Support-vector classification of low-dose nitrous oxide administration with multi-channel EEG power spectra
Support-vector machines (SVMs) can potentially improve patient monitoring during nitrous oxide anaesthesia. By elucidating the effects of low-dose nitrous oxide on the power spectra of multi-channel EEG recordings, we quantified the degree to which these effects generalise across participants. In th...
Gespeichert in:
| Veröffentlicht in: | Journal of clinical monitoring and computing 2024-04, Vol.38 (2), p.363-371 |
|---|---|
| Hauptverfasser: | , , , , , |
| Format: | Artikel |
| Sprache: | eng |
| Schlagworte: | |
| Online-Zugang: | Volltext |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| container_end_page | 371 |
|---|---|
| container_issue | 2 |
| container_start_page | 363 |
| container_title | Journal of clinical monitoring and computing |
| container_volume | 38 |
| creator | Vrijdag, Xavier C. E. Hallum, Luke E. Tonks, Emma I. van Waart, Hanna Mitchell, Simon J. Sleigh, Jamie W. |
| description | Support-vector machines (SVMs) can potentially improve patient monitoring during nitrous oxide anaesthesia. By elucidating the effects of low-dose nitrous oxide on the power spectra of multi-channel EEG recordings, we quantified the degree to which these effects generalise across participants. In this single-blind, cross-over study, 32-channel EEG was recorded from 12 healthy participants exposed to 0, 20, 30 and 40% end-tidal nitrous oxide. Features of the delta-, theta-, alpha- and beta-band power were used within a 12-fold, participant-wise cross-validation framework to train and test two SVMs: (1) binary SVM classifying EEG during 0 or 40% exposure (chance = 50%); (2) multi-class SVM classifying EEG during 0, 20, 30 or 40% exposure (chance = 25%). Both the binary (accuracy 92%) and the multi-class (accuracy 52%) SVMs classified EEG recordings at rates significantly better than chance (p |
| doi_str_mv | 10.1007/s10877-023-01054-w |
| format | Article |
| fullrecord | <record><control><sourceid>proquest_cross</sourceid><recordid>TN_cdi_proquest_miscellaneous_2836874603</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2836874603</sourcerecordid><originalsourceid>FETCH-LOGICAL-c370t-59c975b379108e2c787f2527fa6bf9470f5cc8a8c73b460691ca0719e67513e93</originalsourceid><addsrcrecordid>eNp9kc1u3SAQhVHVqvnrC3RRIXXTDelgbA8sq-g2iRSpiyRrxOXihtQ2LuA4ffuQOE2lLrIapPnOgcMh5COHYw6AXxMHicigEgw4NDVb3pB93qBgVcvrt-UsJDIuAPfIQUq3AKCk4O_JnsC6Bs5xn_y6nKcpxMzunM0hUtublHznrck-jDR0tA8L24Xk6OhzDHOi4d7vHDW7wY8-5biCi883dJj77Jm9MePoerrZnNIpLC7SNBXzaI7Iu870yX14nofk-vvm6uSMXfw4PT_5dsGsQMisUVZhsxWoSj5XWZTYVU2FnWm3naoRusZaaaRFsa1baBW3BpAr12LDhVPikHxZfacYfs8uZT34ZF3fm9GVALqSopVYpKKgn_9Db8Mcx_I6LUBUshZS8UJVK2VjSCm6Tk_RDyb-0Rz0YxV6rUKXKvRTFXopok_P1vN2cLsXyd-_L4BYgVRW408X_939iu0DJTaVCw</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>3032843891</pqid></control><display><type>article</type><title>Support-vector classification of low-dose nitrous oxide administration with multi-channel EEG power spectra</title><source>SpringerLink Journals - AutoHoldings</source><creator>Vrijdag, Xavier C. E. ; Hallum, Luke E. ; Tonks, Emma I. ; van Waart, Hanna ; Mitchell, Simon J. ; Sleigh, Jamie W.</creator><creatorcontrib>Vrijdag, Xavier C. E. ; Hallum, Luke E. ; Tonks, Emma I. ; van Waart, Hanna ; Mitchell, Simon J. ; Sleigh, Jamie W.</creatorcontrib><description>Support-vector machines (SVMs) can potentially improve patient monitoring during nitrous oxide anaesthesia. By elucidating the effects of low-dose nitrous oxide on the power spectra of multi-channel EEG recordings, we quantified the degree to which these effects generalise across participants. In this single-blind, cross-over study, 32-channel EEG was recorded from 12 healthy participants exposed to 0, 20, 30 and 40% end-tidal nitrous oxide. Features of the delta-, theta-, alpha- and beta-band power were used within a 12-fold, participant-wise cross-validation framework to train and test two SVMs: (1) binary SVM classifying EEG during 0 or 40% exposure (chance = 50%); (2) multi-class SVM classifying EEG during 0, 20, 30 or 40% exposure (chance = 25%). Both the binary (accuracy 92%) and the multi-class (accuracy 52%) SVMs classified EEG recordings at rates significantly better than chance (p < 0.001 and p = 0.01, respectively). To determine the relative importance of frequency band features for classification accuracy, we systematically removed features before re-training and re-testing the SVMs. This showed the relative importance of decreased delta power and the frontal region. SVM classification identified that the most important effects of nitrous oxide were found in the delta band in the frontal electrodes that was consistent between participants. Furthermore, support-vector classification of nitrous oxide dosage is a promising method that might be used to improve patient monitoring during nitrous oxide anaesthesia.</description><identifier>ISSN: 1387-1307</identifier><identifier>EISSN: 1573-2614</identifier><identifier>DOI: 10.1007/s10877-023-01054-w</identifier><identifier>PMID: 37440117</identifier><language>eng</language><publisher>Dordrecht: Springer Netherlands</publisher><subject>Accuracy ; Anesthesia ; Anesthesiology ; Classification ; Critical Care Medicine ; Exposure ; Frequencies ; Health Sciences ; Intensive ; Medicine ; Medicine & Public Health ; Monitoring ; Nitrous oxide ; Original Research ; Power spectra ; Statistics for Life Sciences ; Support vector machines</subject><ispartof>Journal of clinical monitoring and computing, 2024-04, Vol.38 (2), p.363-371</ispartof><rights>The Author(s) 2023</rights><rights>2023. The Author(s).</rights><rights>The Author(s) 2023. This work is published under http://creativecommons.org/licenses/by/4.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.</rights><lds50>peer_reviewed</lds50><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed><cites>FETCH-LOGICAL-c370t-59c975b379108e2c787f2527fa6bf9470f5cc8a8c73b460691ca0719e67513e93</cites><orcidid>0000-0002-5149-6371 ; 0000-0002-8184-1703 ; 0000-0001-5907-6083 ; 0000-0002-6931-0168 ; 0000-0002-1966-5825</orcidid></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktopdf>$$Uhttps://link.springer.com/content/pdf/10.1007/s10877-023-01054-w$$EPDF$$P50$$Gspringer$$Hfree_for_read</linktopdf><linktohtml>$$Uhttps://link.springer.com/10.1007/s10877-023-01054-w$$EHTML$$P50$$Gspringer$$Hfree_for_read</linktohtml><link.rule.ids>314,776,780,27903,27904,41467,42536,51297</link.rule.ids><backlink>$$Uhttps://www.ncbi.nlm.nih.gov/pubmed/37440117$$D View this record in MEDLINE/PubMed$$Hfree_for_read</backlink></links><search><creatorcontrib>Vrijdag, Xavier C. E.</creatorcontrib><creatorcontrib>Hallum, Luke E.</creatorcontrib><creatorcontrib>Tonks, Emma I.</creatorcontrib><creatorcontrib>van Waart, Hanna</creatorcontrib><creatorcontrib>Mitchell, Simon J.</creatorcontrib><creatorcontrib>Sleigh, Jamie W.</creatorcontrib><title>Support-vector classification of low-dose nitrous oxide administration with multi-channel EEG power spectra</title><title>Journal of clinical monitoring and computing</title><addtitle>J Clin Monit Comput</addtitle><addtitle>J Clin Monit Comput</addtitle><description>Support-vector machines (SVMs) can potentially improve patient monitoring during nitrous oxide anaesthesia. By elucidating the effects of low-dose nitrous oxide on the power spectra of multi-channel EEG recordings, we quantified the degree to which these effects generalise across participants. In this single-blind, cross-over study, 32-channel EEG was recorded from 12 healthy participants exposed to 0, 20, 30 and 40% end-tidal nitrous oxide. Features of the delta-, theta-, alpha- and beta-band power were used within a 12-fold, participant-wise cross-validation framework to train and test two SVMs: (1) binary SVM classifying EEG during 0 or 40% exposure (chance = 50%); (2) multi-class SVM classifying EEG during 0, 20, 30 or 40% exposure (chance = 25%). Both the binary (accuracy 92%) and the multi-class (accuracy 52%) SVMs classified EEG recordings at rates significantly better than chance (p < 0.001 and p = 0.01, respectively). To determine the relative importance of frequency band features for classification accuracy, we systematically removed features before re-training and re-testing the SVMs. This showed the relative importance of decreased delta power and the frontal region. SVM classification identified that the most important effects of nitrous oxide were found in the delta band in the frontal electrodes that was consistent between participants. Furthermore, support-vector classification of nitrous oxide dosage is a promising method that might be used to improve patient monitoring during nitrous oxide anaesthesia.</description><subject>Accuracy</subject><subject>Anesthesia</subject><subject>Anesthesiology</subject><subject>Classification</subject><subject>Critical Care Medicine</subject><subject>Exposure</subject><subject>Frequencies</subject><subject>Health Sciences</subject><subject>Intensive</subject><subject>Medicine</subject><subject>Medicine & Public Health</subject><subject>Monitoring</subject><subject>Nitrous oxide</subject><subject>Original Research</subject><subject>Power spectra</subject><subject>Statistics for Life Sciences</subject><subject>Support vector machines</subject><issn>1387-1307</issn><issn>1573-2614</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2024</creationdate><recordtype>article</recordtype><sourceid>C6C</sourceid><recordid>eNp9kc1u3SAQhVHVqvnrC3RRIXXTDelgbA8sq-g2iRSpiyRrxOXihtQ2LuA4ffuQOE2lLrIapPnOgcMh5COHYw6AXxMHicigEgw4NDVb3pB93qBgVcvrt-UsJDIuAPfIQUq3AKCk4O_JnsC6Bs5xn_y6nKcpxMzunM0hUtublHznrck-jDR0tA8L24Xk6OhzDHOi4d7vHDW7wY8-5biCi883dJj77Jm9MePoerrZnNIpLC7SNBXzaI7Iu870yX14nofk-vvm6uSMXfw4PT_5dsGsQMisUVZhsxWoSj5XWZTYVU2FnWm3naoRusZaaaRFsa1baBW3BpAr12LDhVPikHxZfacYfs8uZT34ZF3fm9GVALqSopVYpKKgn_9Db8Mcx_I6LUBUshZS8UJVK2VjSCm6Tk_RDyb-0Rz0YxV6rUKXKvRTFXopok_P1vN2cLsXyd-_L4BYgVRW408X_939iu0DJTaVCw</recordid><startdate>20240401</startdate><enddate>20240401</enddate><creator>Vrijdag, Xavier C. E.</creator><creator>Hallum, Luke E.</creator><creator>Tonks, Emma I.</creator><creator>van Waart, Hanna</creator><creator>Mitchell, Simon J.</creator><creator>Sleigh, Jamie W.</creator><general>Springer Netherlands</general><general>Springer Nature B.V</general><scope>C6C</scope><scope>NPM</scope><scope>AAYXX</scope><scope>CITATION</scope><scope>7SC</scope><scope>7SP</scope><scope>7U5</scope><scope>8FD</scope><scope>JQ2</scope><scope>K9.</scope><scope>L7M</scope><scope>L~C</scope><scope>L~D</scope><scope>NAPCQ</scope><scope>7X8</scope><orcidid>https://orcid.org/0000-0002-5149-6371</orcidid><orcidid>https://orcid.org/0000-0002-8184-1703</orcidid><orcidid>https://orcid.org/0000-0001-5907-6083</orcidid><orcidid>https://orcid.org/0000-0002-6931-0168</orcidid><orcidid>https://orcid.org/0000-0002-1966-5825</orcidid></search><sort><creationdate>20240401</creationdate><title>Support-vector classification of low-dose nitrous oxide administration with multi-channel EEG power spectra</title><author>Vrijdag, Xavier C. E. ; Hallum, Luke E. ; Tonks, Emma I. ; van Waart, Hanna ; Mitchell, Simon J. ; Sleigh, Jamie W.</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c370t-59c975b379108e2c787f2527fa6bf9470f5cc8a8c73b460691ca0719e67513e93</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2024</creationdate><topic>Accuracy</topic><topic>Anesthesia</topic><topic>Anesthesiology</topic><topic>Classification</topic><topic>Critical Care Medicine</topic><topic>Exposure</topic><topic>Frequencies</topic><topic>Health Sciences</topic><topic>Intensive</topic><topic>Medicine</topic><topic>Medicine & Public Health</topic><topic>Monitoring</topic><topic>Nitrous oxide</topic><topic>Original Research</topic><topic>Power spectra</topic><topic>Statistics for Life Sciences</topic><topic>Support vector machines</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Vrijdag, Xavier C. E.</creatorcontrib><creatorcontrib>Hallum, Luke E.</creatorcontrib><creatorcontrib>Tonks, Emma I.</creatorcontrib><creatorcontrib>van Waart, Hanna</creatorcontrib><creatorcontrib>Mitchell, Simon J.</creatorcontrib><creatorcontrib>Sleigh, Jamie W.</creatorcontrib><collection>Springer Nature OA Free Journals</collection><collection>PubMed</collection><collection>CrossRef</collection><collection>Computer and Information Systems Abstracts</collection><collection>Electronics & Communications Abstracts</collection><collection>Solid State and Superconductivity Abstracts</collection><collection>Technology Research Database</collection><collection>ProQuest Computer Science Collection</collection><collection>ProQuest Health & Medical Complete (Alumni)</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>MEDLINE - Academic</collection><jtitle>Journal of clinical monitoring and computing</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Vrijdag, Xavier C. E.</au><au>Hallum, Luke E.</au><au>Tonks, Emma I.</au><au>van Waart, Hanna</au><au>Mitchell, Simon J.</au><au>Sleigh, Jamie W.</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Support-vector classification of low-dose nitrous oxide administration with multi-channel EEG power spectra</atitle><jtitle>Journal of clinical monitoring and computing</jtitle><stitle>J Clin Monit Comput</stitle><addtitle>J Clin Monit Comput</addtitle><date>2024-04-01</date><risdate>2024</risdate><volume>38</volume><issue>2</issue><spage>363</spage><epage>371</epage><pages>363-371</pages><issn>1387-1307</issn><eissn>1573-2614</eissn><abstract>Support-vector machines (SVMs) can potentially improve patient monitoring during nitrous oxide anaesthesia. By elucidating the effects of low-dose nitrous oxide on the power spectra of multi-channel EEG recordings, we quantified the degree to which these effects generalise across participants. In this single-blind, cross-over study, 32-channel EEG was recorded from 12 healthy participants exposed to 0, 20, 30 and 40% end-tidal nitrous oxide. Features of the delta-, theta-, alpha- and beta-band power were used within a 12-fold, participant-wise cross-validation framework to train and test two SVMs: (1) binary SVM classifying EEG during 0 or 40% exposure (chance = 50%); (2) multi-class SVM classifying EEG during 0, 20, 30 or 40% exposure (chance = 25%). Both the binary (accuracy 92%) and the multi-class (accuracy 52%) SVMs classified EEG recordings at rates significantly better than chance (p < 0.001 and p = 0.01, respectively). To determine the relative importance of frequency band features for classification accuracy, we systematically removed features before re-training and re-testing the SVMs. This showed the relative importance of decreased delta power and the frontal region. SVM classification identified that the most important effects of nitrous oxide were found in the delta band in the frontal electrodes that was consistent between participants. Furthermore, support-vector classification of nitrous oxide dosage is a promising method that might be used to improve patient monitoring during nitrous oxide anaesthesia.</abstract><cop>Dordrecht</cop><pub>Springer Netherlands</pub><pmid>37440117</pmid><doi>10.1007/s10877-023-01054-w</doi><tpages>9</tpages><orcidid>https://orcid.org/0000-0002-5149-6371</orcidid><orcidid>https://orcid.org/0000-0002-8184-1703</orcidid><orcidid>https://orcid.org/0000-0001-5907-6083</orcidid><orcidid>https://orcid.org/0000-0002-6931-0168</orcidid><orcidid>https://orcid.org/0000-0002-1966-5825</orcidid><oa>free_for_read</oa></addata></record> |
| fulltext | fulltext |
| identifier | ISSN: 1387-1307 |
| ispartof | Journal of clinical monitoring and computing, 2024-04, Vol.38 (2), p.363-371 |
| issn | 1387-1307 1573-2614 |
| language | eng |
| recordid | cdi_proquest_miscellaneous_2836874603 |
| source | SpringerLink Journals - AutoHoldings |
| subjects | Accuracy Anesthesia Anesthesiology Classification Critical Care Medicine Exposure Frequencies Health Sciences Intensive Medicine Medicine & Public Health Monitoring Nitrous oxide Original Research Power spectra Statistics for Life Sciences Support vector machines |
| title | Support-vector classification of low-dose nitrous oxide administration with multi-channel EEG power spectra |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-26T00%3A09%3A59IST&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=Support-vector%20classification%20of%20low-dose%20nitrous%20oxide%20administration%20with%20multi-channel%20EEG%20power%20spectra&rft.jtitle=Journal%20of%20clinical%20monitoring%20and%20computing&rft.au=Vrijdag,%20Xavier%20C.%20E.&rft.date=2024-04-01&rft.volume=38&rft.issue=2&rft.spage=363&rft.epage=371&rft.pages=363-371&rft.issn=1387-1307&rft.eissn=1573-2614&rft_id=info:doi/10.1007/s10877-023-01054-w&rft_dat=%3Cproquest_cross%3E2836874603%3C/proquest_cross%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=3032843891&rft_id=info:pmid/37440117&rfr_iscdi=true |