Automatic Detection of Atrial Fibrillation in Cardiac Vibration Signals

We present a study on the feasibility of the automatic detection of atrial fibrillation (AF) from cardiac vibration signals (ballistocardiograms/BCGs) recorded by unobtrusive bed-mounted sensors. The proposed system is intended as a screening and monitoring tool in home-healthcare applications and n...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:IEEE journal of biomedical and health informatics 2013-01, Vol.17 (1), p.162-171
Hauptverfasser: Bruser, C., Diesel, J., Zink, M. D. H., Winter, S., Schauerte, P., Leonhardt, S.
Format: Artikel
Sprache:eng
Schlagworte:
Online-Zugang:Volltext bestellen
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page 171
container_issue 1
container_start_page 162
container_title IEEE journal of biomedical and health informatics
container_volume 17
creator Bruser, C.
Diesel, J.
Zink, M. D. H.
Winter, S.
Schauerte, P.
Leonhardt, S.
description We present a study on the feasibility of the automatic detection of atrial fibrillation (AF) from cardiac vibration signals (ballistocardiograms/BCGs) recorded by unobtrusive bed-mounted sensors. The proposed system is intended as a screening and monitoring tool in home-healthcare applications and not as a replacement for ECG-based methods used in clinical environments. Based on the BCG data recorded in a study with ten AF patients, we evaluate and rank seven popular machine learning algorithms (naive Bayes, linear and quadratic discriminant analysis, support vector machines, random forests as well as bagged and boosted trees) for their performance in separating 30-s long BCG epochs into one of three classes: sinus rhythm, AF, and artifact. For each algorithm, feature subsets of a set of statistical time-frequency-domain and time-domain features were selected based on the mutual information between features and class labels as well as the first- and second-order interactions among features. The classifiers were evaluated on a set of 856 epochs by means of tenfold cross validation. The best algorithm (random forests) achieved a Matthews correlation coefficient, mean sensitivity, and mean specificity of 0.921, 0.938, and 0.982, respectively.
doi_str_mv 10.1109/TITB.2012.2225067
format Article
fullrecord <record><control><sourceid>proquest_RIE</sourceid><recordid>TN_cdi_ieee_primary_6331528</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ieee_id>6331528</ieee_id><sourcerecordid>1459977727</sourcerecordid><originalsourceid>FETCH-LOGICAL-c369t-26aa593d2cf1e3876032c6e1bab29a6a98eacf8bb98503e9655b717661cf7f703</originalsourceid><addsrcrecordid>eNo9kE9PAjEQxRujEYJ8AGNi9uhlsZ3Sf0dEQRISD6LXplu6pmaXxXb34Le3uMBcZvLmzcvkh9AtwRNCsHrcrDZPE8AEJgDAMBcXaAiEyxwAy8vTTNR0gMYxfuNUMkmKX6MBUCw5ozBEy1nXNrVpvc2eXets65td1pTZrA3eVNnCF8FXlfmX_S6bm7D1xmafSe_Fd_-1M1W8QVdlam587CP0sXjZzF_z9dtyNZ-tc0u5anPgxjBFt2BL4qgUHFOw3JHCFKAMN0o6Y0tZFEoyTJ3ijBWCCM6JLUUpMB2hhz53H5qfzsVW1z5al17cuaaLmkyZUkIIEMlKeqsNTYzBlXoffG3CryZYHxDqA0J9QKiPCNPN_TG-K2q3PV-cgCXDXW_wzrnzmlNKGEj6B6n3dBU</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>1459977727</pqid></control><display><type>article</type><title>Automatic Detection of Atrial Fibrillation in Cardiac Vibration Signals</title><source>IEEE Electronic Library (IEL)</source><creator>Bruser, C. ; Diesel, J. ; Zink, M. D. H. ; Winter, S. ; Schauerte, P. ; Leonhardt, S.</creator><creatorcontrib>Bruser, C. ; Diesel, J. ; Zink, M. D. H. ; Winter, S. ; Schauerte, P. ; Leonhardt, S.</creatorcontrib><description>We present a study on the feasibility of the automatic detection of atrial fibrillation (AF) from cardiac vibration signals (ballistocardiograms/BCGs) recorded by unobtrusive bed-mounted sensors. The proposed system is intended as a screening and monitoring tool in home-healthcare applications and not as a replacement for ECG-based methods used in clinical environments. Based on the BCG data recorded in a study with ten AF patients, we evaluate and rank seven popular machine learning algorithms (naive Bayes, linear and quadratic discriminant analysis, support vector machines, random forests as well as bagged and boosted trees) for their performance in separating 30-s long BCG epochs into one of three classes: sinus rhythm, AF, and artifact. For each algorithm, feature subsets of a set of statistical time-frequency-domain and time-domain features were selected based on the mutual information between features and class labels as well as the first- and second-order interactions among features. The classifiers were evaluated on a set of 856 epochs by means of tenfold cross validation. The best algorithm (random forests) achieved a Matthews correlation coefficient, mean sensitivity, and mean specificity of 0.921, 0.938, and 0.982, respectively.</description><identifier>ISSN: 2168-2194</identifier><identifier>EISSN: 2168-2208</identifier><identifier>DOI: 10.1109/TITB.2012.2225067</identifier><identifier>PMID: 23086532</identifier><identifier>CODEN: IJBHA9</identifier><language>eng</language><publisher>United States: IEEE</publisher><subject>Aged ; Aged, 80 and over ; Algorithms ; Atrial fibrillation (AF) ; Atrial Fibrillation - diagnosis ; Atrial Fibrillation - physiopathology ; ballistocardiography (BCG) ; Ballistocardiography - methods ; Bayes Theorem ; classification ; Electrocardiography ; Female ; Humans ; Male ; Middle Aged ; Monitoring ; Reproducibility of Results ; Rhythm ; Sensors ; Signal Processing, Computer-Assisted ; Spectrogram ; Vibrations</subject><ispartof>IEEE journal of biomedical and health informatics, 2013-01, Vol.17 (1), p.162-171</ispartof><lds50>peer_reviewed</lds50><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c369t-26aa593d2cf1e3876032c6e1bab29a6a98eacf8bb98503e9655b717661cf7f703</citedby><cites>FETCH-LOGICAL-c369t-26aa593d2cf1e3876032c6e1bab29a6a98eacf8bb98503e9655b717661cf7f703</cites></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://ieeexplore.ieee.org/document/6331528$$EHTML$$P50$$Gieee$$H</linktohtml><link.rule.ids>314,780,784,796,27924,27925,54758</link.rule.ids><linktorsrc>$$Uhttps://ieeexplore.ieee.org/document/6331528$$EView_record_in_IEEE$$FView_record_in_$$GIEEE</linktorsrc><backlink>$$Uhttps://www.ncbi.nlm.nih.gov/pubmed/23086532$$D View this record in MEDLINE/PubMed$$Hfree_for_read</backlink></links><search><creatorcontrib>Bruser, C.</creatorcontrib><creatorcontrib>Diesel, J.</creatorcontrib><creatorcontrib>Zink, M. D. H.</creatorcontrib><creatorcontrib>Winter, S.</creatorcontrib><creatorcontrib>Schauerte, P.</creatorcontrib><creatorcontrib>Leonhardt, S.</creatorcontrib><title>Automatic Detection of Atrial Fibrillation in Cardiac Vibration Signals</title><title>IEEE journal of biomedical and health informatics</title><addtitle>JBHI</addtitle><addtitle>IEEE J Biomed Health Inform</addtitle><description>We present a study on the feasibility of the automatic detection of atrial fibrillation (AF) from cardiac vibration signals (ballistocardiograms/BCGs) recorded by unobtrusive bed-mounted sensors. The proposed system is intended as a screening and monitoring tool in home-healthcare applications and not as a replacement for ECG-based methods used in clinical environments. Based on the BCG data recorded in a study with ten AF patients, we evaluate and rank seven popular machine learning algorithms (naive Bayes, linear and quadratic discriminant analysis, support vector machines, random forests as well as bagged and boosted trees) for their performance in separating 30-s long BCG epochs into one of three classes: sinus rhythm, AF, and artifact. For each algorithm, feature subsets of a set of statistical time-frequency-domain and time-domain features were selected based on the mutual information between features and class labels as well as the first- and second-order interactions among features. The classifiers were evaluated on a set of 856 epochs by means of tenfold cross validation. The best algorithm (random forests) achieved a Matthews correlation coefficient, mean sensitivity, and mean specificity of 0.921, 0.938, and 0.982, respectively.</description><subject>Aged</subject><subject>Aged, 80 and over</subject><subject>Algorithms</subject><subject>Atrial fibrillation (AF)</subject><subject>Atrial Fibrillation - diagnosis</subject><subject>Atrial Fibrillation - physiopathology</subject><subject>ballistocardiography (BCG)</subject><subject>Ballistocardiography - methods</subject><subject>Bayes Theorem</subject><subject>classification</subject><subject>Electrocardiography</subject><subject>Female</subject><subject>Humans</subject><subject>Male</subject><subject>Middle Aged</subject><subject>Monitoring</subject><subject>Reproducibility of Results</subject><subject>Rhythm</subject><subject>Sensors</subject><subject>Signal Processing, Computer-Assisted</subject><subject>Spectrogram</subject><subject>Vibrations</subject><issn>2168-2194</issn><issn>2168-2208</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2013</creationdate><recordtype>article</recordtype><sourceid>RIE</sourceid><sourceid>EIF</sourceid><recordid>eNo9kE9PAjEQxRujEYJ8AGNi9uhlsZ3Sf0dEQRISD6LXplu6pmaXxXb34Le3uMBcZvLmzcvkh9AtwRNCsHrcrDZPE8AEJgDAMBcXaAiEyxwAy8vTTNR0gMYxfuNUMkmKX6MBUCw5ozBEy1nXNrVpvc2eXets65td1pTZrA3eVNnCF8FXlfmX_S6bm7D1xmafSe_Fd_-1M1W8QVdlam587CP0sXjZzF_z9dtyNZ-tc0u5anPgxjBFt2BL4qgUHFOw3JHCFKAMN0o6Y0tZFEoyTJ3ijBWCCM6JLUUpMB2hhz53H5qfzsVW1z5al17cuaaLmkyZUkIIEMlKeqsNTYzBlXoffG3CryZYHxDqA0J9QKiPCNPN_TG-K2q3PV-cgCXDXW_wzrnzmlNKGEj6B6n3dBU</recordid><startdate>201301</startdate><enddate>201301</enddate><creator>Bruser, C.</creator><creator>Diesel, J.</creator><creator>Zink, M. D. H.</creator><creator>Winter, S.</creator><creator>Schauerte, P.</creator><creator>Leonhardt, S.</creator><general>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>7X8</scope></search><sort><creationdate>201301</creationdate><title>Automatic Detection of Atrial Fibrillation in Cardiac Vibration Signals</title><author>Bruser, C. ; Diesel, J. ; Zink, M. D. H. ; Winter, S. ; Schauerte, P. ; Leonhardt, S.</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c369t-26aa593d2cf1e3876032c6e1bab29a6a98eacf8bb98503e9655b717661cf7f703</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2013</creationdate><topic>Aged</topic><topic>Aged, 80 and over</topic><topic>Algorithms</topic><topic>Atrial fibrillation (AF)</topic><topic>Atrial Fibrillation - diagnosis</topic><topic>Atrial Fibrillation - physiopathology</topic><topic>ballistocardiography (BCG)</topic><topic>Ballistocardiography - methods</topic><topic>Bayes Theorem</topic><topic>classification</topic><topic>Electrocardiography</topic><topic>Female</topic><topic>Humans</topic><topic>Male</topic><topic>Middle Aged</topic><topic>Monitoring</topic><topic>Reproducibility of Results</topic><topic>Rhythm</topic><topic>Sensors</topic><topic>Signal Processing, Computer-Assisted</topic><topic>Spectrogram</topic><topic>Vibrations</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Bruser, C.</creatorcontrib><creatorcontrib>Diesel, J.</creatorcontrib><creatorcontrib>Zink, M. D. H.</creatorcontrib><creatorcontrib>Winter, S.</creatorcontrib><creatorcontrib>Schauerte, P.</creatorcontrib><creatorcontrib>Leonhardt, S.</creatorcontrib><collection>IEEE All-Society Periodicals Package (ASPP) 2005-present</collection><collection>IEEE All-Society Periodicals Package (ASPP) 1998-Present</collection><collection>IEEE Electronic Library (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>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>Bruser, C.</au><au>Diesel, J.</au><au>Zink, M. D. H.</au><au>Winter, S.</au><au>Schauerte, P.</au><au>Leonhardt, S.</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Automatic Detection of Atrial Fibrillation in Cardiac Vibration Signals</atitle><jtitle>IEEE journal of biomedical and health informatics</jtitle><stitle>JBHI</stitle><addtitle>IEEE J Biomed Health Inform</addtitle><date>2013-01</date><risdate>2013</risdate><volume>17</volume><issue>1</issue><spage>162</spage><epage>171</epage><pages>162-171</pages><issn>2168-2194</issn><eissn>2168-2208</eissn><coden>IJBHA9</coden><abstract>We present a study on the feasibility of the automatic detection of atrial fibrillation (AF) from cardiac vibration signals (ballistocardiograms/BCGs) recorded by unobtrusive bed-mounted sensors. The proposed system is intended as a screening and monitoring tool in home-healthcare applications and not as a replacement for ECG-based methods used in clinical environments. Based on the BCG data recorded in a study with ten AF patients, we evaluate and rank seven popular machine learning algorithms (naive Bayes, linear and quadratic discriminant analysis, support vector machines, random forests as well as bagged and boosted trees) for their performance in separating 30-s long BCG epochs into one of three classes: sinus rhythm, AF, and artifact. For each algorithm, feature subsets of a set of statistical time-frequency-domain and time-domain features were selected based on the mutual information between features and class labels as well as the first- and second-order interactions among features. The classifiers were evaluated on a set of 856 epochs by means of tenfold cross validation. The best algorithm (random forests) achieved a Matthews correlation coefficient, mean sensitivity, and mean specificity of 0.921, 0.938, and 0.982, respectively.</abstract><cop>United States</cop><pub>IEEE</pub><pmid>23086532</pmid><doi>10.1109/TITB.2012.2225067</doi><tpages>10</tpages></addata></record>
fulltext fulltext_linktorsrc
identifier ISSN: 2168-2194
ispartof IEEE journal of biomedical and health informatics, 2013-01, Vol.17 (1), p.162-171
issn 2168-2194
2168-2208
language eng
recordid cdi_ieee_primary_6331528
source IEEE Electronic Library (IEL)
subjects Aged
Aged, 80 and over
Algorithms
Atrial fibrillation (AF)
Atrial Fibrillation - diagnosis
Atrial Fibrillation - physiopathology
ballistocardiography (BCG)
Ballistocardiography - methods
Bayes Theorem
classification
Electrocardiography
Female
Humans
Male
Middle Aged
Monitoring
Reproducibility of Results
Rhythm
Sensors
Signal Processing, Computer-Assisted
Spectrogram
Vibrations
title Automatic Detection of Atrial Fibrillation in Cardiac Vibration Signals
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-24T09%3A57%3A39IST&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=Automatic%20Detection%20of%20Atrial%20Fibrillation%20in%20Cardiac%20Vibration%20Signals&rft.jtitle=IEEE%20journal%20of%20biomedical%20and%20health%20informatics&rft.au=Bruser,%20C.&rft.date=2013-01&rft.volume=17&rft.issue=1&rft.spage=162&rft.epage=171&rft.pages=162-171&rft.issn=2168-2194&rft.eissn=2168-2208&rft.coden=IJBHA9&rft_id=info:doi/10.1109/TITB.2012.2225067&rft_dat=%3Cproquest_RIE%3E1459977727%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=1459977727&rft_id=info:pmid/23086532&rft_ieee_id=6331528&rfr_iscdi=true