SiCRNN: A Siamese Approach for Sleep Apnea Identification via Tracheal Microphone Signals

Sleep apnea syndrome (SAS) affects about 3–7% of the global population, but is often undiagnosed. It involves pauses in breathing during sleep, for at least 10 s, due to partial or total airway blockage. The current gold standard for diagnosing SAS is polysomnography (PSG), an intrusive procedure th...

Full description

Saved in:
Bibliographic Details
Main Authors: Davide Lillini, Carlo Aironi, Lucia Migliorelli, Leonardo Gabrielli, Stefano Squartini
Format: Article
Language:English
Published: MDPI AG 2024-12-01
Series:Sensors
Subjects:
Online Access:https://www.mdpi.com/1424-8220/24/23/7782
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849220414699470848
author Davide Lillini
Carlo Aironi
Lucia Migliorelli
Leonardo Gabrielli
Stefano Squartini
author_facet Davide Lillini
Carlo Aironi
Lucia Migliorelli
Leonardo Gabrielli
Stefano Squartini
author_sort Davide Lillini
collection DOAJ
description Sleep apnea syndrome (SAS) affects about 3–7% of the global population, but is often undiagnosed. It involves pauses in breathing during sleep, for at least 10 s, due to partial or total airway blockage. The current gold standard for diagnosing SAS is polysomnography (PSG), an intrusive procedure that depends on subjective assessment by expert clinicians. To address the limitations of PSG, we propose a decision support system, which uses a tracheal microphone for data collection and a deep learning (DL) approach—namely SiCRNN—to detect apnea events during overnight sleep recordings. Our proposed SiCRNN processes Mel spectrograms using a Siamese approach, integrating a convolutional neural network (CNN) backbone and a bidirectional gated recurrent unit (GRU). The final detection of <i>apnea</i> events is performed using an unsupervised clustering algorithm, specifically <i>k-means</i>. Multiple experimental runs were carried out to determine the optimal network configuration and the most suitable type and frequency range for the input data. Tests with data from eight patients showed that our method can achieve a <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mi>R</mi><mi>e</mi><mi>c</mi><mi>a</mi><mi>l</mi><mi>l</mi></mrow></semantics></math></inline-formula> score of up to 95% for <i>apnea</i> events. We also compared the proposed approach to a fully convolutional baseline, recently introduced in the literature, highlighting the effectiveness of the Siamese training paradigm in improving the identification of SAS.
format Article
id doaj-art-f9750a6587a84c42a559bc6c9b939e5b
institution Kabale University
issn 1424-8220
language English
publishDate 2024-12-01
publisher MDPI AG
record_format Article
series Sensors
spelling doaj-art-f9750a6587a84c42a559bc6c9b939e5b2024-12-13T16:32:45ZengMDPI AGSensors1424-82202024-12-012423778210.3390/s24237782SiCRNN: A Siamese Approach for Sleep Apnea Identification via Tracheal Microphone SignalsDavide Lillini0Carlo Aironi1Lucia Migliorelli2Leonardo Gabrielli3Stefano Squartini4Department of Information Engineering, Università Politecnica delle Marche, Via Brecce Bianche 12, 60131 Ancona, ItalyDepartment of Information Engineering, Università Politecnica delle Marche, Via Brecce Bianche 12, 60131 Ancona, ItalyDepartment of Information Engineering, Università Politecnica delle Marche, Via Brecce Bianche 12, 60131 Ancona, ItalyDepartment of Information Engineering, Università Politecnica delle Marche, Via Brecce Bianche 12, 60131 Ancona, ItalyDepartment of Information Engineering, Università Politecnica delle Marche, Via Brecce Bianche 12, 60131 Ancona, ItalySleep apnea syndrome (SAS) affects about 3–7% of the global population, but is often undiagnosed. It involves pauses in breathing during sleep, for at least 10 s, due to partial or total airway blockage. The current gold standard for diagnosing SAS is polysomnography (PSG), an intrusive procedure that depends on subjective assessment by expert clinicians. To address the limitations of PSG, we propose a decision support system, which uses a tracheal microphone for data collection and a deep learning (DL) approach—namely SiCRNN—to detect apnea events during overnight sleep recordings. Our proposed SiCRNN processes Mel spectrograms using a Siamese approach, integrating a convolutional neural network (CNN) backbone and a bidirectional gated recurrent unit (GRU). The final detection of <i>apnea</i> events is performed using an unsupervised clustering algorithm, specifically <i>k-means</i>. Multiple experimental runs were carried out to determine the optimal network configuration and the most suitable type and frequency range for the input data. Tests with data from eight patients showed that our method can achieve a <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mi>R</mi><mi>e</mi><mi>c</mi><mi>a</mi><mi>l</mi><mi>l</mi></mrow></semantics></math></inline-formula> score of up to 95% for <i>apnea</i> events. We also compared the proposed approach to a fully convolutional baseline, recently introduced in the literature, highlighting the effectiveness of the Siamese training paradigm in improving the identification of SAS.https://www.mdpi.com/1424-8220/24/23/7782sleep apnea syndromedeep learningclinical decision support systemsleep apneaOSA detection
spellingShingle Davide Lillini
Carlo Aironi
Lucia Migliorelli
Leonardo Gabrielli
Stefano Squartini
SiCRNN: A Siamese Approach for Sleep Apnea Identification via Tracheal Microphone Signals
Sensors
sleep apnea syndrome
deep learning
clinical decision support system
sleep apnea
OSA detection
title SiCRNN: A Siamese Approach for Sleep Apnea Identification via Tracheal Microphone Signals
title_full SiCRNN: A Siamese Approach for Sleep Apnea Identification via Tracheal Microphone Signals
title_fullStr SiCRNN: A Siamese Approach for Sleep Apnea Identification via Tracheal Microphone Signals
title_full_unstemmed SiCRNN: A Siamese Approach for Sleep Apnea Identification via Tracheal Microphone Signals
title_short SiCRNN: A Siamese Approach for Sleep Apnea Identification via Tracheal Microphone Signals
title_sort sicrnn a siamese approach for sleep apnea identification via tracheal microphone signals
topic sleep apnea syndrome
deep learning
clinical decision support system
sleep apnea
OSA detection
url https://www.mdpi.com/1424-8220/24/23/7782
work_keys_str_mv AT davidelillini sicrnnasiameseapproachforsleepapneaidentificationviatrachealmicrophonesignals
AT carloaironi sicrnnasiameseapproachforsleepapneaidentificationviatrachealmicrophonesignals
AT luciamigliorelli sicrnnasiameseapproachforsleepapneaidentificationviatrachealmicrophonesignals
AT leonardogabrielli sicrnnasiameseapproachforsleepapneaidentificationviatrachealmicrophonesignals
AT stefanosquartini sicrnnasiameseapproachforsleepapneaidentificationviatrachealmicrophonesignals