Machine Learning to Predict Outcomes and Cost by Phase of Care After Coronary Artery Bypass Grafting
Machine learning may enhance prediction of outcomes after coronary artery bypass grafting (CABG). We sought to develop and validate a dynamic machine learning model to predict CABG outcomes at clinically relevant pre- and postoperative time points. The Society of Thoracic Surgeons (STS) registry dat...
Saved in:
Published in | The Annals of thoracic surgery Vol. 114; no. 3; pp. 711 - 719 |
---|---|
Main Authors | , , , , , , , , , |
Format | Journal Article |
Language | English |
Published |
Netherlands
Elsevier Inc
01.09.2022
|
Online Access | Get full text |
Cover
Loading…
Abstract | Machine learning may enhance prediction of outcomes after coronary artery bypass grafting (CABG). We sought to develop and validate a dynamic machine learning model to predict CABG outcomes at clinically relevant pre- and postoperative time points.
The Society of Thoracic Surgeons (STS) registry data elements from 2086 isolated CABG patients were divided into training and testing datasets and input into Extreme Gradient Boosting decision-tree machine learning algorithms. Two prediction models were developed based on data from preoperative (80 parameters) and postoperative (125 parameters) phases of care. Outcomes included operative mortality, major morbidity or mortality, high cost, and 30-day readmission. Machine learning and STS model performance were assessed using accuracy and the area under the precision-recall curve (AUC-PR).
Preoperative machine learning models predicted mortality (accuracy, 98%; AUC-PR = 0.16; F1 = 0.24), major morbidity or mortality (accuracy, 75%; AUC-PR = 0.33; F1 = 0.42), high cost (accuracy, 83%; AUC-PR = 0.51; F1 = 0.52), and 30-day readmission (accuracy, 70%; AUC-PR = 0.47; F1 = 0.49) with high accuracy. Preoperative machine learning models performed similarly to the STS for prediction of mortality (STS AUC-PR = 0.11; P = .409) and outperformed STS for prediction of mortality or major morbidity (STS AUC-PR = 0.28; P < .001). Addition of intraoperative parameters further improved machine learning model performance for major morbidity or mortality (AUC-PR = 0.39; P < .01) and high cost (AUC-PR = 0.64; P < .01), with cross-clamp and bypass times emerging as important additive predictive parameters.
Machine learning can predict mortality, major morbidity, high cost, and readmission after isolated CABG. Prediction based on the phase of care allows for dynamic risk assessment through the hospital course, which may benefit quality assessment and clinical decision-making.
[Display omitted] |
---|---|
AbstractList | Machine learning may enhance prediction of outcomes after coronary artery bypass grafting (CABG). We sought to develop and validate a dynamic machine learning model to predict CABG outcomes at clinically relevant pre- and postoperative time points.
The Society of Thoracic Surgeons (STS) registry data elements from 2086 isolated CABG patients were divided into training and testing datasets and input into Extreme Gradient Boosting decision-tree machine learning algorithms. Two prediction models were developed based on data from preoperative (80 parameters) and postoperative (125 parameters) phases of care. Outcomes included operative mortality, major morbidity or mortality, high cost, and 30-day readmission. Machine learning and STS model performance were assessed using accuracy and the area under the precision-recall curve (AUC-PR).
Preoperative machine learning models predicted mortality (accuracy, 98%; AUC-PR = 0.16; F1 = 0.24), major morbidity or mortality (accuracy, 75%; AUC-PR = 0.33; F1 = 0.42), high cost (accuracy, 83%; AUC-PR = 0.51; F1 = 0.52), and 30-day readmission (accuracy, 70%; AUC-PR = 0.47; F1 = 0.49) with high accuracy. Preoperative machine learning models performed similarly to the STS for prediction of mortality (STS AUC-PR = 0.11; P = .409) and outperformed STS for prediction of mortality or major morbidity (STS AUC-PR = 0.28; P < .001). Addition of intraoperative parameters further improved machine learning model performance for major morbidity or mortality (AUC-PR = 0.39; P < .01) and high cost (AUC-PR = 0.64; P < .01), with cross-clamp and bypass times emerging as important additive predictive parameters.
Machine learning can predict mortality, major morbidity, high cost, and readmission after isolated CABG. Prediction based on the phase of care allows for dynamic risk assessment through the hospital course, which may benefit quality assessment and clinical decision-making.
[Display omitted] BACKGROUNDMachine learning may enhance prediction of outcomes after coronary artery bypass grafting (CABG). We sought to develop and validate a dynamic machine learning model to predict CABG outcomes at clinically relevant pre- and postoperative time points. METHODSThe Society of Thoracic Surgeons (STS) registry data elements from 2086 isolated CABG patients were divided into training and testing datasets and input into Extreme Gradient Boosting decision-tree machine learning algorithms. Two prediction models were developed based on data from preoperative (80 parameters) and postoperative (125 parameters) phases of care. Outcomes included operative mortality, major morbidity or mortality, high cost, and 30-day readmission. Machine learning and STS model performance were assessed using accuracy and the area under the precision-recall curve (AUC-PR). RESULTSPreoperative machine learning models predicted mortality (accuracy, 98%; AUC-PR = 0.16; F1 = 0.24), major morbidity or mortality (accuracy, 75%; AUC-PR = 0.33; F1 = 0.42), high cost (accuracy, 83%; AUC-PR = 0.51; F1 = 0.52), and 30-day readmission (accuracy, 70%; AUC-PR = 0.47; F1 = 0.49) with high accuracy. Preoperative machine learning models performed similarly to the STS for prediction of mortality (STS AUC-PR = 0.11; P = .409) and outperformed STS for prediction of mortality or major morbidity (STS AUC-PR = 0.28; P < .001). Addition of intraoperative parameters further improved machine learning model performance for major morbidity or mortality (AUC-PR = 0.39; P < .01) and high cost (AUC-PR = 0.64; P < .01), with cross-clamp and bypass times emerging as important additive predictive parameters. CONCLUSIONSMachine learning can predict mortality, major morbidity, high cost, and readmission after isolated CABG. Prediction based on the phase of care allows for dynamic risk assessment through the hospital course, which may benefit quality assessment and clinical decision-making. Machine learning may enhance prediction of outcomes after coronary artery bypass grafting (CABG). We sought to develop and validate a dynamic machine learning model to predict CABG outcomes at clinically relevant pre- and postoperative time points. The Society of Thoracic Surgeons (STS) registry data elements from 2086 isolated CABG patients were divided into training and testing datasets and input into Extreme Gradient Boosting decision-tree machine learning algorithms. Two prediction models were developed based on data from preoperative (80 parameters) and postoperative (125 parameters) phases of care. Outcomes included operative mortality, major morbidity or mortality, high cost, and 30-day readmission. Machine learning and STS model performance were assessed using accuracy and the area under the precision-recall curve (AUC-PR). Preoperative machine learning models predicted mortality (accuracy, 98%; AUC-PR = 0.16; F1 = 0.24), major morbidity or mortality (accuracy, 75%; AUC-PR = 0.33; F1 = 0.42), high cost (accuracy, 83%; AUC-PR = 0.51; F1 = 0.52), and 30-day readmission (accuracy, 70%; AUC-PR = 0.47; F1 = 0.49) with high accuracy. Preoperative machine learning models performed similarly to the STS for prediction of mortality (STS AUC-PR = 0.11; P = .409) and outperformed STS for prediction of mortality or major morbidity (STS AUC-PR = 0.28; P < .001). Addition of intraoperative parameters further improved machine learning model performance for major morbidity or mortality (AUC-PR = 0.39; P < .01) and high cost (AUC-PR = 0.64; P < .01), with cross-clamp and bypass times emerging as important additive predictive parameters. Machine learning can predict mortality, major morbidity, high cost, and readmission after isolated CABG. Prediction based on the phase of care allows for dynamic risk assessment through the hospital course, which may benefit quality assessment and clinical decision-making. |
Author | Rosengart, Todd K. Ryan, Christopher T. Chatterjee, Subhasis Ghanta, Ravi K. Havelka, Jim Coselli, Joseph S. Nguyen, Tom C. Wall, Matthew J. Corr, Stuart J. Zea-Vera, Rodrigo |
AuthorAffiliation | 4 Division of Adult Cardiothoracic Surgery, University of California San Francisco, San Francisco, California 1 Michael E. DeBakey Department of Surgery, Baylor College of Medicine, Houston, Texas 5 Department of Cardiovascular Surgery, Texas Heart Institute, Houston, Texas 2 InformAI, Houston, Texas 3 DeBakey Heart and Vascular Center, Houston Methodist Hospital, Houston, Texas |
AuthorAffiliation_xml | – name: 4 Division of Adult Cardiothoracic Surgery, University of California San Francisco, San Francisco, California – name: 2 InformAI, Houston, Texas – name: 1 Michael E. DeBakey Department of Surgery, Baylor College of Medicine, Houston, Texas – name: 5 Department of Cardiovascular Surgery, Texas Heart Institute, Houston, Texas – name: 3 DeBakey Heart and Vascular Center, Houston Methodist Hospital, Houston, Texas |
Author_xml | – sequence: 1 givenname: Rodrigo orcidid: 0000-0002-8549-0656 surname: Zea-Vera fullname: Zea-Vera, Rodrigo organization: Michael E. DeBakey Department of Surgery, Baylor College of Medicine, Houston, Texas – sequence: 2 givenname: Christopher T. surname: Ryan fullname: Ryan, Christopher T. organization: Michael E. DeBakey Department of Surgery, Baylor College of Medicine, Houston, Texas – sequence: 3 givenname: Jim surname: Havelka fullname: Havelka, Jim organization: InformAI, Houston, Texas – sequence: 4 givenname: Stuart J. surname: Corr fullname: Corr, Stuart J. organization: DeBakey Heart and Vascular Center, Houston Methodist Hospital, Houston, Texas – sequence: 5 givenname: Tom C. surname: Nguyen fullname: Nguyen, Tom C. organization: Division of Adult Cardiothoracic Surgery, University of California at San Francisco, San Francisco, California – sequence: 6 givenname: Subhasis surname: Chatterjee fullname: Chatterjee, Subhasis organization: Michael E. DeBakey Department of Surgery, Baylor College of Medicine, Houston, Texas – sequence: 7 givenname: Matthew J. surname: Wall fullname: Wall, Matthew J. organization: Michael E. DeBakey Department of Surgery, Baylor College of Medicine, Houston, Texas – sequence: 8 givenname: Joseph S. surname: Coselli fullname: Coselli, Joseph S. organization: Michael E. DeBakey Department of Surgery, Baylor College of Medicine, Houston, Texas – sequence: 9 givenname: Todd K. surname: Rosengart fullname: Rosengart, Todd K. organization: Michael E. DeBakey Department of Surgery, Baylor College of Medicine, Houston, Texas – sequence: 10 givenname: Ravi K. surname: Ghanta fullname: Ghanta, Ravi K. email: ravi.ghanta@bcm.edu organization: Michael E. DeBakey Department of Surgery, Baylor College of Medicine, Houston, Texas |
BackLink | https://www.ncbi.nlm.nih.gov/pubmed/34582751$$D View this record in MEDLINE/PubMed |
BookMark | eNqFkUFPGzEQha2KqgTav4B87GUX22uvdy9IIQKKlAoO7dny2rPEUWKnthcp_x5HoRROPY1G782b0Xxn6MQHDwhhSmpKaHu5rnVehahNmmLNCKM16WrCySc0o0KwqmWiP0EzQkhT8V6KU3SW0rq0rMhf0GnDRcekoDNkf2qzch7wEnT0zj_hHPBjBOtMxg9TNmELCWtv8SKkjIc9flzpBDiMeKEj4PmYIRYtBq_jHs9jaff4er_TKeG7qMdcMr-iz6PeJPj2Ws_R79ubX4sf1fLh7n4xX1aG9yJXnNOWMjtKxhnVfcf7kTUt6wU0VnLOe0qtGExjJAxjBxIkkYJxADu0nA2yOUdXx9zdNGzBGvA56o3aRbctx6mgnfqoeLdST-FZ9ZI0LTkEfH8NiOHPBCmrrUsGNhvtIUxJMSGlbCjjvFi7o9XEkFKE8W0NJeoASa3VP0jqAEmRThVIZfTi_Zlvg3-pFMP10QDlWc8OokrGgTeFSgSTlQ3u_1teABVrqu0 |
CitedBy_id | crossref_primary_10_3390_s23041811 crossref_primary_10_3390_app12052737 crossref_primary_10_1002_clc_23963 crossref_primary_10_1111_bcp_15846 crossref_primary_10_1007_s10157_024_02472_z crossref_primary_10_1016_j_athoracsur_2022_06_055 crossref_primary_10_1016_j_surg_2024_03_051 crossref_primary_10_3389_fcvm_2022_977747 |
Cites_doi | 10.1097/CRD.0000000000000294 10.21037/jtd-20-2736 10.1016/j.jtcvs.2019.07.017 10.1016/j.athoracsur.2019.09.042 10.1016/j.athoracsur.2016.01.105 10.1093/ehjqcco/qcy027 10.1016/j.athoracsur.2020.04.142 10.1016/j.jtcvs.2020.07.105 10.1016/S2589-7500(20)30018-2 10.1093/ejcts/ezs043 10.1016/j.athoracsur.2019.11.003 10.1016/j.athoracsur.2018.10.077 10.1016/j.jtcvs.2020.08.091 10.1186/2193-1801-2-222 10.1053/j.jvca.2008.08.004 10.1016/S0003-4975(97)00225-7 10.1016/j.athoracsur.2019.09.049 10.1016/j.jtcvs.2020.09.076 10.1016/j.athoracsur.2018.03.003 10.1093/icvts/ivu102 10.1080/09537104.2018.1466389 |
ContentType | Journal Article |
Copyright | 2022 The Society of Thoracic Surgeons Copyright © 2021 The Society of Thoracic Surgeons. Published by Elsevier Inc. All rights reserved. |
Copyright_xml | – notice: 2022 The Society of Thoracic Surgeons – notice: Copyright © 2021 The Society of Thoracic Surgeons. Published by Elsevier Inc. All rights reserved. |
DBID | NPM AAYXX CITATION 7X8 5PM |
DOI | 10.1016/j.athoracsur.2021.08.040 |
DatabaseName | PubMed CrossRef MEDLINE - Academic PubMed Central (Full Participant titles) |
DatabaseTitle | PubMed CrossRef MEDLINE - Academic |
DatabaseTitleList | MEDLINE - Academic PubMed |
Database_xml | – sequence: 1 dbid: NPM name: PubMed url: https://proxy.k.utb.cz/login?url=http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed sourceTypes: Index Database |
DeliveryMethod | fulltext_linktorsrc |
EISSN | 1552-6259 |
EndPage | 719 |
ExternalDocumentID | 10_1016_j_athoracsur_2021_08_040 34582751 S0003497521016490 |
Genre | Journal Article |
GroupedDBID | --- --K .1- .55 .FO .GJ 0R~ 1B1 1P~ 1~5 23M 3O- 4.4 457 4G. 53G 5GY 5RE 5VS 6J9 7-5 71M AAEDT AAEDW AAEJM AAIAV AALRI AAQFI AAQQT AAQXK AAXUO ABJNI ABLJU ABMAC ABOCM ACGFO ACGFS ACIUM ACRZS ADBBV ADMUD ADPAM AENEX AEVXI AFCTW AFFNX AFRHN AFTJW AGHFR AGZHU AHPSJ AI. AITUG AJJEV AJUYK ALMA_UNASSIGNED_HOLDINGS ALXNB AMRAJ ASPBG AVWKF AZFZN BAWUL BELOY C5W CS3 DIK E3Z EBS EFJIC EJD F5P FDB FEDTE FGOYB GBLVA GX1 HVGLF HZ~ IH2 IHE J1W J5H K-O KOM L7B M41 MO0 N9A NQ- O9- OA- OK1 OL. OVD P2P P6G PC. R2- RIG ROL RPZ SES SSZ TEORI TR2 UDS UNMZH UV1 VH1 W8F X7M XH2 XPP Z5R ZA5 ZGI ZXP AKRWK NPM AAYXX ACRPL ADNMO CITATION 7X8 5PM |
ID | FETCH-LOGICAL-c495t-441612df72421a9849f236295e3d7444911d5bc3c7ebf8e7e707524eedb642b73 |
ISSN | 0003-4975 |
IngestDate | Tue Sep 17 21:29:47 EDT 2024 Wed Dec 04 04:50:09 EST 2024 Fri Dec 06 01:13:44 EST 2024 Sat Sep 28 08:22:44 EDT 2024 Fri Feb 23 02:38:57 EST 2024 |
IsPeerReviewed | true |
IsScholarly | true |
Issue | 3 |
Language | English |
License | Copyright © 2021 The Society of Thoracic Surgeons. Published by Elsevier Inc. All rights reserved. |
LinkModel | OpenURL |
MergedId | FETCHMERGED-LOGICAL-c495t-441612df72421a9849f236295e3d7444911d5bc3c7ebf8e7e707524eedb642b73 |
Notes | ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 23 |
ORCID | 0000-0002-8549-0656 |
PMID | 34582751 |
PQID | 2577731244 |
PQPubID | 23479 |
PageCount | 9 |
ParticipantIDs | pubmedcentral_primary_oai_pubmedcentral_nih_gov_9703607 proquest_miscellaneous_2577731244 crossref_primary_10_1016_j_athoracsur_2021_08_040 pubmed_primary_34582751 elsevier_sciencedirect_doi_10_1016_j_athoracsur_2021_08_040 |
PublicationCentury | 2000 |
PublicationDate | 2022-09-01 |
PublicationDateYYYYMMDD | 2022-09-01 |
PublicationDate_xml | – month: 09 year: 2022 text: 2022-09-01 day: 01 |
PublicationDecade | 2020 |
PublicationPlace | Netherlands |
PublicationPlace_xml | – name: Netherlands |
PublicationTitle | The Annals of thoracic surgery |
PublicationTitleAlternate | Ann Thorac Surg |
PublicationYear | 2022 |
Publisher | Elsevier Inc |
Publisher_xml | – name: Elsevier Inc |
References | O’Brien, Feng, He (bib1) 2018; 105 Salgado, Azevedo, Proença, Vieira (bib9) 2016 Nammas, Dalén, Rosato (bib17) 2019; 30 Fernandez (bib6) 2020; 109 Salis, Mazzanti, Merli (bib13) 2008; 22 Ishwaran, Blackstone (bib22) 2022; 163 Blackstone, Swain, McCardle, Adams (bib7) 2019; 158 Kilic, Goyal, Miller (bib5) 2019; 109 Nashef, Roques, Sharples (bib2) 2012; 41 Shah, Zhang, Chatterjee (bib20) 2019; 107 Kilic (bib10) 2020; 109 Lippmann, Shahian (bib12) 1997; 63 Zea-Vera, Zhang, Amin (bib21) 2021; 111 Thorsen-Meyer, Nielsen, Nielsen (bib19) 2020; 2 Benedetto, Dimagli, Sinha (bib4) 2022; 163 Dong, Peng (bib8) 2013; 2 Chalmers, Pullan, Mediratta, Poullis (bib14) 2014; 19 Biancari, Mariscalco, Gherli (bib16) 2018; 4 Ge, Wang, Chen (bib18) 2021; 13 Manyam R, Zhang Y, Carter S, Binongo JN, Rosenblum JM, Keeling WB. Unraveling the impact of time-dependent perioperative variables on 30-day readmission after coronary artery bypass surgery. Miller (bib11) 2020; 28 Ad, Holmes, Patel, Pritchard, Shuman, Halpin (bib3) 2016; 102 Published online September 29, 2020. O’Brien (10.1016/j.athoracsur.2021.08.040_bib1) 2018; 105 Nashef (10.1016/j.athoracsur.2021.08.040_bib2) 2012; 41 10.1016/j.athoracsur.2021.08.040_bib15 Lippmann (10.1016/j.athoracsur.2021.08.040_bib12) 1997; 63 Biancari (10.1016/j.athoracsur.2021.08.040_bib16) 2018; 4 Miller (10.1016/j.athoracsur.2021.08.040_bib11) 2020; 28 Chalmers (10.1016/j.athoracsur.2021.08.040_bib14) 2014; 19 Kilic (10.1016/j.athoracsur.2021.08.040_bib10) 2020; 109 Ishwaran (10.1016/j.athoracsur.2021.08.040_bib22) 2022; 163 Fernandez (10.1016/j.athoracsur.2021.08.040_bib6) 2020; 109 Ad (10.1016/j.athoracsur.2021.08.040_bib3) 2016; 102 Nammas (10.1016/j.athoracsur.2021.08.040_bib17) 2019; 30 Salis (10.1016/j.athoracsur.2021.08.040_bib13) 2008; 22 Benedetto (10.1016/j.athoracsur.2021.08.040_bib4) 2022; 163 Zea-Vera (10.1016/j.athoracsur.2021.08.040_bib21) 2021; 111 Blackstone (10.1016/j.athoracsur.2021.08.040_bib7) 2019; 158 Kilic (10.1016/j.athoracsur.2021.08.040_bib5) 2019; 109 Ge (10.1016/j.athoracsur.2021.08.040_bib18) 2021; 13 Thorsen-Meyer (10.1016/j.athoracsur.2021.08.040_bib19) 2020; 2 Salgado (10.1016/j.athoracsur.2021.08.040_bib9) 2016 Shah (10.1016/j.athoracsur.2021.08.040_bib20) 2019; 107 Dong (10.1016/j.athoracsur.2021.08.040_bib8) 2013; 2 |
References_xml | – start-page: 143 year: 2016 end-page: 162 ident: bib9 article-title: Missing data publication-title: MIT Critical Data, ed. Secondary Analysis of Electronic Health Records contributor: fullname: Vieira – volume: 28 start-page: 53 year: 2020 end-page: 64 ident: bib11 article-title: Machine intelligence in cardiovascular medicine publication-title: Cardiol Rev contributor: fullname: Miller – volume: 163 start-page: 2075 year: 2022 end-page: 2087.e9 ident: bib4 article-title: Machine learning improves mortality risk prediction after cardiac surgery: systematic review and meta-analysis publication-title: J Thorac Cardiovasc Surg contributor: fullname: Sinha – volume: 102 start-page: 573 year: 2016 end-page: 579 ident: bib3 article-title: Comparison of EuroSCORE II, original EuroSCORE, and The Society of Thoracic Surgeons risk score in cardiac surgery patients publication-title: Ann Thorac Surg contributor: fullname: Halpin – volume: 109 start-page: 1811 year: 2019 end-page: 1819 ident: bib5 article-title: Predictive utility of a machine learning algorithm in estimating mortality risk in cardiac surgery publication-title: Ann Thorac Surg contributor: fullname: Miller – volume: 13 start-page: 735 year: 2021 end-page: 742 ident: bib18 article-title: Risk factors for and outcomes of prolonged mechanical ventilation in patients received DeBakey type I aortic dissection repair publication-title: J Thorac Dis contributor: fullname: Chen – volume: 22 start-page: 814 year: 2008 end-page: 822 ident: bib13 article-title: Cardiopulmonary bypass duration is an independent predictor of morbidity and mortality after cardiac surgery publication-title: J Cardiothorac Vasc Anesth contributor: fullname: Merli – volume: 4 start-page: 246 year: 2018 end-page: 257 ident: bib16 article-title: Variation in preoperative antithrombotic strategy, severe bleeding, and use of blood products in coronary artery bypass grafting: results from the multicentre E-CABG registry publication-title: Eur Heart J Qual Care Clin Outcomes contributor: fullname: Gherli – volume: 19 start-page: 21 year: 2014 end-page: 26 ident: bib14 article-title: A need for speed? Bypass time and outcomes after isolated aortic valve replacement surgery publication-title: Interact Cardiovasc Thorac Surg contributor: fullname: Poullis – volume: 63 start-page: 1635 year: 1997 end-page: 1643 ident: bib12 article-title: Coronary artery bypass risk prediction using neural networks publication-title: Ann Thorac Surg contributor: fullname: Shahian – volume: 105 start-page: 1419 year: 2018 end-page: 1428 ident: bib1 article-title: The Society of Thoracic Surgeons 2018 adult cardiac surgery risk models: part 2—statistical methods and results publication-title: Ann Thorac Surg contributor: fullname: He – volume: 2 start-page: e179 year: 2020 end-page: e191 ident: bib19 article-title: Dynamic and explainable machine learning prediction of mortality in patients in the intensive care unit: a retrospective study of high-frequency data in electronic patient records publication-title: Lancet Digit Health contributor: fullname: Nielsen – volume: 111 start-page: 488 year: 2021 end-page: 494 ident: bib21 article-title: Development of a risk score to predict 90-day readmission after coronary artery bypass graft publication-title: Ann Thorac Surg contributor: fullname: Amin – volume: 41 start-page: 734 year: 2012 end-page: 744 ident: bib2 article-title: EuroSCORE II publication-title: Eur J Cardiothorac Surg contributor: fullname: Sharples – volume: 158 start-page: 1120 year: 2019 end-page: 1126 ident: bib7 article-title: Governance Committee, American Association for Thoracic Surgery Quality Assessment Program. A comprehensive AATS quality program for the 21st century publication-title: J Thorac Cardiovasc Surg contributor: fullname: Adams – volume: 109 start-page: 1323 year: 2020 end-page: 1329 ident: bib10 article-title: Artificial intelligence and machine learning in cardiovascular health care publication-title: Ann Thorac Surg contributor: fullname: Kilic – volume: 163 start-page: 2088 year: 2022 end-page: 2090 ident: bib22 article-title: Commentary: dabblers: beware of hidden dangers in machine-learning comparisons publication-title: J Thorac Cardiovasc Surg contributor: fullname: Blackstone – volume: 107 start-page: 1782 year: 2019 end-page: 1789 ident: bib20 article-title: Incidence, cost, and risk factors for readmission after coronary artery bypass grafting publication-title: Ann Thorac Surg contributor: fullname: Chatterjee – volume: 2 start-page: 222 year: 2013 ident: bib8 article-title: Principled missing data methods for researchers publication-title: SpringerPlus contributor: fullname: Peng – volume: 109 start-page: 10 year: 2020 end-page: 13 ident: bib6 article-title: The future is now: the 2020 evolution of The Society of Thoracic Surgeons national database publication-title: Ann Thorac Surg contributor: fullname: Fernandez – volume: 30 start-page: 480 year: 2019 end-page: 486 ident: bib17 article-title: Impact of preoperative thrombocytopenia on the outcome after coronary artery bypass grafting publication-title: Platelets contributor: fullname: Rosato – start-page: 143 year: 2016 ident: 10.1016/j.athoracsur.2021.08.040_bib9 article-title: Missing data contributor: fullname: Salgado – volume: 28 start-page: 53 year: 2020 ident: 10.1016/j.athoracsur.2021.08.040_bib11 article-title: Machine intelligence in cardiovascular medicine publication-title: Cardiol Rev doi: 10.1097/CRD.0000000000000294 contributor: fullname: Miller – volume: 13 start-page: 735 year: 2021 ident: 10.1016/j.athoracsur.2021.08.040_bib18 article-title: Risk factors for and outcomes of prolonged mechanical ventilation in patients received DeBakey type I aortic dissection repair publication-title: J Thorac Dis doi: 10.21037/jtd-20-2736 contributor: fullname: Ge – volume: 158 start-page: 1120 year: 2019 ident: 10.1016/j.athoracsur.2021.08.040_bib7 article-title: Governance Committee, American Association for Thoracic Surgery Quality Assessment Program. A comprehensive AATS quality program for the 21st century publication-title: J Thorac Cardiovasc Surg doi: 10.1016/j.jtcvs.2019.07.017 contributor: fullname: Blackstone – volume: 109 start-page: 1323 year: 2020 ident: 10.1016/j.athoracsur.2021.08.040_bib10 article-title: Artificial intelligence and machine learning in cardiovascular health care publication-title: Ann Thorac Surg doi: 10.1016/j.athoracsur.2019.09.042 contributor: fullname: Kilic – volume: 102 start-page: 573 year: 2016 ident: 10.1016/j.athoracsur.2021.08.040_bib3 article-title: Comparison of EuroSCORE II, original EuroSCORE, and The Society of Thoracic Surgeons risk score in cardiac surgery patients publication-title: Ann Thorac Surg doi: 10.1016/j.athoracsur.2016.01.105 contributor: fullname: Ad – volume: 4 start-page: 246 year: 2018 ident: 10.1016/j.athoracsur.2021.08.040_bib16 article-title: Variation in preoperative antithrombotic strategy, severe bleeding, and use of blood products in coronary artery bypass grafting: results from the multicentre E-CABG registry publication-title: Eur Heart J Qual Care Clin Outcomes doi: 10.1093/ehjqcco/qcy027 contributor: fullname: Biancari – volume: 111 start-page: 488 year: 2021 ident: 10.1016/j.athoracsur.2021.08.040_bib21 article-title: Development of a risk score to predict 90-day readmission after coronary artery bypass graft publication-title: Ann Thorac Surg doi: 10.1016/j.athoracsur.2020.04.142 contributor: fullname: Zea-Vera – volume: 163 start-page: 2075 year: 2022 ident: 10.1016/j.athoracsur.2021.08.040_bib4 article-title: Machine learning improves mortality risk prediction after cardiac surgery: systematic review and meta-analysis publication-title: J Thorac Cardiovasc Surg doi: 10.1016/j.jtcvs.2020.07.105 contributor: fullname: Benedetto – volume: 2 start-page: e179 year: 2020 ident: 10.1016/j.athoracsur.2021.08.040_bib19 article-title: Dynamic and explainable machine learning prediction of mortality in patients in the intensive care unit: a retrospective study of high-frequency data in electronic patient records publication-title: Lancet Digit Health doi: 10.1016/S2589-7500(20)30018-2 contributor: fullname: Thorsen-Meyer – volume: 41 start-page: 734 year: 2012 ident: 10.1016/j.athoracsur.2021.08.040_bib2 article-title: EuroSCORE II publication-title: Eur J Cardiothorac Surg doi: 10.1093/ejcts/ezs043 contributor: fullname: Nashef – volume: 109 start-page: 10 year: 2020 ident: 10.1016/j.athoracsur.2021.08.040_bib6 article-title: The future is now: the 2020 evolution of The Society of Thoracic Surgeons national database publication-title: Ann Thorac Surg doi: 10.1016/j.athoracsur.2019.11.003 contributor: fullname: Fernandez – volume: 107 start-page: 1782 year: 2019 ident: 10.1016/j.athoracsur.2021.08.040_bib20 article-title: Incidence, cost, and risk factors for readmission after coronary artery bypass grafting publication-title: Ann Thorac Surg doi: 10.1016/j.athoracsur.2018.10.077 contributor: fullname: Shah – volume: 163 start-page: 2088 year: 2022 ident: 10.1016/j.athoracsur.2021.08.040_bib22 article-title: Commentary: dabblers: beware of hidden dangers in machine-learning comparisons publication-title: J Thorac Cardiovasc Surg doi: 10.1016/j.jtcvs.2020.08.091 contributor: fullname: Ishwaran – volume: 2 start-page: 222 year: 2013 ident: 10.1016/j.athoracsur.2021.08.040_bib8 article-title: Principled missing data methods for researchers publication-title: SpringerPlus doi: 10.1186/2193-1801-2-222 contributor: fullname: Dong – volume: 22 start-page: 814 year: 2008 ident: 10.1016/j.athoracsur.2021.08.040_bib13 article-title: Cardiopulmonary bypass duration is an independent predictor of morbidity and mortality after cardiac surgery publication-title: J Cardiothorac Vasc Anesth doi: 10.1053/j.jvca.2008.08.004 contributor: fullname: Salis – volume: 63 start-page: 1635 year: 1997 ident: 10.1016/j.athoracsur.2021.08.040_bib12 article-title: Coronary artery bypass risk prediction using neural networks publication-title: Ann Thorac Surg doi: 10.1016/S0003-4975(97)00225-7 contributor: fullname: Lippmann – volume: 109 start-page: 1811 year: 2019 ident: 10.1016/j.athoracsur.2021.08.040_bib5 article-title: Predictive utility of a machine learning algorithm in estimating mortality risk in cardiac surgery publication-title: Ann Thorac Surg doi: 10.1016/j.athoracsur.2019.09.049 contributor: fullname: Kilic – ident: 10.1016/j.athoracsur.2021.08.040_bib15 doi: 10.1016/j.jtcvs.2020.09.076 – volume: 105 start-page: 1419 year: 2018 ident: 10.1016/j.athoracsur.2021.08.040_bib1 article-title: The Society of Thoracic Surgeons 2018 adult cardiac surgery risk models: part 2—statistical methods and results publication-title: Ann Thorac Surg doi: 10.1016/j.athoracsur.2018.03.003 contributor: fullname: O’Brien – volume: 19 start-page: 21 year: 2014 ident: 10.1016/j.athoracsur.2021.08.040_bib14 article-title: A need for speed? Bypass time and outcomes after isolated aortic valve replacement surgery publication-title: Interact Cardiovasc Thorac Surg doi: 10.1093/icvts/ivu102 contributor: fullname: Chalmers – volume: 30 start-page: 480 year: 2019 ident: 10.1016/j.athoracsur.2021.08.040_bib17 article-title: Impact of preoperative thrombocytopenia on the outcome after coronary artery bypass grafting publication-title: Platelets doi: 10.1080/09537104.2018.1466389 contributor: fullname: Nammas |
SSID | ssj0002155 |
Score | 2.511889 |
Snippet | Machine learning may enhance prediction of outcomes after coronary artery bypass grafting (CABG). We sought to develop and validate a dynamic machine learning... BACKGROUNDMachine learning may enhance prediction of outcomes after coronary artery bypass grafting (CABG). We sought to develop and validate a dynamic machine... |
SourceID | pubmedcentral proquest crossref pubmed elsevier |
SourceType | Open Access Repository Aggregation Database Index Database Publisher |
StartPage | 711 |
Title | Machine Learning to Predict Outcomes and Cost by Phase of Care After Coronary Artery Bypass Grafting |
URI | https://dx.doi.org/10.1016/j.athoracsur.2021.08.040 https://www.ncbi.nlm.nih.gov/pubmed/34582751 https://search.proquest.com/docview/2577731244 https://pubmed.ncbi.nlm.nih.gov/PMC9703607 |
Volume | 114 |
hasFullText | 1 |
inHoldings | 1 |
isFullTextHit | |
isPrint | |
link | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwnV3fb9MwELZK98ILGuJXGSAj8RalahNnTsRTqYBp02BCndhbFMc2bYFkal2k8tfwp3IXx0lbihh7idq0deLc1_N39t1nQl4JHQjOhPCBzIc-k1z5AsZFX0vJdSx1Fg2xGvn8w_HJJTu9iq46nV8bWUsrI_r5z711JbexKpwDu2KV7H9YtmkUTsBrsC8cwcJwvJGNz6tMSOVEUr8gkbxY4NKL8T6uDFxSWQnmcbk0SDQvppmdu8eyI29U7Q8-Rg0DzJ0bYXbn2nuzvgZC7b1fZNq4cW3eYqpVXDZTgE8-y73lRmk1zkGrDKcJLSstJYT_ZbOss86KHUkDb9JvveAP9e2rTd6dfW9WR8qF3RvMYP6pd9rfnKiAGNdlYrXON8QN7aIt52tLSGuUhRuulNdOWNXvkr0O3849zOG5V32GDkPMH1hZVqsDta2xvTP2NRmJLtltnrYtpdhSirt0ssEdcoBSi6xLDkZnnz6fNaM9UKbI7cqInauzxWwO4f67-hsF-jPE2c3U3aA-k0Nyr45Z6MgC8D7pqOIBkTX4qAMfNSWtwUcd-CiAjyL4qFjTCny01BTBRyvwUQc-asFHLfioA99Dcvnu7WR84tdbdvg5RNrGZxgvB1JzzDTIkpglOgCKlEQqlJwxBkOrjEQe5lwJHSuuOFDWgAFRExAICx4-It2iLNQTQgMRDwehymOdMKZlkHEusag1lzo-jnjeI0P3FNNrq8yS_suKPfLaPe60ZpiWOaaApxv8-qWzUApOGFfWskKVq2UK4x7nIVLlHnlsLdbcU4gr0zwa9gjfsmXzBRR43_6kmE0rofcE1fEG_OktenpE7rb_wWekaxYr9RzosxEvagT_Br_0yys |
link.rule.ids | 230,314,780,784,885,27924,27925 |
linkProvider | Library Specific Holdings |
openUrl | ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=Machine+Learning+to+Predict+Outcomes+and+Cost+by+Phase+of+Care+After+Coronary+Artery+Bypass+Grafting&rft.jtitle=The+Annals+of+thoracic+surgery&rft.au=Zea-Vera%2C+Rodrigo&rft.au=Ryan%2C+Christopher+T.&rft.au=Havelka%2C+Jim&rft.au=Corr%2C+Stuart+J.&rft.date=2022-09-01&rft.issn=0003-4975&rft.volume=114&rft.issue=3&rft.spage=711&rft.epage=719&rft_id=info:doi/10.1016%2Fj.athoracsur.2021.08.040&rft.externalDBID=n%2Fa&rft.externalDocID=10_1016_j_athoracsur_2021_08_040 |
thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0003-4975&client=summon |
thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0003-4975&client=summon |
thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0003-4975&client=summon |