Deep learning of sleep apnea-hypopnea events for accurate classification of obstructive sleep apnea and determination of clinical severity
Sleep Medicine · 2024-02 · 114 · 211-219
DOI: 10.1016/j.sleep.2024.01.015 ↗Kurz gefasst
Fachartikel in der Zeitschrift Sleep Medicine, 2024-02. Verfasst von Soonhyun Yook und 4 weiteren Autor:innen. Beteiligte Einrichtung: USC Stevens Neuroimaging and Informatics Institute, Keck School of Medicine of USC, University of Southern California, Los Angeles, CA, 90033, USA. Hauptthemen laut MEDLINE: Deep Learning, Sleep Apnea, Obstructive, Sleep Apnea Syndromes. Die Arbeit wurde bisher 43-mal zitiert (Crossref) und nennt 65 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar. Gefördert von: NIBIB NIH HHS.
Abstract (Originalsprache)
BACKGROUND: /Objective: Automatic apnea/hypopnea events classification, crucial for clinical applications, often faces challenges, particularly in hypopnea detection. This study aimed to evaluate the efficiency of a combined approach using nasal respiration flow (RF), peripheral oxygen saturation (SpO2), and ECG signals during polysomnography (PSG) for improved sleep apnea/hypopnea detection and obstructive sleep apnea (OSA) severity screening. METHODS: An Xception network was trained using main features from RF, SpO2, and ECG signals obtained during PSG. In addition, we incorporated demographic data for enhanced performance. The detection of apnea/hypopnea events was based on RF and SpO2 feature sets, while the screening and severity categorization of OSA utilized predicted apnea/hypopnea events in conjunction with demographic data. RESULTS: Using RF and SpO2 feature sets, our model achieved an accuracy of 94 % in detecting apnea/hypopnea events. For OSA screening, an exceptional accuracy of 99 % and an AUC of 0.99 were achieved. OSA severity categorization yielded an accuracy of 93 % and an AUC of 0.91, with no misclassification between normal and mild OSA versus moderate and severe OSA. However, classification errors predominantly arose in cases with hypopnea-prevalent participants. CONCLUSIONS: The proposed method offers a robust automatic detection system for apnea/hypopnea events, requiring fewer sensors than traditional PSG, and demonstrates exceptional performance. Additionally, the classification algorithms for OSA screening and severity categorization exhibit significant discriminatory capacity.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- USC Stevens Neuroimaging and Informatics Institute, Keck School of Medicine of USC, University of Southern California, Los Angeles, CA, 90033, USA.
- Department of Neurology, Seoul Hospital, College of Medicine, Ewha Womans University, Seoul, 07804, South Korea.
- Department of Neurology, Neuroscience Center, Samsung Medical Center, Samsung Biomedical Research Institute, School of Medicine, Sungkyunkwan University, Seoul, 06351, South Korea. Electronic address: ejoo@skku.edu.
- USC Stevens Neuroimaging and Informatics Institute, Keck School of Medicine of USC, University of Southern California, Los Angeles, CA, 90033, USA. Electronic address: hosung.kim@loni.usc.edu.
Förderung
- NIBIB NIH HHS
Zitieren
APA
Yook, S., Kim, D., Gupte, C., Joo, E. Y., & Kim, H. (2024). Deep learning of sleep apnea-hypopnea events for accurate classification of obstructive sleep apnea and determination of clinical severity. Sleep Medicine, 114, 211-219. https://doi.org/10.1016/j.sleep.2024.01.015
Vancouver
Yook S, Kim D, Gupte C, Joo EY, Kim H. Deep learning of sleep apnea-hypopnea events for accurate classification of obstructive sleep apnea and determination of clinical severity. Sleep Medicine. 2024;114:211-219. doi:10.1016/j.sleep.2024.01.015
BibTeX
@article{Yook2024,
author = {Yook, Soonhyun and Kim, Dongyeop and Gupte, Chaitanya and Joo, Eun Yeon and Kim, Hosung},
title = {Deep learning of sleep apnea-hypopnea events for accurate classification of obstructive sleep apnea and determination of clinical severity},
journal = {Sleep Medicine},
year = {2024},
volume = {114},
pages = {211--219},
doi = {10.1016/j.sleep.2024.01.015}
}
EUVIMED