Accurate detection of sleep apnea with long short-term memory network based on RR interval signals

Sleep apnea is a common condition that is characterized by sleep-disordered breathing. Worldwide the number of apnea cases has increased and there has been a growing number of patients suffering from apnea complications. Unfortunately, many cases remain undetected, because expensive and inconvenient...

Full description

Saved in:
Bibliographic Details
Published in:Knowledge-based systems 2021-01, Vol.212, p.106591, Article 106591
Main Authors: Faust, Oliver, Barika, Ragab, Shenfield, Alex, Ciaccio, Edward J., Acharya, U. Rajendra
Format: Article
Language:English
Subjects:
Accuracy
Algorithms
Bandpass filters
Deep learning
Detrending
Diagnosis
Electrocardiography
Gaussian process
Heart rate variability
Intervals
Machine learning
Sensitivity
Signal classification
Signal processing
Sleep apnea
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
cited_by cdi_FETCH-LOGICAL-c380t-608d4fe626570589ee03212ad762585add2d96cf88e8a52767c11805b1044bb53
cites cdi_FETCH-LOGICAL-c380t-608d4fe626570589ee03212ad762585add2d96cf88e8a52767c11805b1044bb53
container_end_page
container_issue
container_start_page 106591
container_title Knowledge-based systems
container_volume 212
creator Faust, Oliver
Barika, Ragab
Shenfield, Alex
Ciaccio, Edward J.
Acharya, U. Rajendra
description Sleep apnea is a common condition that is characterized by sleep-disordered breathing. Worldwide the number of apnea cases has increased and there has been a growing number of patients suffering from apnea complications. Unfortunately, many cases remain undetected, because expensive and inconvenient examination methods are formidable barriers with regard to the diagnostics. Furthermore, treatment monitoring depends on the same methods which also underpin the initial diagnosis; hence issues related to the examination methods cause difficulties with managing sleep apnea as well. Computer-Aided Diagnosis (CAD) systems could be a tool to increase the efficiency and efficacy of diagnosis. To investigate this hypothesis, we designed a deep learning model that classifies beat-to-beat interval traces, medically known as RR intervals, into apnea versus non-apnea. The RR intervals were extracted from Electrocardiogram (ECG) signals contained in the Apnea-ECG benchmark Database. Before feeding the RR intervals to the classification algorithm, the signal was band-pass filtered with an Ornstein–Uhlenbeck third-order Gaussian process. 10-fold cross-validation indicated that the Long Short-Term Memory (LSTM) network has 99.80% accuracy, 99.85% sensitivity, and 99.73% specificity. With hold-out validation, the same network achieved 81.30% accuracy, 59.90% sensitivity, and 91.75% specificity. During the design, we learned that the band-pass filter improved classification accuracy by over 20%. The increased performance resulted from the fact that neural activation functions can process a DC free signal more efficiently. The result is likely transferable to the design of other RR interval based CAD systems, where the filter can help to improve classification performance.
doi_str_mv 10.1016/j.knosys.2020.106591
format article
fullrecord <record><control><sourceid>proquest_cross</sourceid><recordid>TN_cdi_proquest_journals_2490265501</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><els_id>S0950705120307206</els_id><sourcerecordid>2490265501</sourcerecordid><originalsourceid>FETCH-LOGICAL-c380t-608d4fe626570589ee03212ad762585add2d96cf88e8a52767c11805b1044bb53</originalsourceid><addsrcrecordid>eNp9kEtLAzEUhYMoWB__wEXA9dSbdDKT2Qil-IKCUHQdMsmdNn1MapIq_femjGtXBy7nHM79CLljMGbAqof1eNP7eIxjDvx0qkTDzsiIyZoXdQnNORlBI6CoQbBLchXjGgA4Z3JE2qkxh6ATUosJTXK-p76jcYu4p3rfo6Y_Lq3o1vdLGlc-pCJh2NEd7nw40h7Tjw8b2uqIlubsYkFdnx3fekujW_Z6G2_IRZcFb__0mnw-P33MXov5-8vbbDovzERCKiqQtuyw4pXIO2WDCBPOuLZ1xYUU2lpum8p0UqLUgtdVbRiTIFoGZdm2YnJN7ofeffBfB4xJrf0hnBYoXjaQewWw7CoHlwk-xoCd2ge30-GoGKgTTbVWA011oqkGmjn2OMQwf_DtMKhoHPYGrQsZm7Le_V_wC9Wjf4s</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2490265501</pqid></control><display><type>article</type><title>Accurate detection of sleep apnea with long short-term memory network based on RR interval signals</title><source>Library &amp; Information Science Abstracts (LISA)</source><source>ScienceDirect Freedom Collection 2022-2024</source><creator>Faust, Oliver ; Barika, Ragab ; Shenfield, Alex ; Ciaccio, Edward J. ; Acharya, U. Rajendra</creator><creatorcontrib>Faust, Oliver ; Barika, Ragab ; Shenfield, Alex ; Ciaccio, Edward J. ; Acharya, U. Rajendra</creatorcontrib><description>Sleep apnea is a common condition that is characterized by sleep-disordered breathing. Worldwide the number of apnea cases has increased and there has been a growing number of patients suffering from apnea complications. Unfortunately, many cases remain undetected, because expensive and inconvenient examination methods are formidable barriers with regard to the diagnostics. Furthermore, treatment monitoring depends on the same methods which also underpin the initial diagnosis; hence issues related to the examination methods cause difficulties with managing sleep apnea as well. Computer-Aided Diagnosis (CAD) systems could be a tool to increase the efficiency and efficacy of diagnosis. To investigate this hypothesis, we designed a deep learning model that classifies beat-to-beat interval traces, medically known as RR intervals, into apnea versus non-apnea. The RR intervals were extracted from Electrocardiogram (ECG) signals contained in the Apnea-ECG benchmark Database. Before feeding the RR intervals to the classification algorithm, the signal was band-pass filtered with an Ornstein–Uhlenbeck third-order Gaussian process. 10-fold cross-validation indicated that the Long Short-Term Memory (LSTM) network has 99.80% accuracy, 99.85% sensitivity, and 99.73% specificity. With hold-out validation, the same network achieved 81.30% accuracy, 59.90% sensitivity, and 91.75% specificity. During the design, we learned that the band-pass filter improved classification accuracy by over 20%. The increased performance resulted from the fact that neural activation functions can process a DC free signal more efficiently. The result is likely transferable to the design of other RR interval based CAD systems, where the filter can help to improve classification performance.</description><identifier>ISSN: 0950-7051</identifier><identifier>EISSN: 1872-7409</identifier><identifier>DOI: 10.1016/j.knosys.2020.106591</identifier><language>eng</language><publisher>Amsterdam: Elsevier B.V</publisher><subject>Accuracy ; Algorithms ; Bandpass filters ; Deep learning ; Detrending ; Diagnosis ; Electrocardiography ; Gaussian process ; Heart rate variability ; Intervals ; Machine learning ; Sensitivity ; Signal classification ; Signal processing ; Sleep apnea</subject><ispartof>Knowledge-based systems, 2021-01, Vol.212, p.106591, Article 106591</ispartof><rights>2020 Elsevier B.V.</rights><rights>Copyright Elsevier Science Ltd. Jan 5, 2021</rights><lds50>peer_reviewed</lds50><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c380t-608d4fe626570589ee03212ad762585add2d96cf88e8a52767c11805b1044bb53</citedby><cites>FETCH-LOGICAL-c380t-608d4fe626570589ee03212ad762585add2d96cf88e8a52767c11805b1044bb53</cites><orcidid>0000-0002-3979-4077 ; 0000-0002-2931-8077</orcidid></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>315,786,790,27957,27958,34170</link.rule.ids></links><search><creatorcontrib>Faust, Oliver</creatorcontrib><creatorcontrib>Barika, Ragab</creatorcontrib><creatorcontrib>Shenfield, Alex</creatorcontrib><creatorcontrib>Ciaccio, Edward J.</creatorcontrib><creatorcontrib>Acharya, U. Rajendra</creatorcontrib><title>Accurate detection of sleep apnea with long short-term memory network based on RR interval signals</title><title>Knowledge-based systems</title><description>Sleep apnea is a common condition that is characterized by sleep-disordered breathing. Worldwide the number of apnea cases has increased and there has been a growing number of patients suffering from apnea complications. Unfortunately, many cases remain undetected, because expensive and inconvenient examination methods are formidable barriers with regard to the diagnostics. Furthermore, treatment monitoring depends on the same methods which also underpin the initial diagnosis; hence issues related to the examination methods cause difficulties with managing sleep apnea as well. Computer-Aided Diagnosis (CAD) systems could be a tool to increase the efficiency and efficacy of diagnosis. To investigate this hypothesis, we designed a deep learning model that classifies beat-to-beat interval traces, medically known as RR intervals, into apnea versus non-apnea. The RR intervals were extracted from Electrocardiogram (ECG) signals contained in the Apnea-ECG benchmark Database. Before feeding the RR intervals to the classification algorithm, the signal was band-pass filtered with an Ornstein–Uhlenbeck third-order Gaussian process. 10-fold cross-validation indicated that the Long Short-Term Memory (LSTM) network has 99.80% accuracy, 99.85% sensitivity, and 99.73% specificity. With hold-out validation, the same network achieved 81.30% accuracy, 59.90% sensitivity, and 91.75% specificity. During the design, we learned that the band-pass filter improved classification accuracy by over 20%. The increased performance resulted from the fact that neural activation functions can process a DC free signal more efficiently. The result is likely transferable to the design of other RR interval based CAD systems, where the filter can help to improve classification performance.</description><subject>Accuracy</subject><subject>Algorithms</subject><subject>Bandpass filters</subject><subject>Deep learning</subject><subject>Detrending</subject><subject>Diagnosis</subject><subject>Electrocardiography</subject><subject>Gaussian process</subject><subject>Heart rate variability</subject><subject>Intervals</subject><subject>Machine learning</subject><subject>Sensitivity</subject><subject>Signal classification</subject><subject>Signal processing</subject><subject>Sleep apnea</subject><issn>0950-7051</issn><issn>1872-7409</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2021</creationdate><recordtype>article</recordtype><sourceid>F2A</sourceid><recordid>eNp9kEtLAzEUhYMoWB__wEXA9dSbdDKT2Qil-IKCUHQdMsmdNn1MapIq_femjGtXBy7nHM79CLljMGbAqof1eNP7eIxjDvx0qkTDzsiIyZoXdQnNORlBI6CoQbBLchXjGgA4Z3JE2qkxh6ATUosJTXK-p76jcYu4p3rfo6Y_Lq3o1vdLGlc-pCJh2NEd7nw40h7Tjw8b2uqIlubsYkFdnx3fekujW_Z6G2_IRZcFb__0mnw-P33MXov5-8vbbDovzERCKiqQtuyw4pXIO2WDCBPOuLZ1xYUU2lpum8p0UqLUgtdVbRiTIFoGZdm2YnJN7ofeffBfB4xJrf0hnBYoXjaQewWw7CoHlwk-xoCd2ge30-GoGKgTTbVWA011oqkGmjn2OMQwf_DtMKhoHPYGrQsZm7Le_V_wC9Wjf4s</recordid><startdate>20210105</startdate><enddate>20210105</enddate><creator>Faust, Oliver</creator><creator>Barika, Ragab</creator><creator>Shenfield, Alex</creator><creator>Ciaccio, Edward J.</creator><creator>Acharya, U. Rajendra</creator><general>Elsevier B.V</general><general>Elsevier Science Ltd</general><scope>AAYXX</scope><scope>CITATION</scope><scope>7SC</scope><scope>8FD</scope><scope>E3H</scope><scope>F2A</scope><scope>JQ2</scope><scope>L7M</scope><scope>L~C</scope><scope>L~D</scope><orcidid>https://orcid.org/0000-0002-3979-4077</orcidid><orcidid>https://orcid.org/0000-0002-2931-8077</orcidid></search><sort><creationdate>20210105</creationdate><title>Accurate detection of sleep apnea with long short-term memory network based on RR interval signals</title><author>Faust, Oliver ; Barika, Ragab ; Shenfield, Alex ; Ciaccio, Edward J. ; Acharya, U. Rajendra</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c380t-608d4fe626570589ee03212ad762585add2d96cf88e8a52767c11805b1044bb53</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2021</creationdate><topic>Accuracy</topic><topic>Algorithms</topic><topic>Bandpass filters</topic><topic>Deep learning</topic><topic>Detrending</topic><topic>Diagnosis</topic><topic>Electrocardiography</topic><topic>Gaussian process</topic><topic>Heart rate variability</topic><topic>Intervals</topic><topic>Machine learning</topic><topic>Sensitivity</topic><topic>Signal classification</topic><topic>Signal processing</topic><topic>Sleep apnea</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Faust, Oliver</creatorcontrib><creatorcontrib>Barika, Ragab</creatorcontrib><creatorcontrib>Shenfield, Alex</creatorcontrib><creatorcontrib>Ciaccio, Edward J.</creatorcontrib><creatorcontrib>Acharya, U. Rajendra</creatorcontrib><collection>CrossRef</collection><collection>Computer and Information Systems Abstracts</collection><collection>Technology Research Database</collection><collection>Library &amp; Information Sciences Abstracts (LISA)</collection><collection>Library &amp; Information Science Abstracts (LISA)</collection><collection>ProQuest Computer Science Collection</collection><collection>Advanced Technologies Database with Aerospace</collection><collection>Computer and Information Systems Abstracts – Academic</collection><collection>Computer and Information Systems Abstracts Professional</collection><jtitle>Knowledge-based systems</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Faust, Oliver</au><au>Barika, Ragab</au><au>Shenfield, Alex</au><au>Ciaccio, Edward J.</au><au>Acharya, U. Rajendra</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Accurate detection of sleep apnea with long short-term memory network based on RR interval signals</atitle><jtitle>Knowledge-based systems</jtitle><date>2021-01-05</date><risdate>2021</risdate><volume>212</volume><spage>106591</spage><pages>106591-</pages><artnum>106591</artnum><issn>0950-7051</issn><eissn>1872-7409</eissn><abstract>Sleep apnea is a common condition that is characterized by sleep-disordered breathing. Worldwide the number of apnea cases has increased and there has been a growing number of patients suffering from apnea complications. Unfortunately, many cases remain undetected, because expensive and inconvenient examination methods are formidable barriers with regard to the diagnostics. Furthermore, treatment monitoring depends on the same methods which also underpin the initial diagnosis; hence issues related to the examination methods cause difficulties with managing sleep apnea as well. Computer-Aided Diagnosis (CAD) systems could be a tool to increase the efficiency and efficacy of diagnosis. To investigate this hypothesis, we designed a deep learning model that classifies beat-to-beat interval traces, medically known as RR intervals, into apnea versus non-apnea. The RR intervals were extracted from Electrocardiogram (ECG) signals contained in the Apnea-ECG benchmark Database. Before feeding the RR intervals to the classification algorithm, the signal was band-pass filtered with an Ornstein–Uhlenbeck third-order Gaussian process. 10-fold cross-validation indicated that the Long Short-Term Memory (LSTM) network has 99.80% accuracy, 99.85% sensitivity, and 99.73% specificity. With hold-out validation, the same network achieved 81.30% accuracy, 59.90% sensitivity, and 91.75% specificity. During the design, we learned that the band-pass filter improved classification accuracy by over 20%. The increased performance resulted from the fact that neural activation functions can process a DC free signal more efficiently. The result is likely transferable to the design of other RR interval based CAD systems, where the filter can help to improve classification performance.</abstract><cop>Amsterdam</cop><pub>Elsevier B.V</pub><doi>10.1016/j.knosys.2020.106591</doi><orcidid>https://orcid.org/0000-0002-3979-4077</orcidid><orcidid>https://orcid.org/0000-0002-2931-8077</orcidid><oa>free_for_read</oa></addata></record>
fulltext fulltext
identifier ISSN: 0950-7051
ispartof Knowledge-based systems, 2021-01, Vol.212, p.106591, Article 106591
issn 0950-7051
1872-7409
language eng
recordid cdi_proquest_journals_2490265501
source Library & Information Science Abstracts (LISA); ScienceDirect Freedom Collection 2022-2024
subjects Accuracy
Algorithms
Bandpass filters
Deep learning
Detrending
Diagnosis
Electrocardiography
Gaussian process
Heart rate variability
Intervals
Machine learning
Sensitivity
Signal classification
Signal processing
Sleep apnea
title Accurate detection of sleep apnea with long short-term memory network based on RR interval signals
url http://sfxeu10.hosted.exlibrisgroup.com/loughborough?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-09-22T21%3A35%3A19IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_cross&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Accurate%20detection%20of%20sleep%20apnea%20with%20long%20short-term%20memory%20network%20based%20on%20RR%20interval%20signals&rft.jtitle=Knowledge-based%20systems&rft.au=Faust,%20Oliver&rft.date=2021-01-05&rft.volume=212&rft.spage=106591&rft.pages=106591-&rft.artnum=106591&rft.issn=0950-7051&rft.eissn=1872-7409&rft_id=info:doi/10.1016/j.knosys.2020.106591&rft_dat=%3Cproquest_cross%3E2490265501%3C/proquest_cross%3E%3Cgrp_id%3Ecdi_FETCH-LOGICAL-c380t-608d4fe626570589ee03212ad762585add2d96cf88e8a52767c11805b1044bb53%3C/grp_id%3E%3Coa%3E%3C/oa%3E%3Curl%3E%3C/url%3E&rft_id=info:oai/&rft_pqid=2490265501&rft_id=info:pmid/&rfr_iscdi=true