Adoption of Transformer Neural Network to Improve the Diagnostic Performance of Oximetry for Obstructive Sleep Apnea
Sensors · 2023
DOI: 10.3390/s23187924 ↗Kurz gefasst
Fachartikel in der Zeitschrift Sensors, 2023. Verfasst von Malak Abdullah Almarshad und 4 weiteren Autor:innen. Beteiligte Einrichtung: Computer Science Department, College of Computer and Information Sciences, King Saud University, Riyadh 11543, Saudi Arabia. Hauptthemen laut MEDLINE: Labor, Obstetric, Sleep Apnea, Obstructive. Die Arbeit wurde bisher 24-mal zitiert (Crossref) und nennt 52 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Deanship of Scientific Research at King Saud University.
Abstract (Originalsprache)
Scoring polysomnography for obstructive sleep apnea diagnosis is a laborious, long, and costly process. Machine learning approaches, such as deep neural networks, can reduce scoring time and costs. However, most methods require prior filtering and preprocessing of the raw signal. Our work presents a novel method for diagnosing obstructive sleep apnea using a transformer neural network with learnable positional encoding, which outperforms existing state-of-the-art solutions. This approach has the potential to improve the diagnostic performance of oximetry for obstructive sleep apnea and reduce the time and costs associated with traditional polysomnography. Contrary to existing approaches, our approach performs annotations at one-second granularity. Allowing physicians to interpret the model’s outcome. In addition, we tested different positional encoding designs as the first layer of the model, and the best results were achieved using a learnable positional encoding based on an autoencoder with structural novelty. In addition, we tried different temporal resolutions with various granularity levels from 1 to 360 s. All experiments were carried out on an independent test set from the public OSASUD dataset and showed that our approach outperforms current state-of-the-art solutions with a satisfactory AUC of 0.89, accuracy of 0.80, and F1-score of 0.79.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Computer Science Department, College of Computer and Information Sciences, King Saud University, Riyadh 11543, Saudi Arabia.
- Computer Science Department, College of Computer and Information Sciences, Al-Imam Mohammad Ibn Saud Islamic University, Riyadh 11432, Saudi Arabia.
- The University Sleep Disorders Center, Department of Medicine, College of Medicine, King Saud University, Riyadh 11324, Saudi Arabia.
- Strategic Technologies Program of the National Plan for Sciences and Technology and Innovation in the Kingdom of Saudi Arabia, Riyadh 11324, Saudi Arabia.
ORCID-Profile: Malak Abdullah Almarshad, Saad Al-Ahmadi, Md Saiful Islam, Ahmed S BaHammam, Adel Soudani
Förderung
- Deanship of Scientific Research at King Saud University
Zitieren
APA
Almarshad, M. A., Al-Ahmadi, S., Islam, M. S., BaHammam, A. S., & Soudani, A. (2023). Adoption of Transformer Neural Network to Improve the Diagnostic Performance of Oximetry for Obstructive Sleep Apnea. Sensors. https://doi.org/10.3390/s23187924
Vancouver
Almarshad MA, Al-Ahmadi S, Islam MS, BaHammam AS, Soudani A. Adoption of Transformer Neural Network to Improve the Diagnostic Performance of Oximetry for Obstructive Sleep Apnea. Sensors. 2023. doi:10.3390/s23187924
BibTeX
@article{Almarshad2023,
author = {Almarshad, Malak Abdullah and Al-Ahmadi, Saad and Islam, Md Saiful and BaHammam, Ahmed S and Soudani, Adel},
title = {Adoption of Transformer Neural Network to Improve the Diagnostic Performance of Oximetry for Obstructive Sleep Apnea},
journal = {Sensors},
year = {2023},
doi = {10.3390/s23187924}
}
EUVIMED