Automated Scoring of Obstructive Sleep Apnea and Hypopnea Events Using Short-Term Electrocardiogram Recordings
Obstructive sleep apnea or hypopnea causes a pause or reduction in airflow with continuous breathing effort. The aim of this study is to identify individual apnea and hypopnea events from normal breathing events using wavelet-based features of 5-s ECG signals (sampling rate = 250 Hz) and estimate th...
Gespeichert in:
| Veröffentlicht in: | IEEE journal of biomedical and health informatics 2009-11, Vol.13 (6), p.1057-1067 |
|---|---|
| Hauptverfasser: | , , |
| Format: | Artikel |
| Sprache: | eng |
| Schlagworte: | |
| Online-Zugang: | Volltext bestellen |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| container_end_page | 1067 |
|---|---|
| container_issue | 6 |
| container_start_page | 1057 |
| container_title | IEEE journal of biomedical and health informatics |
| container_volume | 13 |
| creator | Khandoker, A.H. Gubbi, J. Palaniswami, M. |
| description | Obstructive sleep apnea or hypopnea causes a pause or reduction in airflow with continuous breathing effort. The aim of this study is to identify individual apnea and hypopnea events from normal breathing events using wavelet-based features of 5-s ECG signals (sampling rate = 250 Hz) and estimate the surrogate apnea index (AI)/hypopnea index (HI) (AHI). Total 82 535 ECG epochs (each of 5-s duration) from normal breathing during sleep, 1638 ECG epochs from 689 hypopnea events, and 3151 ECG epochs from 1862 apnea events were collected from 17 patients in the training set. Two-staged feedforward neural network model was trained using features from ECG signals with leave-one-patient-out cross-validation technique. At the first stage of classification, events (apnea and hypopnea) were classified from normal breathing events, and at the second stage, hypopneas were identified from apnea. Independent test was performed on 16 subjects' ECGs containing 483 hypopnea and 1352 apnea events. The cross-validation and independent test accuracies of apnea and hypopnea detection were found to be 94.84% and 76.82%, respectively, for training set, and 94.72% and 79.77%, respectively, for test set. The Bland-Altman plots showed unbiased estimations with standard deviations of plusmn 2.19, plusmn 2.16, and plusmn 3.64 events/h for AI, HI, and AHI, respectively. Results indicate the possibility of recognizing apnea/hypopnea events based on shorter segments of ECG signals. |
| doi_str_mv | 10.1109/TITB.2009.2031639 |
| format | Article |
| fullrecord | <record><control><sourceid>proquest_RIE</sourceid><recordid>TN_cdi_proquest_miscellaneous_21336824</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ieee_id>5256176</ieee_id><sourcerecordid>1671262713</sourcerecordid><originalsourceid>FETCH-LOGICAL-c443t-40cbc89d1864c84de420f59d24876ff7e3c74705c6e662502143ba1f85fa3fb63</originalsourceid><addsrcrecordid>eNqF0l1rFDEUBuAgiq2rP0AECb1Qb6bm-2Qu17LaQqHgbq-HTOZMnTIzWZOZQv-9GXdR8KLe5IM85xCSl5C3nJ1zzsrPu6vdl3PBWJkHyY0sn5FTrrUtGJPieV4zWxYAwE_Iq5TuGeNKc_mSnPASQJegTsm4nqcwuAkbuvUhduMdDS29qdMUZz91D0i3PeKervcjOurGhl4-7sPvzeYBxynR27QUbX-EOBU7jAPd9OinGLyLTRfuohvod8ytm8zSa_KidX3CN8d5RW6_bnYXl8X1zberi_V14ZWSU6GYr70tG26N8lY1qARrddkIZcG0LaD0oIBpb9AYoZngStaOt1a3Tra1kSvy8dB3H8PPGdNUDV3y2PduxDCnyhoAqRnY_0qQ0nAFlmX54UkpeKZWqAw_PQm5AS6MgOxX5Owfeh_mOOanqawGJWwplivyA_IxpBSxrfaxG1x8rDirliBUSxCqJQjVMQi55v2x8VwP2PytOP58Bu8OoEPEP8daaMPByF_XVLX0</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>857428928</pqid></control><display><type>article</type><title>Automated Scoring of Obstructive Sleep Apnea and Hypopnea Events Using Short-Term Electrocardiogram Recordings</title><source>IEL</source><creator>Khandoker, A.H. ; Gubbi, J. ; Palaniswami, M.</creator><creatorcontrib>Khandoker, A.H. ; Gubbi, J. ; Palaniswami, M.</creatorcontrib><description>Obstructive sleep apnea or hypopnea causes a pause or reduction in airflow with continuous breathing effort. The aim of this study is to identify individual apnea and hypopnea events from normal breathing events using wavelet-based features of 5-s ECG signals (sampling rate = 250 Hz) and estimate the surrogate apnea index (AI)/hypopnea index (HI) (AHI). Total 82 535 ECG epochs (each of 5-s duration) from normal breathing during sleep, 1638 ECG epochs from 689 hypopnea events, and 3151 ECG epochs from 1862 apnea events were collected from 17 patients in the training set. Two-staged feedforward neural network model was trained using features from ECG signals with leave-one-patient-out cross-validation technique. At the first stage of classification, events (apnea and hypopnea) were classified from normal breathing events, and at the second stage, hypopneas were identified from apnea. Independent test was performed on 16 subjects' ECGs containing 483 hypopnea and 1352 apnea events. The cross-validation and independent test accuracies of apnea and hypopnea detection were found to be 94.84% and 76.82%, respectively, for training set, and 94.72% and 79.77%, respectively, for test set. The Bland-Altman plots showed unbiased estimations with standard deviations of plusmn 2.19, plusmn 2.16, and plusmn 3.64 events/h for AI, HI, and AHI, respectively. Results indicate the possibility of recognizing apnea/hypopnea events based on shorter segments of ECG signals.</description><identifier>ISSN: 1089-7771</identifier><identifier>ISSN: 2168-2194</identifier><identifier>EISSN: 1558-0032</identifier><identifier>EISSN: 2168-2208</identifier><identifier>DOI: 10.1109/TITB.2009.2031639</identifier><identifier>PMID: 19775974</identifier><identifier>CODEN: ITIBFX</identifier><language>eng</language><publisher>United States: IEEE</publisher><subject>Adult ; Artificial intelligence ; Breathing ; ECG ; Electrocardiography ; Electrocardiography - methods ; Electromyography ; Electrooculography ; Feedforward ; Humans ; Hypertension ; Lungs ; Middle Aged ; Models, Biological ; Monitoring, Physiologic - methods ; Neural networks ; Neural Networks (Computer) ; neural networks (NNs) ; obstructive sleep apnea (OSA) ; Patients ; Pattern Recognition, Automated - methods ; Polysomnography - methods ; Reproducibility of Results ; ROC Curve ; Sampling ; Signal Processing, Computer-Assisted ; Signal sampling ; Sleep ; Sleep apnea ; Sleep Apnea, Obstructive - physiopathology ; Sleep disorders ; sleep study ; Studies ; Testing ; Training ; wavelet</subject><ispartof>IEEE journal of biomedical and health informatics, 2009-11, Vol.13 (6), p.1057-1067</ispartof><rights>Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2009</rights><lds50>peer_reviewed</lds50><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c443t-40cbc89d1864c84de420f59d24876ff7e3c74705c6e662502143ba1f85fa3fb63</citedby><cites>FETCH-LOGICAL-c443t-40cbc89d1864c84de420f59d24876ff7e3c74705c6e662502143ba1f85fa3fb63</cites></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://ieeexplore.ieee.org/document/5256176$$EHTML$$P50$$Gieee$$H</linktohtml><link.rule.ids>314,776,780,792,27901,27902,54733</link.rule.ids><linktorsrc>$$Uhttps://ieeexplore.ieee.org/document/5256176$$EView_record_in_IEEE$$FView_record_in_$$GIEEE</linktorsrc><backlink>$$Uhttps://www.ncbi.nlm.nih.gov/pubmed/19775974$$D View this record in MEDLINE/PubMed$$Hfree_for_read</backlink></links><search><creatorcontrib>Khandoker, A.H.</creatorcontrib><creatorcontrib>Gubbi, J.</creatorcontrib><creatorcontrib>Palaniswami, M.</creatorcontrib><title>Automated Scoring of Obstructive Sleep Apnea and Hypopnea Events Using Short-Term Electrocardiogram Recordings</title><title>IEEE journal of biomedical and health informatics</title><addtitle>TITB</addtitle><addtitle>IEEE Trans Inf Technol Biomed</addtitle><description>Obstructive sleep apnea or hypopnea causes a pause or reduction in airflow with continuous breathing effort. The aim of this study is to identify individual apnea and hypopnea events from normal breathing events using wavelet-based features of 5-s ECG signals (sampling rate = 250 Hz) and estimate the surrogate apnea index (AI)/hypopnea index (HI) (AHI). Total 82 535 ECG epochs (each of 5-s duration) from normal breathing during sleep, 1638 ECG epochs from 689 hypopnea events, and 3151 ECG epochs from 1862 apnea events were collected from 17 patients in the training set. Two-staged feedforward neural network model was trained using features from ECG signals with leave-one-patient-out cross-validation technique. At the first stage of classification, events (apnea and hypopnea) were classified from normal breathing events, and at the second stage, hypopneas were identified from apnea. Independent test was performed on 16 subjects' ECGs containing 483 hypopnea and 1352 apnea events. The cross-validation and independent test accuracies of apnea and hypopnea detection were found to be 94.84% and 76.82%, respectively, for training set, and 94.72% and 79.77%, respectively, for test set. The Bland-Altman plots showed unbiased estimations with standard deviations of plusmn 2.19, plusmn 2.16, and plusmn 3.64 events/h for AI, HI, and AHI, respectively. Results indicate the possibility of recognizing apnea/hypopnea events based on shorter segments of ECG signals.</description><subject>Adult</subject><subject>Artificial intelligence</subject><subject>Breathing</subject><subject>ECG</subject><subject>Electrocardiography</subject><subject>Electrocardiography - methods</subject><subject>Electromyography</subject><subject>Electrooculography</subject><subject>Feedforward</subject><subject>Humans</subject><subject>Hypertension</subject><subject>Lungs</subject><subject>Middle Aged</subject><subject>Models, Biological</subject><subject>Monitoring, Physiologic - methods</subject><subject>Neural networks</subject><subject>Neural Networks (Computer)</subject><subject>neural networks (NNs)</subject><subject>obstructive sleep apnea (OSA)</subject><subject>Patients</subject><subject>Pattern Recognition, Automated - methods</subject><subject>Polysomnography - methods</subject><subject>Reproducibility of Results</subject><subject>ROC Curve</subject><subject>Sampling</subject><subject>Signal Processing, Computer-Assisted</subject><subject>Signal sampling</subject><subject>Sleep</subject><subject>Sleep apnea</subject><subject>Sleep Apnea, Obstructive - physiopathology</subject><subject>Sleep disorders</subject><subject>sleep study</subject><subject>Studies</subject><subject>Testing</subject><subject>Training</subject><subject>wavelet</subject><issn>1089-7771</issn><issn>2168-2194</issn><issn>1558-0032</issn><issn>2168-2208</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2009</creationdate><recordtype>article</recordtype><sourceid>RIE</sourceid><sourceid>EIF</sourceid><recordid>eNqF0l1rFDEUBuAgiq2rP0AECb1Qb6bm-2Qu17LaQqHgbq-HTOZMnTIzWZOZQv-9GXdR8KLe5IM85xCSl5C3nJ1zzsrPu6vdl3PBWJkHyY0sn5FTrrUtGJPieV4zWxYAwE_Iq5TuGeNKc_mSnPASQJegTsm4nqcwuAkbuvUhduMdDS29qdMUZz91D0i3PeKervcjOurGhl4-7sPvzeYBxynR27QUbX-EOBU7jAPd9OinGLyLTRfuohvod8ytm8zSa_KidX3CN8d5RW6_bnYXl8X1zberi_V14ZWSU6GYr70tG26N8lY1qARrddkIZcG0LaD0oIBpb9AYoZngStaOt1a3Tra1kSvy8dB3H8PPGdNUDV3y2PduxDCnyhoAqRnY_0qQ0nAFlmX54UkpeKZWqAw_PQm5AS6MgOxX5Owfeh_mOOanqawGJWwplivyA_IxpBSxrfaxG1x8rDirliBUSxCqJQjVMQi55v2x8VwP2PytOP58Bu8OoEPEP8daaMPByF_XVLX0</recordid><startdate>20091101</startdate><enddate>20091101</enddate><creator>Khandoker, A.H.</creator><creator>Gubbi, J.</creator><creator>Palaniswami, M.</creator><general>IEEE</general><general>The Institute of Electrical and Electronics Engineers, Inc. (IEEE)</general><scope>97E</scope><scope>RIA</scope><scope>RIE</scope><scope>CGR</scope><scope>CUY</scope><scope>CVF</scope><scope>ECM</scope><scope>EIF</scope><scope>NPM</scope><scope>AAYXX</scope><scope>CITATION</scope><scope>7QF</scope><scope>7QO</scope><scope>7QQ</scope><scope>7SC</scope><scope>7SE</scope><scope>7SP</scope><scope>7SR</scope><scope>7TA</scope><scope>7TB</scope><scope>7U5</scope><scope>8BQ</scope><scope>8FD</scope><scope>F28</scope><scope>FR3</scope><scope>H8D</scope><scope>JG9</scope><scope>JQ2</scope><scope>K9.</scope><scope>KR7</scope><scope>L7M</scope><scope>L~C</scope><scope>L~D</scope><scope>NAPCQ</scope><scope>P64</scope><scope>7X8</scope></search><sort><creationdate>20091101</creationdate><title>Automated Scoring of Obstructive Sleep Apnea and Hypopnea Events Using Short-Term Electrocardiogram Recordings</title><author>Khandoker, A.H. ; Gubbi, J. ; Palaniswami, M.</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c443t-40cbc89d1864c84de420f59d24876ff7e3c74705c6e662502143ba1f85fa3fb63</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2009</creationdate><topic>Adult</topic><topic>Artificial intelligence</topic><topic>Breathing</topic><topic>ECG</topic><topic>Electrocardiography</topic><topic>Electrocardiography - methods</topic><topic>Electromyography</topic><topic>Electrooculography</topic><topic>Feedforward</topic><topic>Humans</topic><topic>Hypertension</topic><topic>Lungs</topic><topic>Middle Aged</topic><topic>Models, Biological</topic><topic>Monitoring, Physiologic - methods</topic><topic>Neural networks</topic><topic>Neural Networks (Computer)</topic><topic>neural networks (NNs)</topic><topic>obstructive sleep apnea (OSA)</topic><topic>Patients</topic><topic>Pattern Recognition, Automated - methods</topic><topic>Polysomnography - methods</topic><topic>Reproducibility of Results</topic><topic>ROC Curve</topic><topic>Sampling</topic><topic>Signal Processing, Computer-Assisted</topic><topic>Signal sampling</topic><topic>Sleep</topic><topic>Sleep apnea</topic><topic>Sleep Apnea, Obstructive - physiopathology</topic><topic>Sleep disorders</topic><topic>sleep study</topic><topic>Studies</topic><topic>Testing</topic><topic>Training</topic><topic>wavelet</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Khandoker, A.H.</creatorcontrib><creatorcontrib>Gubbi, J.</creatorcontrib><creatorcontrib>Palaniswami, M.</creatorcontrib><collection>IEEE All-Society Periodicals Package (ASPP) 2005-present</collection><collection>IEEE All-Society Periodicals Package (ASPP) 1998-Present</collection><collection>IEL</collection><collection>Medline</collection><collection>MEDLINE</collection><collection>MEDLINE (Ovid)</collection><collection>MEDLINE</collection><collection>MEDLINE</collection><collection>PubMed</collection><collection>CrossRef</collection><collection>Aluminium Industry Abstracts</collection><collection>Biotechnology Research Abstracts</collection><collection>Ceramic Abstracts</collection><collection>Computer and Information Systems Abstracts</collection><collection>Corrosion Abstracts</collection><collection>Electronics & Communications Abstracts</collection><collection>Engineered Materials Abstracts</collection><collection>Materials Business File</collection><collection>Mechanical & Transportation Engineering Abstracts</collection><collection>Solid State and Superconductivity Abstracts</collection><collection>METADEX</collection><collection>Technology Research Database</collection><collection>ANTE: Abstracts in New Technology & Engineering</collection><collection>Engineering Research Database</collection><collection>Aerospace Database</collection><collection>Materials Research Database</collection><collection>ProQuest Computer Science Collection</collection><collection>ProQuest Health & Medical Complete (Alumni)</collection><collection>Civil Engineering Abstracts</collection><collection>Advanced Technologies Database with Aerospace</collection><collection>Computer and Information Systems Abstracts Academic</collection><collection>Computer and Information Systems Abstracts Professional</collection><collection>Nursing & Allied Health Premium</collection><collection>Biotechnology and BioEngineering Abstracts</collection><collection>MEDLINE - Academic</collection><jtitle>IEEE journal of biomedical and health informatics</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Khandoker, A.H.</au><au>Gubbi, J.</au><au>Palaniswami, M.</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Automated Scoring of Obstructive Sleep Apnea and Hypopnea Events Using Short-Term Electrocardiogram Recordings</atitle><jtitle>IEEE journal of biomedical and health informatics</jtitle><stitle>TITB</stitle><addtitle>IEEE Trans Inf Technol Biomed</addtitle><date>2009-11-01</date><risdate>2009</risdate><volume>13</volume><issue>6</issue><spage>1057</spage><epage>1067</epage><pages>1057-1067</pages><issn>1089-7771</issn><issn>2168-2194</issn><eissn>1558-0032</eissn><eissn>2168-2208</eissn><coden>ITIBFX</coden><abstract>Obstructive sleep apnea or hypopnea causes a pause or reduction in airflow with continuous breathing effort. The aim of this study is to identify individual apnea and hypopnea events from normal breathing events using wavelet-based features of 5-s ECG signals (sampling rate = 250 Hz) and estimate the surrogate apnea index (AI)/hypopnea index (HI) (AHI). Total 82 535 ECG epochs (each of 5-s duration) from normal breathing during sleep, 1638 ECG epochs from 689 hypopnea events, and 3151 ECG epochs from 1862 apnea events were collected from 17 patients in the training set. Two-staged feedforward neural network model was trained using features from ECG signals with leave-one-patient-out cross-validation technique. At the first stage of classification, events (apnea and hypopnea) were classified from normal breathing events, and at the second stage, hypopneas were identified from apnea. Independent test was performed on 16 subjects' ECGs containing 483 hypopnea and 1352 apnea events. The cross-validation and independent test accuracies of apnea and hypopnea detection were found to be 94.84% and 76.82%, respectively, for training set, and 94.72% and 79.77%, respectively, for test set. The Bland-Altman plots showed unbiased estimations with standard deviations of plusmn 2.19, plusmn 2.16, and plusmn 3.64 events/h for AI, HI, and AHI, respectively. Results indicate the possibility of recognizing apnea/hypopnea events based on shorter segments of ECG signals.</abstract><cop>United States</cop><pub>IEEE</pub><pmid>19775974</pmid><doi>10.1109/TITB.2009.2031639</doi><tpages>11</tpages></addata></record> |
| fulltext | fulltext_linktorsrc |
| identifier | ISSN: 1089-7771 |
| ispartof | IEEE journal of biomedical and health informatics, 2009-11, Vol.13 (6), p.1057-1067 |
| issn | 1089-7771 2168-2194 1558-0032 2168-2208 |
| language | eng |
| recordid | cdi_proquest_miscellaneous_21336824 |
| source | IEL |
| subjects | Adult Artificial intelligence Breathing ECG Electrocardiography Electrocardiography - methods Electromyography Electrooculography Feedforward Humans Hypertension Lungs Middle Aged Models, Biological Monitoring, Physiologic - methods Neural networks Neural Networks (Computer) neural networks (NNs) obstructive sleep apnea (OSA) Patients Pattern Recognition, Automated - methods Polysomnography - methods Reproducibility of Results ROC Curve Sampling Signal Processing, Computer-Assisted Signal sampling Sleep Sleep apnea Sleep Apnea, Obstructive - physiopathology Sleep disorders sleep study Studies Testing Training wavelet |
| title | Automated Scoring of Obstructive Sleep Apnea and Hypopnea Events Using Short-Term Electrocardiogram Recordings |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-02-18T14%3A46%3A26IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_RIE&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Automated%20Scoring%20of%20Obstructive%20Sleep%20Apnea%20and%20Hypopnea%20Events%20Using%20Short-Term%20Electrocardiogram%20Recordings&rft.jtitle=IEEE%20journal%20of%20biomedical%20and%20health%20informatics&rft.au=Khandoker,%20A.H.&rft.date=2009-11-01&rft.volume=13&rft.issue=6&rft.spage=1057&rft.epage=1067&rft.pages=1057-1067&rft.issn=1089-7771&rft.eissn=1558-0032&rft.coden=ITIBFX&rft_id=info:doi/10.1109/TITB.2009.2031639&rft_dat=%3Cproquest_RIE%3E1671262713%3C/proquest_RIE%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=857428928&rft_id=info:pmid/19775974&rft_ieee_id=5256176&rfr_iscdi=true |