematics and Computer Science, Delft University of Technology, Delft, the Netherlands., Doan D; Department of Neonatology, Wilhelmina Children's Hospital, University Medical Center Utrecht Utrecht, the Netherlands., Overeem S; Department of Electrical Engineering, Eindhoven University of Technology, the Netherlands; Sleep Medicine Center Kempenhaeghe, Heeze, the Netherlands., Serdijn WA; Section Bioelectronics, Department of Electrical Engineering, Mathematics and Computer Science, Delft University of Technology, Delft, the Netherlands., Joosten KFM; Pediatric Intensive Care Unit, Erasmus MC, Sophia Children's Hospital, Rotterdam, the Netherlands., Long X; Department of Electrical Engineering, Eindhoven University of Technology, the Netherlands., Dudink J; Department of Neonatology, Wilhelmina Children's Hospital, University Medical Center Utrecht Utrecht, the Netherlands. Electronic address: j.dudink@umcutrecht.nl.
Jazyk: angličtina
Zdroj: Sleep medicine [Sleep Med] 2021 Jun; Vol. 82, pp. 1-8. Date of Electronic Publication: 2021 Mar 29.
DOI: 10.1016/j.sleep.2021.03.022
Abstrakt: Study Objectives: Unobtrusive monitoring of sleep and sleep disorders in children presents challenges. We investigated the possibility of using Ultra-Wide band (UWB) radar to measure sleep in children.
Methods: Thirty-two children scheduled to undergo a clinical polysomnography participated; their ages ranged from 2 months to 14 years. During the polysomnography, the children's body movements and breathing rate were measured by an UWB-radar. A total of 38 features were calculated from the motion signals and breathing rate obtained from the raw radar signals. Adaptive boosting was used as machine learning classifier to estimate sleep stages, with polysomnography as gold standard method for comparison.
Results: Data of all participants combined, this study achieved a Cohen's Kappa coefficient of 0.67 and an overall accuracy of 89.8% for wake and sleep classification, a Kappa of 0.47 and an accuracy of 72.9% for wake, rapid-eye-movement (REM) sleep, and non-REM sleep classification, and a Kappa of 0.43 and an accuracy of 58.0% for wake, REM sleep, light sleep and deep sleep classification.
Conclusion: Although the current performance is not sufficient for clinical use yet, UWB radar is a promising method for non-contact sleep analysis in children.
(Copyright © 2021 The Author(s). Published by Elsevier B.V. All rights reserved.)
Databáze: MEDLINE
Externí odkaz: