EUVIMEDEUVIMED entdecken
Crossref

Automated remote sleep monitoring needs uncertainty quantification

Elisabeth R M Heremans iD, Laura Van den Bulcke, Nabeel Seedat, Astrid Devulder, Pascal Borzée, Bertien Buyse iD, Dries Testelmans iD, Maarten Van Den Bossche, Mihaela van der Schaar, Maarten De Vos

Journal of Sleep Research · 2025

DOI: 10.1111/jsr.14300 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Sleep Research, 2025. Verfasst von Elisabeth R M Heremans und 9 weiteren Autor:innen. Beteiligte Einrichtung: Department of Electrical Engineering (ESAT), STADIUS Center for Dynamical Systems, Signal Processing and Data Analytics, KU Leuven, Leuven, Belgium. Hauptthemen laut MEDLINE: Electroencephalography, Machine Learning, Polysomnography, Sleep Stages. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 50 Literaturangaben. Gefördert von: Vlaamse regering, Flanders AI Research Program, Fonds Wetenschappelijk Onderzoek, Bijzonder onderzoeksfonds KU Leuven.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Wearable electroencephalography devices emerge as a cost‐effective and ergonomic alternative to gold‐standard polysomnography, paving the way for better health monitoring and sleep disorder screening. Machine learning allows to automate sleep stage classification, but trust and reliability issues have hampered its adoption in clinical applications. Estimating uncertainty is a crucial factor in enhancing reliability by identifying regions of heightened and diminished confidence. In this study, we used an uncertainty‐centred machine learning pipeline, U‐PASS, to automate sleep staging in a challenging real‐world dataset of single‐channel electroencephalography and accelerometry collected with a wearable device from an elderly population. We were able to effectively limit the uncertainty of our machine learning model and to reliably inform clinical experts of which predictions were uncertain to improve the machine learning model's reliability. This increased the five‐stage sleep‐scoring accuracy of a state‐of‐the‐art machine learning model from 63.9% to 71.2% on our dataset. Remarkably, the machine learning approach outperformed the human expert in interpreting these wearable data. Manual review by sleep specialists, without specific training for sleep staging on wearable electroencephalography, proved ineffective. The clinical utility of this automated remote monitoring system was also demonstrated, establishing a strong correlation between the predicted sleep parameters and the reference polysomnography parameters, and reproducing known correlations with the apnea–hypopnea index. In essence, this work presents a promising avenue to revolutionize remote patient care through the power of machine learning by the use of an automated data‐processing pipeline enhanced with uncertainty estimation.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

ElectroencephalographyMachine LearningPolysomnographySleep StagesHumansUncertaintyWearable Electronic DevicesMaleAgedReproducibility of ResultsFemaleAccelerometrySleep Wake Disorders

Stichwörter der Autor:innen

electroencephalographymachine learningsleep staginguncertainty quantificationwearable electroencephalography

Autor:innen und Institutionen

  • Department of Electrical Engineering (ESAT), STADIUS Center for Dynamical Systems, Signal Processing and Data Analytics, KU Leuven, Leuven, Belgium.
  • Neuropsychiatry, Department of Neurosciences, KU Leuven, Leuven, Belgium.
  • Department of Applied Mathematics and Theoretical Physics, University of Cambridge, Cambridge, UK.
  • Department of Neurology, University Hospitals Leuven, Leuven, Belgium.
  • Department of Pneumology, University Hospitals Leuven, Leuven, Belgium.
  • Department of Regeneration, KU Leuven, Leuven, Belgium.

ORCID-Profile: Elisabeth R M Heremans, Bertien Buyse, Dries Testelmans

Förderung

  • Vlaamse regering, Flanders AI Research Program
  • Fonds Wetenschappelijk Onderzoek
  • Bijzonder onderzoeksfonds KU Leuven
  • Vlaamse regering

Zitieren

APA

Heremans, E. R. M., Van den Bulcke, L., Seedat, N., Devulder, A., Borzée, P., Buyse, B., Testelmans, D., Van Den Bossche, M., van der Schaar, M., & De Vos, M. (2025). Automated remote sleep monitoring needs uncertainty quantification. Journal of Sleep Research. https://doi.org/10.1111/jsr.14300

Vancouver

Heremans ERM, Van den Bulcke L, Seedat N, Devulder A, Borzée P, Buyse B, et al. Automated remote sleep monitoring needs uncertainty quantification. Journal of Sleep Research. 2025. doi:10.1111/jsr.14300

BibTeX
@article{Heremans2025,
  author = {Heremans, Elisabeth R M and Van den Bulcke, Laura and Seedat, Nabeel and Devulder, Astrid and Borzée, Pascal and Buyse, Bertien and Testelmans, Dries and Van Den Bossche, Maarten and van der Schaar, Mihaela and De Vos, Maarten},
  title = {Automated remote sleep monitoring needs uncertainty quantification},
  journal = {Journal of Sleep Research},
  year = {2025},
  doi = {10.1111/jsr.14300}
}
Kostenlos starten →