Machine Learning Models with Preoperative Risk Factors and Intraoperative Hypotension Parameters Predict Mortality After Cardiac Surgery
Objectives: Machine learning models used to predict postoperative mortality rarely include intraoperative factors. Several intraoperative factors like hypotension (IOH), vasopressor-inotropes, and cardiopulmonary bypass (CPB) time are significantly associated with postoperative outcomes. The authors...
Gespeichert in:
| Veröffentlicht in: | Journal of cardiothoracic and vascular anesthesia 2021-03, Vol.35 (3), p.857-865 |
|---|---|
| Hauptverfasser: | , , , |
| Format: | Artikel |
| Sprache: | eng |
| Schlagworte: | |
| Online-Zugang: | Volltext |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| container_end_page | 865 |
|---|---|
| container_issue | 3 |
| container_start_page | 857 |
| container_title | Journal of cardiothoracic and vascular anesthesia |
| container_volume | 35 |
| creator | Fernandes, Marta Priscila Bento Armengol de la Hoz, Miguel Rangasamy, Valluvan Subramaniam, Balachundhar |
| description | Objectives: Machine learning models used to predict postoperative mortality rarely include intraoperative factors. Several intraoperative factors like hypotension (IOH), vasopressor-inotropes, and cardiopulmonary bypass (CPB) time are significantly associated with postoperative outcomes. The authors explored the ability of machine learning models incorporating intraoperative risk factors to predict mortality after cardiac surgery.
Design: Retrospective study.
Setting: Tertiary hospital.
Participants: A total of 5,015 adults who underwent cardiac surgery from 2008 to 2016.
Intervention: None.
Measurements and Main Results: The intraoperative phase was divided into the following: (1) CPB, (2) outside CPB, and (3) total surgery for quantifying IOH only. Phase-specific IOH parameters (area under the curve for mean arterial pressure |
| doi_str_mv | 10.1053/j.jvca.2020.07.029 |
| format | Article |
| fullrecord | <record><control><sourceid>proquest_cross</sourceid><recordid>TN_cdi_proquest_miscellaneous_2430369806</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><els_id>S1053077020306595</els_id><sourcerecordid>2430369806</sourcerecordid><originalsourceid>FETCH-LOGICAL-c356t-8d13cce7c8ff1fe345657c655624ec78e93037b2ce8f0ae5aa6cb682b402ebce3</originalsourceid><addsrcrecordid>eNp9kU1vEzEQhi0EoqXwBzggH7ns4rXX643EpYoorZSKio-zNTs72zps7GA7QfkH_GwcpcCN04w0zzyH92XsdSPqRmj1bl2v9wi1FFLUwtRCLp6w80YrWfWtlE_LXqhKGCPO2IuU1kI0jdbmOTtT0rRGCnXOft0CPjhPfEUQvfP3_DaMNCf-0-UHfhcpbClCdnvin136zq8Ac4iJgx_5jc8R_t2vD9uQyScXPL-DCBvKVMjiGB3m4o0ZZpcP_HIqB76EODpA_mUX7ykeXrJnE8yJXj3OC_bt6sPX5XW1-vTxZnm5qlDpLlf92ChEMthPUzORanWnDXZad7IlND0tlFBmkEj9JIA0QIdD18uhFZIGJHXB3p682xh-7Chlu3EJaZ7BU9glK9si6Ba96AoqTyjGkFKkyW6j20A82EbYY7Z2bY8N2GMDVhhbGihPbx79u2FD49-XP5EX4P0JKCnT3lG0CR15LClFwmzH4P7n_w3hc5qo</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2430369806</pqid></control><display><type>article</type><title>Machine Learning Models with Preoperative Risk Factors and Intraoperative Hypotension Parameters Predict Mortality After Cardiac Surgery</title><source>Elsevier ScienceDirect Journals</source><creator>Fernandes, Marta Priscila Bento ; Armengol de la Hoz, Miguel ; Rangasamy, Valluvan ; Subramaniam, Balachundhar</creator><creatorcontrib>Fernandes, Marta Priscila Bento ; Armengol de la Hoz, Miguel ; Rangasamy, Valluvan ; Subramaniam, Balachundhar</creatorcontrib><description>Objectives: Machine learning models used to predict postoperative mortality rarely include intraoperative factors. Several intraoperative factors like hypotension (IOH), vasopressor-inotropes, and cardiopulmonary bypass (CPB) time are significantly associated with postoperative outcomes. The authors explored the ability of machine learning models incorporating intraoperative risk factors to predict mortality after cardiac surgery.
Design: Retrospective study.
Setting: Tertiary hospital.
Participants: A total of 5,015 adults who underwent cardiac surgery from 2008 to 2016.
Intervention: None.
Measurements and Main Results: The intraoperative phase was divided into the following: (1) CPB, (2) outside CPB, and (3) total surgery for quantifying IOH only. Phase-specific IOH parameters (area under the curve for mean arterial pressure <65 mmHg), vasopressor-inotropes (norepinephrine equivalents), duration, and cross-clamp time, along with preoperative risk factors ,were incorporated into the models. The primary outcome was mortality. The following 5 models were applied to 3 intraoperative phases separately: (1) logistic regression, (2) random forests, (3) neural networks, (4) support vector machines, and (5) extreme gradient boosting (XGB). Mortality was predicted using area under the receiver operating characteristic curve. Of 5,015 patients included, 112 (2.2%) died. XGB model from the outside-CPB phase predicted mortality better with area under the receiver operating characteristic curve, 95% confidence interval (CI): 0.88(0.83-0.94); positive predictive value, 0.10(0.06-0.15); specificity 0.85 (0.83-0.87) and sensitivity 0.75 (0.57-0.90).
Conclusion: XGB machine learning model from IOH outside the CPB phase seemed to offer a better discrimination, sensitivity, specificity, and positive predictive value compared with other models. Machine learning models incorporating intraoperative adverse factors might offer better predictive ability for risk stratification and triaging of patients after cardiac surgery.</description><identifier>ISSN: 1053-0770</identifier><identifier>EISSN: 1532-8422</identifier><identifier>DOI: 10.1053/j.jvca.2020.07.029</identifier><identifier>PMID: 32747203</identifier><language>eng</language><publisher>United States: Elsevier Inc</publisher><subject>cardiac surgery ; intraoperative adverse factors ; intraoperative hypotension ; Machine learning ; mortality prediction</subject><ispartof>Journal of cardiothoracic and vascular anesthesia, 2021-03, Vol.35 (3), p.857-865</ispartof><rights>2020 Elsevier Inc.</rights><rights>Copyright © 2020 Elsevier Inc. All rights reserved.</rights><lds50>peer_reviewed</lds50><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c356t-8d13cce7c8ff1fe345657c655624ec78e93037b2ce8f0ae5aa6cb682b402ebce3</citedby><cites>FETCH-LOGICAL-c356t-8d13cce7c8ff1fe345657c655624ec78e93037b2ce8f0ae5aa6cb682b402ebce3</cites><orcidid>0000-0002-7203-2832 ; 0000-0001-7705-5796</orcidid></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://dx.doi.org/10.1053/j.jvca.2020.07.029$$EHTML$$P50$$Gelsevier$$H</linktohtml><link.rule.ids>314,777,781,3537,27905,27906,45976</link.rule.ids><backlink>$$Uhttps://www.ncbi.nlm.nih.gov/pubmed/32747203$$D View this record in MEDLINE/PubMed$$Hfree_for_read</backlink></links><search><creatorcontrib>Fernandes, Marta Priscila Bento</creatorcontrib><creatorcontrib>Armengol de la Hoz, Miguel</creatorcontrib><creatorcontrib>Rangasamy, Valluvan</creatorcontrib><creatorcontrib>Subramaniam, Balachundhar</creatorcontrib><title>Machine Learning Models with Preoperative Risk Factors and Intraoperative Hypotension Parameters Predict Mortality After Cardiac Surgery</title><title>Journal of cardiothoracic and vascular anesthesia</title><addtitle>J Cardiothorac Vasc Anesth</addtitle><description>Objectives: Machine learning models used to predict postoperative mortality rarely include intraoperative factors. Several intraoperative factors like hypotension (IOH), vasopressor-inotropes, and cardiopulmonary bypass (CPB) time are significantly associated with postoperative outcomes. The authors explored the ability of machine learning models incorporating intraoperative risk factors to predict mortality after cardiac surgery.
Design: Retrospective study.
Setting: Tertiary hospital.
Participants: A total of 5,015 adults who underwent cardiac surgery from 2008 to 2016.
Intervention: None.
Measurements and Main Results: The intraoperative phase was divided into the following: (1) CPB, (2) outside CPB, and (3) total surgery for quantifying IOH only. Phase-specific IOH parameters (area under the curve for mean arterial pressure <65 mmHg), vasopressor-inotropes (norepinephrine equivalents), duration, and cross-clamp time, along with preoperative risk factors ,were incorporated into the models. The primary outcome was mortality. The following 5 models were applied to 3 intraoperative phases separately: (1) logistic regression, (2) random forests, (3) neural networks, (4) support vector machines, and (5) extreme gradient boosting (XGB). Mortality was predicted using area under the receiver operating characteristic curve. Of 5,015 patients included, 112 (2.2%) died. XGB model from the outside-CPB phase predicted mortality better with area under the receiver operating characteristic curve, 95% confidence interval (CI): 0.88(0.83-0.94); positive predictive value, 0.10(0.06-0.15); specificity 0.85 (0.83-0.87) and sensitivity 0.75 (0.57-0.90).
Conclusion: XGB machine learning model from IOH outside the CPB phase seemed to offer a better discrimination, sensitivity, specificity, and positive predictive value compared with other models. Machine learning models incorporating intraoperative adverse factors might offer better predictive ability for risk stratification and triaging of patients after cardiac surgery.</description><subject>cardiac surgery</subject><subject>intraoperative adverse factors</subject><subject>intraoperative hypotension</subject><subject>Machine learning</subject><subject>mortality prediction</subject><issn>1053-0770</issn><issn>1532-8422</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2021</creationdate><recordtype>article</recordtype><recordid>eNp9kU1vEzEQhi0EoqXwBzggH7ns4rXX643EpYoorZSKio-zNTs72zps7GA7QfkH_GwcpcCN04w0zzyH92XsdSPqRmj1bl2v9wi1FFLUwtRCLp6w80YrWfWtlE_LXqhKGCPO2IuU1kI0jdbmOTtT0rRGCnXOft0CPjhPfEUQvfP3_DaMNCf-0-UHfhcpbClCdnvin136zq8Ac4iJgx_5jc8R_t2vD9uQyScXPL-DCBvKVMjiGB3m4o0ZZpcP_HIqB76EODpA_mUX7ykeXrJnE8yJXj3OC_bt6sPX5XW1-vTxZnm5qlDpLlf92ChEMthPUzORanWnDXZad7IlND0tlFBmkEj9JIA0QIdD18uhFZIGJHXB3p682xh-7Chlu3EJaZ7BU9glK9si6Ba96AoqTyjGkFKkyW6j20A82EbYY7Z2bY8N2GMDVhhbGihPbx79u2FD49-XP5EX4P0JKCnT3lG0CR15LClFwmzH4P7n_w3hc5qo</recordid><startdate>202103</startdate><enddate>202103</enddate><creator>Fernandes, Marta Priscila Bento</creator><creator>Armengol de la Hoz, Miguel</creator><creator>Rangasamy, Valluvan</creator><creator>Subramaniam, Balachundhar</creator><general>Elsevier Inc</general><scope>NPM</scope><scope>AAYXX</scope><scope>CITATION</scope><scope>7X8</scope><orcidid>https://orcid.org/0000-0002-7203-2832</orcidid><orcidid>https://orcid.org/0000-0001-7705-5796</orcidid></search><sort><creationdate>202103</creationdate><title>Machine Learning Models with Preoperative Risk Factors and Intraoperative Hypotension Parameters Predict Mortality After Cardiac Surgery</title><author>Fernandes, Marta Priscila Bento ; Armengol de la Hoz, Miguel ; Rangasamy, Valluvan ; Subramaniam, Balachundhar</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c356t-8d13cce7c8ff1fe345657c655624ec78e93037b2ce8f0ae5aa6cb682b402ebce3</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2021</creationdate><topic>cardiac surgery</topic><topic>intraoperative adverse factors</topic><topic>intraoperative hypotension</topic><topic>Machine learning</topic><topic>mortality prediction</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Fernandes, Marta Priscila Bento</creatorcontrib><creatorcontrib>Armengol de la Hoz, Miguel</creatorcontrib><creatorcontrib>Rangasamy, Valluvan</creatorcontrib><creatorcontrib>Subramaniam, Balachundhar</creatorcontrib><collection>PubMed</collection><collection>CrossRef</collection><collection>MEDLINE - Academic</collection><jtitle>Journal of cardiothoracic and vascular anesthesia</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Fernandes, Marta Priscila Bento</au><au>Armengol de la Hoz, Miguel</au><au>Rangasamy, Valluvan</au><au>Subramaniam, Balachundhar</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Machine Learning Models with Preoperative Risk Factors and Intraoperative Hypotension Parameters Predict Mortality After Cardiac Surgery</atitle><jtitle>Journal of cardiothoracic and vascular anesthesia</jtitle><addtitle>J Cardiothorac Vasc Anesth</addtitle><date>2021-03</date><risdate>2021</risdate><volume>35</volume><issue>3</issue><spage>857</spage><epage>865</epage><pages>857-865</pages><issn>1053-0770</issn><eissn>1532-8422</eissn><abstract>Objectives: Machine learning models used to predict postoperative mortality rarely include intraoperative factors. Several intraoperative factors like hypotension (IOH), vasopressor-inotropes, and cardiopulmonary bypass (CPB) time are significantly associated with postoperative outcomes. The authors explored the ability of machine learning models incorporating intraoperative risk factors to predict mortality after cardiac surgery.
Design: Retrospective study.
Setting: Tertiary hospital.
Participants: A total of 5,015 adults who underwent cardiac surgery from 2008 to 2016.
Intervention: None.
Measurements and Main Results: The intraoperative phase was divided into the following: (1) CPB, (2) outside CPB, and (3) total surgery for quantifying IOH only. Phase-specific IOH parameters (area under the curve for mean arterial pressure <65 mmHg), vasopressor-inotropes (norepinephrine equivalents), duration, and cross-clamp time, along with preoperative risk factors ,were incorporated into the models. The primary outcome was mortality. The following 5 models were applied to 3 intraoperative phases separately: (1) logistic regression, (2) random forests, (3) neural networks, (4) support vector machines, and (5) extreme gradient boosting (XGB). Mortality was predicted using area under the receiver operating characteristic curve. Of 5,015 patients included, 112 (2.2%) died. XGB model from the outside-CPB phase predicted mortality better with area under the receiver operating characteristic curve, 95% confidence interval (CI): 0.88(0.83-0.94); positive predictive value, 0.10(0.06-0.15); specificity 0.85 (0.83-0.87) and sensitivity 0.75 (0.57-0.90).
Conclusion: XGB machine learning model from IOH outside the CPB phase seemed to offer a better discrimination, sensitivity, specificity, and positive predictive value compared with other models. Machine learning models incorporating intraoperative adverse factors might offer better predictive ability for risk stratification and triaging of patients after cardiac surgery.</abstract><cop>United States</cop><pub>Elsevier Inc</pub><pmid>32747203</pmid><doi>10.1053/j.jvca.2020.07.029</doi><tpages>9</tpages><orcidid>https://orcid.org/0000-0002-7203-2832</orcidid><orcidid>https://orcid.org/0000-0001-7705-5796</orcidid></addata></record> |
| fulltext | fulltext |
| identifier | ISSN: 1053-0770 |
| ispartof | Journal of cardiothoracic and vascular anesthesia, 2021-03, Vol.35 (3), p.857-865 |
| issn | 1053-0770 1532-8422 |
| language | eng |
| recordid | cdi_proquest_miscellaneous_2430369806 |
| source | Elsevier ScienceDirect Journals |
| subjects | cardiac surgery intraoperative adverse factors intraoperative hypotension Machine learning mortality prediction |
| title | Machine Learning Models with Preoperative Risk Factors and Intraoperative Hypotension Parameters Predict Mortality After Cardiac Surgery |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-17T19%3A02%3A47IST&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=Machine%20Learning%20Models%20with%20Preoperative%20Risk%20Factors%20and%20Intraoperative%20Hypotension%20Parameters%20Predict%20Mortality%20After%20Cardiac%20Surgery&rft.jtitle=Journal%20of%20cardiothoracic%20and%20vascular%20anesthesia&rft.au=Fernandes,%20Marta%20Priscila%20Bento&rft.date=2021-03&rft.volume=35&rft.issue=3&rft.spage=857&rft.epage=865&rft.pages=857-865&rft.issn=1053-0770&rft.eissn=1532-8422&rft_id=info:doi/10.1053/j.jvca.2020.07.029&rft_dat=%3Cproquest_cross%3E2430369806%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=2430369806&rft_id=info:pmid/32747203&rft_els_id=S1053077020306595&rfr_iscdi=true |