Development of a Machine Learning Model to Predict Outcomes and Cost After Cardiac Surgery
Machine learning (ML) algorithms may enhance outcomes prediction and help guide clinical decision making. This study aimed to develop and validate a ML model that predicts postoperative outcomes and costs after cardiac surgery. The Society of Thoracic Surgeons registry data from 4874 patients who un...
Saved in:
Published in | The Annals of thoracic surgery Vol. 115; no. 6; pp. 1533 - 1542 |
---|---|
Main Authors | , , , , , , , , |
Format | Journal Article |
Language | English |
Published |
Netherlands
Elsevier Inc
01.06.2023
|
Subjects | |
Online Access | Get full text |
Cover
Loading…
Abstract | Machine learning (ML) algorithms may enhance outcomes prediction and help guide clinical decision making. This study aimed to develop and validate a ML model that predicts postoperative outcomes and costs after cardiac surgery.
The Society of Thoracic Surgeons registry data from 4874 patients who underwent cardiac surgery (56% coronary artery bypass grafting, 42% valve surgery, 19% aortic surgery) at our institution were divided into training (80%) and testing (20%) datasets. The Extreme Gradient Boosting decision-tree ML algorithms were trained to predict three outcomes: operative mortality, major morbidity or mortality, and Medicare outlier high hospitalization cost. Algorithm performance was determined using accuracy, F1 score, and area under the precision-recall curve (AUC-PR). The ML algorithms were validated in index surgery cases with The Society of Thoracic Surgeons risk scores for mortality and major morbidities and with logistic regression and were then applied to nonindex cases.
The ML algorithms with 25 input parameters predicted operative mortality (accuracy 95%; F1 0.31; AUC-PR 0.21), major morbidity or mortality (accuracy 71%, F1 0.47; AUC-PR 0.47), and high cost (accuracy 84%; F1 0.62; AUC-PR 0.65). Preoperative creatinine, complete blood count, patient height and weight, ventricular function, and liver dysfunction were important predictors for all outcomes. For patients undergoing nonindex cardiac operations, the ML model achieved an AUC-PR of 0.15 (95% CI, 0.05-0.32) for mortality and 0.59 (95% CI, 0.51-0.68) for major morbidity or mortality.
The extreme gradient boosting ML algorithms can predict mortality, major morbidity, and high cost after cardiac surgery, including operations without established risk models. These ML algorithms may refine risk prediction after cardiac surgery for a wide range of procedures.
[Display omitted] |
---|---|
AbstractList | BACKGROUNDMachine learning (ML) algorithms may enhance outcomes prediction and help guide clinical decision making. This study aimed to develop and validate a ML model that predicts postoperative outcomes and costs after cardiac surgery. METHODSThe Society of Thoracic Surgeons registry data from 4874 patients who underwent cardiac surgery (56% coronary artery bypass grafting, 42% valve surgery, 19% aortic surgery) at our institution were divided into training (80%) and testing (20%) datasets. The Extreme Gradient Boosting decision-tree ML algorithms were trained to predict three outcomes: operative mortality, major morbidity or mortality, and Medicare outlier high hospitalization cost. Algorithm performance was determined using accuracy, F1 score, and area under the precision-recall curve (AUC-PR). The ML algorithms were validated in index surgery cases with The Society of Thoracic Surgeons risk scores for mortality and major morbidities and with logistic regression and were then applied to nonindex cases. RESULTSThe ML algorithms with 25 input parameters predicted operative mortality (accuracy 95%; F1 0.31; AUC-PR 0.21), major morbidity or mortality (accuracy 71%, F1 0.47; AUC-PR 0.47), and high cost (accuracy 84%; F1 0.62; AUC-PR 0.65). Preoperative creatinine, complete blood count, patient height and weight, ventricular function, and liver dysfunction were important predictors for all outcomes. For patients undergoing nonindex cardiac operations, the ML model achieved an AUC-PR of 0.15 (95% CI, 0.05-0.32) for mortality and 0.59 (95% CI, 0.51-0.68) for major morbidity or mortality. CONCLUSIONSThe extreme gradient boosting ML algorithms can predict mortality, major morbidity, and high cost after cardiac surgery, including operations without established risk models. These ML algorithms may refine risk prediction after cardiac surgery for a wide range of procedures. Machine learning (ML) algorithms may enhance outcomes prediction and help guide clinical decision making. This study aimed to develop and validate a ML model that predicts postoperative outcomes and costs after cardiac surgery. The Society of Thoracic Surgeons registry data from 4874 patients who underwent cardiac surgery (56% coronary artery bypass grafting, 42% valve surgery, 19% aortic surgery) at our institution were divided into training (80%) and testing (20%) datasets. The Extreme Gradient Boosting decision-tree ML algorithms were trained to predict three outcomes: operative mortality, major morbidity or mortality, and Medicare outlier high hospitalization cost. Algorithm performance was determined using accuracy, F1 score, and area under the precision-recall curve (AUC-PR). The ML algorithms were validated in index surgery cases with The Society of Thoracic Surgeons risk scores for mortality and major morbidities and with logistic regression and were then applied to nonindex cases. The ML algorithms with 25 input parameters predicted operative mortality (accuracy 95%; F1 0.31; AUC-PR 0.21), major morbidity or mortality (accuracy 71%, F1 0.47; AUC-PR 0.47), and high cost (accuracy 84%; F1 0.62; AUC-PR 0.65). Preoperative creatinine, complete blood count, patient height and weight, ventricular function, and liver dysfunction were important predictors for all outcomes. For patients undergoing nonindex cardiac operations, the ML model achieved an AUC-PR of 0.15 (95% CI, 0.05-0.32) for mortality and 0.59 (95% CI, 0.51-0.68) for major morbidity or mortality. The extreme gradient boosting ML algorithms can predict mortality, major morbidity, and high cost after cardiac surgery, including operations without established risk models. These ML algorithms may refine risk prediction after cardiac surgery for a wide range of procedures. Machine learning (ML) algorithms may enhance outcomes prediction and help guide clinical decision making. This study aimed to develop and validate a ML model that predicts postoperative outcomes and costs after cardiac surgery. The Society of Thoracic Surgeons registry data from 4874 patients who underwent cardiac surgery (56% coronary artery bypass grafting, 42% valve surgery, 19% aortic surgery) at our institution were divided into training (80%) and testing (20%) datasets. The Extreme Gradient Boosting decision-tree ML algorithms were trained to predict three outcomes: operative mortality, major morbidity or mortality, and Medicare outlier high hospitalization cost. Algorithm performance was determined using accuracy, F1 score, and area under the precision-recall curve (AUC-PR). The ML algorithms were validated in index surgery cases with The Society of Thoracic Surgeons risk scores for mortality and major morbidities and with logistic regression and were then applied to nonindex cases. The ML algorithms with 25 input parameters predicted operative mortality (accuracy 95%; F1 0.31; AUC-PR 0.21), major morbidity or mortality (accuracy 71%, F1 0.47; AUC-PR 0.47), and high cost (accuracy 84%; F1 0.62; AUC-PR 0.65). Preoperative creatinine, complete blood count, patient height and weight, ventricular function, and liver dysfunction were important predictors for all outcomes. For patients undergoing nonindex cardiac operations, the ML model achieved an AUC-PR of 0.15 (95% CI, 0.05-0.32) for mortality and 0.59 (95% CI, 0.51-0.68) for major morbidity or mortality. The extreme gradient boosting ML algorithms can predict mortality, major morbidity, and high cost after cardiac surgery, including operations without established risk models. These ML algorithms may refine risk prediction after cardiac surgery for a wide range of procedures. [Display omitted] |
Author | Rosengart, Todd K. Ryan, Christopher T. Chatterjee, Subhasis Ghanta, Ravi K. Havelka, Jim Coselli, Joseph S. Navarro, Sergio M. Wall, Matthew J. Zea-Vera, Rodrigo |
Author_xml | – sequence: 1 givenname: Rodrigo 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: Sergio M. surname: Navarro fullname: Navarro, Sergio M. organization: Michael E. DeBakey Department of Surgery, Baylor College of Medicine, Houston, Texas – sequence: 4 givenname: Jim surname: Havelka fullname: Havelka, Jim organization: InformAI, Houston, Texas – sequence: 5 givenname: Matthew J. surname: Wall fullname: Wall, Matthew J. organization: Michael E. DeBakey Department of Surgery, Baylor College of Medicine, Houston, Texas – sequence: 6 givenname: Joseph S. surname: Coselli fullname: Coselli, Joseph S. organization: Michael E. DeBakey Department of Surgery, Baylor College of Medicine, Houston, Texas – sequence: 7 givenname: Todd K. surname: Rosengart fullname: Rosengart, Todd K. organization: Michael E. DeBakey Department of Surgery, Baylor College of Medicine, Houston, Texas – sequence: 8 givenname: Subhasis surname: Chatterjee fullname: Chatterjee, Subhasis organization: Michael E. DeBakey Department of Surgery, Baylor College of Medicine, Houston, Texas – sequence: 9 givenname: Ravi K. orcidid: 0000-0003-3299-2668 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/35917942$$D View this record in MEDLINE/PubMed |
BookMark | eNqFkMFO3DAQhi1EVRboKyAfuSS1ndiJj7C0UGkRlVouvVjOZAJeJfZiO0i8PUFL2yOn0Wi-f0bzHZNDHzwSQjkrOePq67a0-TFEC2mOpWBClEyVTMoDsuJSikIJqQ_JijFWFbVu5BE5Tmm7tGIZfyZHldS80bVYkT9X-Ixj2E3oMw0DtfTWwqPzSDdoo3f-gd6GHkeaA_0ZsXeQ6d2cIUyYqPU9XYeU6cWQMdK1jb2zQH_N8QHjyyn5NNgx4Zf3ekLuv3_7vb4pNnfXP9YXmwKqps6FsEzXmncA1iK0rJXIFegWre4UqIFXrRZd10LVVUx2bSdkpUWjtATZ93VTnZDz_d5dDE8zpmwmlwDH0XoMczJC6UY1shF6Qds9CjGkFHEwu-gmG18MZ-bNrNma_2bNm1nDlFnMLtGz9ytzN2H_L_hX5QJc7gFcfn12GE0Chx4WZxEhmz64j6-8AkTMkPM |
CitedBy_id | crossref_primary_10_1097_SLA_0000000000005853 crossref_primary_10_1152_ajplung_00250_2022 crossref_primary_10_1016_j_athoracsur_2023_04_019 crossref_primary_10_1016_j_health_2024_100351 crossref_primary_10_1016_j_jtcvs_2024_04_027 crossref_primary_10_1016_j_surg_2024_03_051 crossref_primary_10_1016_j_athoracsur_2022_07_026 crossref_primary_10_1016_j_jtcvs_2024_04_022 |
Cites_doi | 10.1016/j.athoracsur.2019.09.042 10.1016/j.jtcvs.2020.08.091 10.1213/ANE.0000000000004636 10.1016/j.jtcvs.2019.07.017 10.1097/SLA.0000000000002956 10.1016/j.athoracsur.2021.08.040 10.1097/CRD.0000000000000294 10.1016/j.jtcvs.2018.03.109 10.1016/j.jtcvs.2020.07.105 10.1016/j.athoracsur.2014.05.073 10.1038/s41746-018-0029-1 10.1001/jamanetworkopen.2019.6835 10.1093/ejcts/ezs043 10.1097/MLR.0000000000001204 10.1016/j.athoracsur.2021.08.028 10.1016/j.jtcvs.2005.12.055 10.1016/j.jacc.2018.03.521 10.1007/s40708-017-0065-7 10.1016/j.athoracsur.2019.09.049 10.1016/j.athoracsur.2018.12.022 10.1016/j.athoracsur.2021.03.043 10.1016/j.athoracsur.2019.11.003 10.3389/fgene.2019.00600 10.1016/S2213-2600(18)30300-X 10.1016/j.jtcvs.2012.07.055 |
ContentType | Journal Article |
Copyright | 2023 The Society of Thoracic Surgeons Copyright © 2023 The Society of Thoracic Surgeons. Published by Elsevier Inc. All rights reserved. |
Copyright_xml | – notice: 2023 The Society of Thoracic Surgeons – notice: Copyright © 2023 The Society of Thoracic Surgeons. Published by Elsevier Inc. All rights reserved. |
DBID | CGR CUY CVF ECM EIF NPM AAYXX CITATION 7X8 |
DOI | 10.1016/j.athoracsur.2022.06.055 |
DatabaseName | Medline MEDLINE MEDLINE (Ovid) MEDLINE MEDLINE PubMed CrossRef MEDLINE - Academic |
DatabaseTitle | MEDLINE Medline Complete MEDLINE with Full Text PubMed MEDLINE (Ovid) CrossRef MEDLINE - Academic |
DatabaseTitleList | MEDLINE - Academic MEDLINE |
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 – sequence: 2 dbid: EIF name: MEDLINE url: https://proxy.k.utb.cz/login?url=https://www.webofscience.com/wos/medline/basic-search sourceTypes: Index Database |
DeliveryMethod | fulltext_linktorsrc |
EISSN | 1552-6259 |
EndPage | 1542 |
ExternalDocumentID | 10_1016_j_athoracsur_2022_06_055 35917942 S0003497522009973 |
Genre | Journal Article |
GeographicLocations | United States |
GeographicLocations_xml | – name: United States |
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 CGR CUY CVF ECM EIF NPM AAYXX ACRPL ADNMO CITATION 7X8 |
ID | FETCH-LOGICAL-c374t-2a09491bccaaec8085e16c98ea9b6c6f13892bb8c3b305b8b253927695c5dd473 |
ISSN | 0003-4975 |
IngestDate | Tue Dec 03 23:24:09 EST 2024 Fri Dec 06 01:13:47 EST 2024 Sat Sep 28 08:16:29 EDT 2024 Fri Feb 23 02:40:21 EST 2024 |
IsPeerReviewed | true |
IsScholarly | true |
Issue | 6 |
Keywords | PROMM STS PROM XGBoost AUC-PR ROC CABG ML |
Language | English |
License | Copyright © 2023 The Society of Thoracic Surgeons. Published by Elsevier Inc. All rights reserved. |
LinkModel | OpenURL |
MergedId | FETCHMERGED-LOGICAL-c374t-2a09491bccaaec8085e16c98ea9b6c6f13892bb8c3b305b8b253927695c5dd473 |
Notes | ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 23 |
ORCID | 0000-0003-3299-2668 |
PMID | 35917942 |
PQID | 2697675729 |
PQPubID | 23479 |
PageCount | 10 |
ParticipantIDs | proquest_miscellaneous_2697675729 crossref_primary_10_1016_j_athoracsur_2022_06_055 pubmed_primary_35917942 elsevier_sciencedirect_doi_10_1016_j_athoracsur_2022_06_055 |
PublicationCentury | 2000 |
PublicationDate | June 2023 2023-06-00 20230601 |
PublicationDateYYYYMMDD | 2023-06-01 |
PublicationDate_xml | – month: 06 year: 2023 text: June 2023 |
PublicationDecade | 2020 |
PublicationPlace | Netherlands |
PublicationPlace_xml | – name: Netherlands |
PublicationTitle | The Annals of thoracic surgery |
PublicationTitleAlternate | Ann Thorac Surg |
PublicationYear | 2023 |
Publisher | Elsevier Inc |
Publisher_xml | – name: Elsevier Inc |
References | Johnson, Torres Soto, Glicksberg (bib4) 2018; 71 Patlolla, Schaff, Dearani, Stulak, Crestanello, Greason (bib17) 2022; 114 Chhabra, Nuliyalu, Dimick, Nathan (bib28) 2019; 57 Kilic (bib5) 2020; 109 LaPar, Hawkins, McMurry (bib27) 2018; 156 Zea-Vera, Ryan, Havelka (bib11) 2022; 114 Ji, Tong, Liu, Shi (bib20) 2019; 10 Mortazavi, Bucholz, Desai (bib9) 2019; 2 Fernandez (bib13) 2020; 109 Torlay, Perrone-Bertolotti, Thomas, Baciu (bib19) 2017; 4 Kennedy, LaPar, Kern (bib26) 2013; 146 Miller (bib30) 2020; 28 Meyer, Zverinski, Pfahringer (bib6) 2018; 6 Osnabrugge, Speir, Head (bib29) 2014; 98 Rajkomar, Oren, Chen (bib31) 2018; 1 Ghanta, LaPar, Zhang (bib15) 2017; 6 Bertsimas, Dunn, Velmahos, Kaafarani (bib8) 2018; 268 Ishwaran, Blackstone (bib23) 2022; 163 Bowdish, D'Agostino, Thourani (bib3) 2021; 111 O'Brien, Feng, He (bib1) 2018; 105 Centers for Medicare & Medicaid Services (bib18) Charles, Mehaffey, Hawkins (bib25) 2019; 107 Blackstone, Swain, McCardle, Adams (bib14) 2019; 158 Nilsson, Ohlsson, Thulin, Höglund, Nashef, Brandt (bib24) 2006; 132 Nashef, Roques, Sharples (bib2) 2012; 41 bib16 Chen, Guestrin (bib21) 2016 Benedetto, Dimagli, Sinha (bib12) 2022; 163 Solomon, Saxena, Neradilek (bib7) 2020; 130 Bergstra, Bengio (bib22) 2012; 13 Kilic, Goyal, Miller (bib10) 2020; 109 35921856 - Ann Thorac Surg. 2023 Jun;115(6):1542-1543 Ghanta (10.1016/j.athoracsur.2022.06.055_bib15) 2017; 6 Bergstra (10.1016/j.athoracsur.2022.06.055_bib22) 2012; 13 LaPar (10.1016/j.athoracsur.2022.06.055_bib27) 2018; 156 Zea-Vera (10.1016/j.athoracsur.2022.06.055_bib11) 2022; 114 Centers for Medicare & Medicaid Services (10.1016/j.athoracsur.2022.06.055_bib18) Nashef (10.1016/j.athoracsur.2022.06.055_bib2) 2012; 41 Ji (10.1016/j.athoracsur.2022.06.055_bib20) 2019; 10 Torlay (10.1016/j.athoracsur.2022.06.055_bib19) 2017; 4 Miller (10.1016/j.athoracsur.2022.06.055_bib30) 2020; 28 Meyer (10.1016/j.athoracsur.2022.06.055_bib6) 2018; 6 Kennedy (10.1016/j.athoracsur.2022.06.055_bib26) 2013; 146 Osnabrugge (10.1016/j.athoracsur.2022.06.055_bib29) 2014; 98 Charles (10.1016/j.athoracsur.2022.06.055_bib25) 2019; 107 Johnson (10.1016/j.athoracsur.2022.06.055_bib4) 2018; 71 Solomon (10.1016/j.athoracsur.2022.06.055_bib7) 2020; 130 Chhabra (10.1016/j.athoracsur.2022.06.055_bib28) 2019; 57 Nilsson (10.1016/j.athoracsur.2022.06.055_bib24) 2006; 132 Blackstone (10.1016/j.athoracsur.2022.06.055_bib14) 2019; 158 Kilic (10.1016/j.athoracsur.2022.06.055_bib5) 2020; 109 Benedetto (10.1016/j.athoracsur.2022.06.055_bib12) 2022; 163 Mortazavi (10.1016/j.athoracsur.2022.06.055_bib9) 2019; 2 Chen (10.1016/j.athoracsur.2022.06.055_bib21) 2016 Ishwaran (10.1016/j.athoracsur.2022.06.055_bib23) 2022; 163 Kilic (10.1016/j.athoracsur.2022.06.055_bib10) 2020; 109 Rajkomar (10.1016/j.athoracsur.2022.06.055_bib31) 2018; 1 Patlolla (10.1016/j.athoracsur.2022.06.055_bib17) 2022; 114 Bertsimas (10.1016/j.athoracsur.2022.06.055_bib8) 2018; 268 Fernandez (10.1016/j.athoracsur.2022.06.055_bib13) 2020; 109 O'Brien (10.1016/j.athoracsur.2022.06.055_bib1) 2018; 105 Bowdish (10.1016/j.athoracsur.2022.06.055_bib3) 2021; 111 |
References_xml | – volume: 6 year: 2017 ident: bib15 article-title: Obesity increases risk-adjusted morbidity, mortality, and cost following cardiac surgery publication-title: J Am Heart Assoc contributor: fullname: Zhang – volume: 146 start-page: 631 year: 2013 end-page: 637 ident: bib26 article-title: Does The Society of Thoracic Surgeons risk score accurately predict operative mortality for patients with pulmonary hypertension? publication-title: J Thorac Cardiovasc Surg contributor: fullname: Kern – 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: 111 start-page: 1770 year: 2021 end-page: 1780 ident: bib3 article-title: STS Adult Cardiac Surgery Database: 2021 update on outcomes, quality, and research publication-title: Ann Thorac Surg contributor: fullname: Thourani – volume: 6 start-page: 905 year: 2018 end-page: 914 ident: bib6 article-title: Machine learning for real-time prediction of complications in critical care: a retrospective study publication-title: Lancet Respir Med contributor: fullname: Pfahringer – volume: 109 start-page: 1811 year: 2020 end-page: 1819 ident: bib10 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: 156 start-page: 66 year: 2018 end-page: 74.e2 ident: bib27 article-title: Investigators for the Virginia Cardiac Services Quality Initiative. Preoperative anemia vs blood transfusion: which is the culprit for worse outcomes in cardiac surgery? publication-title: J Thorac Cardiovasc Surg contributor: fullname: McMurry – volume: 163 start-page: 2075 year: 2022 end-page: 2087 ident: bib12 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: 114 start-page: 711 year: 2022 end-page: 719 ident: bib11 article-title: Machine learning to predict outcomes and cost by phase of care after coronary artery bypass grafting publication-title: Ann Thorac Surg contributor: fullname: Havelka – 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: 132 start-page: 12 year: 2006 end-page: 19 ident: bib24 article-title: Risk factor identification and mortality prediction in cardiac surgery using artificial neural networks publication-title: J Thorac Cardiovasc Surg contributor: fullname: Brandt – volume: 98 start-page: 1286 year: 2014 end-page: 1293 ident: bib29 article-title: Prediction of costs and length of stay in coronary artery bypass grafting publication-title: Ann Thorac Surg contributor: fullname: Head – start-page: 785 year: 2016 end-page: 794 ident: bib21 article-title: XGBoost: a scalable tree boosting system publication-title: Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining contributor: fullname: Guestrin – volume: 114 start-page: 659 year: 2022 end-page: 666 ident: bib17 article-title: Aortic stenosis and coronary artery disease: cost of transcatheter vs surgical management publication-title: Ann Thorac Surg contributor: fullname: Greason – ident: bib18 article-title: FY 2019 final rule and correction notice data files contributor: fullname: Centers for Medicare & Medicaid Services – volume: 268 start-page: 574 year: 2018 end-page: 583 ident: bib8 article-title: Surgical risk is not linear: derivation and validation of a novel, user-friendly, and machine-learning-based Predictive Optimal Trees in Emergency Surgery Risk (POTTER) calculator publication-title: Ann Surg contributor: fullname: Kaafarani – volume: 109 start-page: 1323 year: 2020 end-page: 1329 ident: bib5 article-title: Artificial intelligence and machine learning in cardiovascular health care publication-title: Ann Thorac Surg contributor: fullname: Kilic – volume: 71 start-page: 2668 year: 2018 end-page: 2679 ident: bib4 article-title: Artificial intelligence in cardiology publication-title: J Am Coll Cardiol contributor: fullname: Glicksberg – volume: 13 start-page: 281 year: 2012 end-page: 305 ident: bib22 article-title: Random search for hyper-parameter optimization publication-title: J Mach Learn Res contributor: fullname: Bengio – volume: 163 start-page: 2088 year: 2022 end-page: 2090 ident: bib23 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: 1706 year: 2019 end-page: 1712 ident: bib25 article-title: Investigators for the Virginia Cardiac Services Quality Initiative. Socioeconomic Distressed Communities Index predicts risk-adjusted mortality after cardiac surgery publication-title: Ann Thorac Surg contributor: fullname: Hawkins – volume: 57 start-page: 869 year: 2019 end-page: 874 ident: bib28 article-title: Who will be the costliest patients? Using recent claims to predict expensive surgical episodes publication-title: Med Care contributor: fullname: Nathan – ident: bib16 article-title: Adult Cardiac Surgery Database data collection – volume: 130 start-page: 1201 year: 2020 end-page: 1210 ident: bib7 article-title: Forecasting a crisis: machine-learning models predict occurrence of intraoperative bradycardia associated with hypotension publication-title: Anesth Analg contributor: fullname: Neradilek – volume: 109 start-page: 10 year: 2020 end-page: 13 ident: bib13 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: 158 start-page: 1120 year: 2019 end-page: 1126 ident: bib14 article-title: Governance Committee, American Association for Thoracic Surgery Quality Assessment Program. A comprehensive American Association for Thoracic Surgery quality program for the 21st century publication-title: J Thorac Cardiovasc Surg contributor: fullname: Adams – volume: 10 start-page: 600 year: 2019 ident: bib20 article-title: Five-feature model for developing the classifier for synergistic vs. antagonistic drug combinations built by XGBoost publication-title: Front Genet contributor: fullname: Shi – volume: 28 start-page: 53 year: 2020 end-page: 64 ident: bib30 article-title: Machine intelligence in cardiovascular medicine publication-title: Cardiol Rev contributor: fullname: Miller – volume: 2 year: 2019 ident: bib9 article-title: Comparison of machine learning methods with national cardiovascular data registry models for prediction of risk of bleeding after percutaneous coronary intervention publication-title: JAMA Netw Open contributor: fullname: Desai – volume: 1 start-page: 18 year: 2018 ident: bib31 article-title: Scalable and accurate deep learning with electronic health records publication-title: NPJ Digit Med contributor: fullname: Chen – volume: 4 start-page: 159 year: 2017 end-page: 169 ident: bib19 article-title: Machine learning-XGBoost analysis of language networks to classify patients with epilepsy publication-title: Brain Inform contributor: fullname: Baciu – volume: 109 start-page: 1323 year: 2020 ident: 10.1016/j.athoracsur.2022.06.055_bib5 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: 105 start-page: 1419 year: 2018 ident: 10.1016/j.athoracsur.2022.06.055_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: O'Brien – volume: 163 start-page: 2088 year: 2022 ident: 10.1016/j.athoracsur.2022.06.055_bib23 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: 130 start-page: 1201 year: 2020 ident: 10.1016/j.athoracsur.2022.06.055_bib7 article-title: Forecasting a crisis: machine-learning models predict occurrence of intraoperative bradycardia associated with hypotension publication-title: Anesth Analg doi: 10.1213/ANE.0000000000004636 contributor: fullname: Solomon – volume: 158 start-page: 1120 year: 2019 ident: 10.1016/j.athoracsur.2022.06.055_bib14 article-title: Governance Committee, American Association for Thoracic Surgery Quality Assessment Program. A comprehensive American Association for Thoracic Surgery quality program for the 21st century publication-title: J Thorac Cardiovasc Surg doi: 10.1016/j.jtcvs.2019.07.017 contributor: fullname: Blackstone – start-page: 785 year: 2016 ident: 10.1016/j.athoracsur.2022.06.055_bib21 article-title: XGBoost: a scalable tree boosting system contributor: fullname: Chen – volume: 268 start-page: 574 year: 2018 ident: 10.1016/j.athoracsur.2022.06.055_bib8 article-title: Surgical risk is not linear: derivation and validation of a novel, user-friendly, and machine-learning-based Predictive Optimal Trees in Emergency Surgery Risk (POTTER) calculator publication-title: Ann Surg doi: 10.1097/SLA.0000000000002956 contributor: fullname: Bertsimas – volume: 114 start-page: 711 year: 2022 ident: 10.1016/j.athoracsur.2022.06.055_bib11 article-title: Machine learning to predict outcomes and cost by phase of care after coronary artery bypass grafting publication-title: Ann Thorac Surg doi: 10.1016/j.athoracsur.2021.08.040 contributor: fullname: Zea-Vera – volume: 28 start-page: 53 year: 2020 ident: 10.1016/j.athoracsur.2022.06.055_bib30 article-title: Machine intelligence in cardiovascular medicine publication-title: Cardiol Rev doi: 10.1097/CRD.0000000000000294 contributor: fullname: Miller – volume: 156 start-page: 66 year: 2018 ident: 10.1016/j.athoracsur.2022.06.055_bib27 article-title: Investigators for the Virginia Cardiac Services Quality Initiative. Preoperative anemia vs blood transfusion: which is the culprit for worse outcomes in cardiac surgery? publication-title: J Thorac Cardiovasc Surg doi: 10.1016/j.jtcvs.2018.03.109 contributor: fullname: LaPar – volume: 163 start-page: 2075 year: 2022 ident: 10.1016/j.athoracsur.2022.06.055_bib12 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: 98 start-page: 1286 year: 2014 ident: 10.1016/j.athoracsur.2022.06.055_bib29 article-title: Prediction of costs and length of stay in coronary artery bypass grafting publication-title: Ann Thorac Surg doi: 10.1016/j.athoracsur.2014.05.073 contributor: fullname: Osnabrugge – volume: 1 start-page: 18 year: 2018 ident: 10.1016/j.athoracsur.2022.06.055_bib31 article-title: Scalable and accurate deep learning with electronic health records publication-title: NPJ Digit Med doi: 10.1038/s41746-018-0029-1 contributor: fullname: Rajkomar – volume: 2 year: 2019 ident: 10.1016/j.athoracsur.2022.06.055_bib9 article-title: Comparison of machine learning methods with national cardiovascular data registry models for prediction of risk of bleeding after percutaneous coronary intervention publication-title: JAMA Netw Open doi: 10.1001/jamanetworkopen.2019.6835 contributor: fullname: Mortazavi – volume: 6 year: 2017 ident: 10.1016/j.athoracsur.2022.06.055_bib15 article-title: Obesity increases risk-adjusted morbidity, mortality, and cost following cardiac surgery publication-title: J Am Heart Assoc contributor: fullname: Ghanta – volume: 41 start-page: 734 year: 2012 ident: 10.1016/j.athoracsur.2022.06.055_bib2 article-title: EuroSCORE II publication-title: Eur J Cardiothorac Surg doi: 10.1093/ejcts/ezs043 contributor: fullname: Nashef – volume: 57 start-page: 869 year: 2019 ident: 10.1016/j.athoracsur.2022.06.055_bib28 article-title: Who will be the costliest patients? Using recent claims to predict expensive surgical episodes publication-title: Med Care doi: 10.1097/MLR.0000000000001204 contributor: fullname: Chhabra – volume: 114 start-page: 659 year: 2022 ident: 10.1016/j.athoracsur.2022.06.055_bib17 article-title: Aortic stenosis and coronary artery disease: cost of transcatheter vs surgical management publication-title: Ann Thorac Surg doi: 10.1016/j.athoracsur.2021.08.028 contributor: fullname: Patlolla – volume: 132 start-page: 12 year: 2006 ident: 10.1016/j.athoracsur.2022.06.055_bib24 article-title: Risk factor identification and mortality prediction in cardiac surgery using artificial neural networks publication-title: J Thorac Cardiovasc Surg doi: 10.1016/j.jtcvs.2005.12.055 contributor: fullname: Nilsson – volume: 71 start-page: 2668 year: 2018 ident: 10.1016/j.athoracsur.2022.06.055_bib4 article-title: Artificial intelligence in cardiology publication-title: J Am Coll Cardiol doi: 10.1016/j.jacc.2018.03.521 contributor: fullname: Johnson – volume: 4 start-page: 159 year: 2017 ident: 10.1016/j.athoracsur.2022.06.055_bib19 article-title: Machine learning-XGBoost analysis of language networks to classify patients with epilepsy publication-title: Brain Inform doi: 10.1007/s40708-017-0065-7 contributor: fullname: Torlay – ident: 10.1016/j.athoracsur.2022.06.055_bib18 contributor: fullname: Centers for Medicare & Medicaid Services – volume: 109 start-page: 1811 year: 2020 ident: 10.1016/j.athoracsur.2022.06.055_bib10 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 – volume: 107 start-page: 1706 year: 2019 ident: 10.1016/j.athoracsur.2022.06.055_bib25 article-title: Investigators for the Virginia Cardiac Services Quality Initiative. Socioeconomic Distressed Communities Index predicts risk-adjusted mortality after cardiac surgery publication-title: Ann Thorac Surg doi: 10.1016/j.athoracsur.2018.12.022 contributor: fullname: Charles – volume: 111 start-page: 1770 year: 2021 ident: 10.1016/j.athoracsur.2022.06.055_bib3 article-title: STS Adult Cardiac Surgery Database: 2021 update on outcomes, quality, and research publication-title: Ann Thorac Surg doi: 10.1016/j.athoracsur.2021.03.043 contributor: fullname: Bowdish – volume: 13 start-page: 281 year: 2012 ident: 10.1016/j.athoracsur.2022.06.055_bib22 article-title: Random search for hyper-parameter optimization publication-title: J Mach Learn Res contributor: fullname: Bergstra – volume: 109 start-page: 10 year: 2020 ident: 10.1016/j.athoracsur.2022.06.055_bib13 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: 10 start-page: 600 year: 2019 ident: 10.1016/j.athoracsur.2022.06.055_bib20 article-title: Five-feature model for developing the classifier for synergistic vs. antagonistic drug combinations built by XGBoost publication-title: Front Genet doi: 10.3389/fgene.2019.00600 contributor: fullname: Ji – volume: 6 start-page: 905 year: 2018 ident: 10.1016/j.athoracsur.2022.06.055_bib6 article-title: Machine learning for real-time prediction of complications in critical care: a retrospective study publication-title: Lancet Respir Med doi: 10.1016/S2213-2600(18)30300-X contributor: fullname: Meyer – volume: 146 start-page: 631 year: 2013 ident: 10.1016/j.athoracsur.2022.06.055_bib26 article-title: Does The Society of Thoracic Surgeons risk score accurately predict operative mortality for patients with pulmonary hypertension? publication-title: J Thorac Cardiovasc Surg doi: 10.1016/j.jtcvs.2012.07.055 contributor: fullname: Kennedy |
SSID | ssj0002155 |
Score | 2.4956264 |
Snippet | Machine learning (ML) algorithms may enhance outcomes prediction and help guide clinical decision making. This study aimed to develop and validate a ML model... BACKGROUNDMachine learning (ML) algorithms may enhance outcomes prediction and help guide clinical decision making. This study aimed to develop and validate a... |
SourceID | proquest crossref pubmed elsevier |
SourceType | Aggregation Database Index Database Publisher |
StartPage | 1533 |
SubjectTerms | Aged Cardiac Surgical Procedures - adverse effects Coronary Artery Bypass - methods Humans Machine Learning Medicare Thoracic Surgery United States - epidemiology |
Title | Development of a Machine Learning Model to Predict Outcomes and Cost After Cardiac Surgery |
URI | https://dx.doi.org/10.1016/j.athoracsur.2022.06.055 https://www.ncbi.nlm.nih.gov/pubmed/35917942 https://search.proquest.com/docview/2697675729 |
Volume | 115 |
hasFullText | 1 |
inHoldings | 1 |
isFullTextHit | |
isPrint | |
link | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwnV1bb9MwFLZK98ILYuJWYMhIvEWpGse5iaeqAk1MBYQ6MfES2Y4zOiBBbYoEf2V_dufYTpqNToy9RFWURrbPl-PvHJ8LIa_iVMH4Su7zFF038STzZcoCH7tuM6kSkXDMd56_jw-P-buT6GQwOO9FLW0aOVZ_duaV3EaqcA_kilmy_yHZ7qVwA36DfOEKEobrjWTci_ixeY5zExqp26qpp6bV2Xfklx9XeCLTeB82DYxE28rMs3rdeFPTJXxmkKJAkfyVJm36Nnd1lpuvABq1VN669yR6nrVA56DlonUBRn_dHeb8FtWVQgbeYty5ocUvLARp3LB6dbqsvfl4qxdhgt9sOO_yR99DwcJtJFWndUPsZBdd0ro2i9PBq69DkYH29mPgeGynrrduhzNYcjNxmDWY-4yZcqy29O_l8tpXtr0uGLGNczvLt2_K8U05hvxF0R2yh1UW-ZDsTY8-fT7qNnpgS1HbkBGn5wLFbPjg7lFdx36us24My1ncJ_eceUKnFmv7ZKCrB-RLD2e0LqmgDme0xRk1OKNNTR3OaIszCjijiDNqcEYdzqjD2UNy_PbNYnbou54cvgoT3vhMTDKeBRI-fKFVCoRdB7HKUi0yGau4xHNvJmWqQgk7iUwli4CBJ3EWqagoeBI-IsOqrvQTQstEA3lOJsWkAFpblKLkYQnWS1DoJMkEH5GgXav8py29kv9LViPyul3U3FFISw1zQM0N_v2ylUMOWhaPzkSl6806Z3GGVY_AEh2Rx1ZA3ZjCKMNdjT29xXifkbvbL-Y5GTarjT4AltvIFw5tFycYqj4 |
link.rule.ids | 314,780,784,27924,27925 |
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=Development+of+a+Machine+Learning+Model+to+Predict+Outcomes+and+Cost+After+Cardiac+Surgery&rft.jtitle=The+Annals+of+thoracic+surgery&rft.au=Zea-Vera%2C+Rodrigo&rft.au=Ryan%2C+Christopher+T.&rft.au=Navarro%2C+Sergio+M.&rft.au=Havelka%2C+Jim&rft.date=2023-06-01&rft.issn=0003-4975&rft.volume=115&rft.issue=6&rft.spage=1533&rft.epage=1542&rft_id=info:doi/10.1016%2Fj.athoracsur.2022.06.055&rft.externalDBID=n%2Fa&rft.externalDocID=10_1016_j_athoracsur_2022_06_055 |
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 |