Automatic sleep staging based on 24/7 EEG SubQ (UNEEG medical) data displays strong agreement with polysomnography in healthy adults
Sleep Health · 2024-12 · 10 (6) · 612-620
DOI: 10.1016/j.sleh.2024.08.007 ↗Kurz gefasst
Klinische Studie in der Zeitschrift Sleep Health, 2024-12. Verfasst von Esben Ahrens und 6 weiteren Autor:innen. Beteiligte Einrichtung: Data Science, T&W Engineering A/S, Lillerød, Denmark; Department of Clinical Medicine, University of Copenhagen, Copenhagen N, Denmark. Electronic ad…. Hauptthemen laut MEDLINE: Electroencephalography, Polysomnography, Sleep Stages. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 35 Literaturangaben. Gefördert von: Innovation Fund.
Abstract (Originalsprache)
GOAL AND AIMS: Performance evaluation of automatic sleep staging on two-channel subcutaneous electroencephalography. FOCUS TECHNOLOGY: UNEEG medical's 24/7 electroencephalography SubQ (the SubQ device) with deep learning model U-SleepSQ. REFERENCE METHOD/TECHNOLOGY: Manually scored hypnograms from polysomnographic recordings. SAMPLE: Twenty-two healthy adults with 1-6 recordings per participant. The clinical study was registered at ClinicalTrials.gov with the identifier NCT04513743. DESIGN: Fine-tuning of U-Sleep in 11-fold cross-participant validation on 22 healthy adults. The resultant model was called U-SleepSQ. CORE ANALYTICS: Bland-Altman analysis of sleep parameters. Advanced multiclass model performance metrics: stage-specific accuracy, specificity, sensitivity, kappa (κ), and F1 score. Additionally, Cohen's κ coefficient and macro F1 score. Longitudinal and participant-level performance evaluation. ADDITIONAL ANALYTICS AND EXPLORATORY ANALYSES: Exploration of model confidence quantification. Performance vs. age, sex, body mass index, SubQ implantation hemisphere, normalized entropy, transition index, and scores from the following three questionnaires: Morningness-Eveningness Questionnaire, World Health Organization's 5-item Well-being Index, and Major Depression Inventory. CORE OUTCOMES: There was a strong agreement between the focus and reference method/technology. IMPORTANT SUPPLEMENTAL OUTCOMES: The confidence score was a promising metric for estimating the reliability of each hypnogram classified by the system. CORE CONCLUSION: The U-SleepSQ model classified hypnograms for healthy participants soon after implantation and longitudinally with a strong agreement with the gold standard of manually scored polysomnographics, exhibiting negligible temporal variation.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Data Science, T&W Engineering A/S, Lillerød, Denmark; Department of Clinical Medicine, University of Copenhagen, Copenhagen N, Denmark. Electronic address: eahr@tweng.com.
- Department of Clinical Medicine, University of Copenhagen, Copenhagen N, Denmark; Danish Center for Sleep Medicine, Department of Clinical Neurophysiology, Rigshospitalet, Glostrup, Denmark.
- Product & Science Department, UNEEG medical A/S, Lillerød, Denmark.
- Department of Clinical Medicine, University of Copenhagen, Copenhagen N, Denmark; Department of Otorhinolaryngology and Maxillofacial Surgery, Zealand University Hospital, Køge, Denmark.
- Product Management, T&W Engineering A/S, Lillerød, Denmark.
Förderung
- Innovation Fund
Zitieren
APA
Ahrens, E., Jennum, P., Duun-Henriksen, J., Djurhuus, B., Homøe, P., Kjær, T. W., & Hemmsen, M. C. (2024). Automatic sleep staging based on 24/7 EEG SubQ (UNEEG medical) data displays strong agreement with polysomnography in healthy adults. Sleep Health, 10(6), 612-620. https://doi.org/10.1016/j.sleh.2024.08.007
Vancouver
Ahrens E, Jennum P, Duun-Henriksen J, Djurhuus B, Homøe P, Kjær TW, et al. Automatic sleep staging based on 24/7 EEG SubQ (UNEEG medical) data displays strong agreement with polysomnography in healthy adults. Sleep Health. 2024;10(6):612-620. doi:10.1016/j.sleh.2024.08.007
BibTeX
@article{Ahrens2024,
author = {Ahrens, Esben and Jennum, Poul and Duun-Henriksen, Jonas and Djurhuus, Bjarki and Homøe, Preben and Kjær, Troels W and Hemmsen, Martin Christian},
title = {Automatic sleep staging based on 24/7 EEG SubQ (UNEEG medical) data displays strong agreement with polysomnography in healthy adults},
journal = {Sleep Health},
year = {2024},
volume = {10},
number = {6},
pages = {612--620},
doi = {10.1016/j.sleh.2024.08.007}
}
EUVIMED