{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,2]],"date-time":"2026-11-02T18:19:09Z","timestamp":1793643549067,"version":"4.5.1"},"reference-count":30,"publisher":"Oxford University Press (OUP)","issue":"6","license":[{"start":{"date-parts":[[2021,5,29]],"date-time":"2021-05-29T00:00:00Z","timestamp":1622246400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/academic.oup.com\/journals\/pages\/open_access\/funder_policies\/chorus\/standard_publication_model"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021,12,1]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>\u2002<\/jats:title>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>OBJECTIVES<\/jats:title>\n                    <jats:p>Machine learning methods potentially provide a highly accurate and detailed assessment of expected individual patient risk before elective cardiac surgery. Correct anticipation of this risk allows for the improved counselling of patients and avoidance of possible complications. We therefore investigated the benefit of modern machine learning methods in personalized risk prediction for patients undergoing elective heart valve surgery.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>METHODS<\/jats:title>\n                    <jats:p>We performed a monocentric retrospective study in patients who underwent elective heart valve surgery between 1 January 2008 and 31 December 2014 at our centre. We used random forests, artificial neural networks and support vector machines to predict the 30-day mortality from a subset of 129 available demographic and preoperative parameters. Exclusion criteria were reoperation of the same patient, patients who needed anterograde cerebral perfusion due to aortic arch surgery and patients with grown-up congenital heart disease. Finally, the cohort consisted of 2229 patients with a 30-day mortality of 3.86% (86 of 2229 cases). This trial has been registered at clinicaltrials.gov (NCT03724123).<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>RESULTS<\/jats:title>\n                    <jats:p>The final random forest model trained on the entire data set provided an out-of-bag area under the receiver operator characteristics curve (AUC) of 0.839, which significantly outperformed the European System for Cardiac Operative Risk Evaluation (EuroSCORE) (AUC = 0.704) and a model trained only on the subset of features EuroSCORE uses (AUC = 0.745).<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>CONCLUSIONS<\/jats:title>\n                    <jats:p>Advanced machine learning methods can predict outcomes of valve surgery procedures with higher accuracy than established risk scores based on logistic regression on pre-selected parameters. This approach is generalizable to other elective high-risk interventions and allows for training models to the cohorts of specific institutions<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1093\/ejcts\/ezab219","type":"journal-article","created":{"date-parts":[[2021,5,6]],"date-time":"2021-05-06T07:28:35Z","timestamp":1620286115000},"page":"1378-1385","source":"Crossref","is-referenced-by-count":25,"title":["Machine learning-based risk profile classification of patients undergoing elective heart valve surgery"],"prefix":"10.1093","volume":"60","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6859-8828","authenticated-orcid":false,"given":"Ulrich","family":"Bodenhofer","sequence":"first","affiliation":[{"name":"School of Informatics, Communications and Media, University of Applied Sciences Upper Austria, Hagenberg, Austria"},{"name":"Institute for Machine Learning, Johannes Kepler University, Linz, Austria"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bettina","family":"Haslinger-Eisterer","sequence":"additional","affiliation":[{"name":"Institute of Anesthesiology and Critical Care Medicine, Kepler University Clinic, Kepler University Linz, Linz, Austria"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Alexander","family":"Minichmayer","sequence":"additional","affiliation":[{"name":"Institute of Anesthesiology and Critical Care Medicine, Kepler University Clinic, Kepler University Linz, Linz, Austria"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Georg","family":"Hermanutz","sequence":"additional","affiliation":[{"name":"Institute for Machine Learning, Johannes Kepler University, Linz, Austria"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8727-2257","authenticated-orcid":false,"given":"Jens","family":"Meier","sequence":"additional","affiliation":[{"name":"Institute of Anesthesiology and Critical Care Medicine, Kepler University Clinic, Kepler University Linz, Linz, Austria"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"286","published-online":{"date-parts":[[2021,5,29]]},"reference":[{"key":"2021120506081039100_ezab219-B1","doi-asserted-by":"crossref","first-page":"9","DOI":"10.1016\/S1010-7940(99)00134-7","article-title":"European system for cardiac operative risk evaluation (EuroSCORE)","volume":"16","author":"Nashef","year":"1999","journal-title":"Eur J Cardiothorac Surg"},{"key":"2021120506081039100_ezab219-B2","doi-asserted-by":"crossref","first-page":"881","DOI":"10.1016\/S0195-668X(02)00799-6","article-title":"The logistic EuroSCORE","volume":"24","author":"Roques","year":"2003","journal-title":"Eur Heart J"},{"key":"2021120506081039100_ezab219-B3","doi-asserted-by":"crossref","first-page":"734","DOI":"10.1093\/ejcts\/ezs043","article-title":"EuroSCORE II","volume":"41","author":"Nashef","year":"2012","journal-title":"Eur J Cardiothorac Surg"},{"key":"2021120506081039100_ezab219-B4","first-page":"I3","article-title":"A method of uniform stratification of risk for evaluating the results of surgery in acquired adult heart disease","volume":"79","author":"Parsonnet","year":"1989","journal-title":"Circulation"},{"key":"2021120506081039100_ezab219-B5","doi-asserted-by":"crossref","first-page":"921","DOI":"10.1016\/j.athoracsur.2007.11.074","article-title":"Do we need separate risk stratification models for hospital mortality after heart valve surgery?","volume":"85","author":"van Gameren","year":"2008","journal-title":"Ann Thorac Surg"},{"key":"2021120506081039100_ezab219-B6","doi-asserted-by":"crossref","first-page":"199","DOI":"10.1016\/S1010-7940(01)01117-4","article-title":"Inaccuracy of four coronary surgery risk-adjusted models to predict mortality in individual patients","volume":"21","author":"Pinna-Pintor","year":"2002","journal-title":"Eur J Cardiothorac Surg"},{"key":"2021120506081039100_ezab219-B7","doi-asserted-by":"crossref","first-page":"468","DOI":"10.1016\/j.athoracsur.2009.04.059","article-title":"Society of Thoracic Surgeons score is superior to the EuroSCORE determining mortality in high risk patients undergoing isolated aortic valve replacement","volume":"88","author":"Wendt","year":"2009","journal-title":"Ann Thorac Surg"},{"key":"2021120506081039100_ezab219-B8","doi-asserted-by":"crossref","first-page":"2353","DOI":"10.1001\/jama.2017.16619","article-title":"Benefits and risks of machine learning decision support systems","volume":"318","author":"Berner","year":"2017","journal-title":"JAMA"},{"key":"2021120506081039100_ezab219-B9","doi-asserted-by":"crossref","first-page":"517","DOI":"10.1001\/jama.2017.7797","article-title":"Unintended consequences of machine learning in medicine","volume":"318","author":"Cabitza","year":"2017","journal-title":"JAMA"},{"key":"2021120506081039100_ezab219-B10","doi-asserted-by":"crossref","first-page":"115","DOI":"10.1038\/nature21056","article-title":"Dermatologist-level classification of skin cancer with deep neural networks","volume":"542","author":"Esteva","year":"2017","journal-title":"Nature"},{"key":"2021120506081039100_ezab219-B11","doi-asserted-by":"crossref","first-page":"1589","DOI":"10.1109\/JBHI.2017.2767063","article-title":"Deep EHR: a survey of recent advances in deep learning techniques for electronic health record (EHR)","volume":"22","author":"Shickel","year":"2018","journal-title":"IEEE J Biomed Health Inform"},{"key":"2021120506081039100_ezab219-B12","doi-asserted-by":"crossref","first-page":"164","DOI":"10.1200\/JCO.2017.35.4_suppl.164","article-title":"Superior prognosis prediction performance of deep learning for gastric cancer compared to Yonsei prognosis prediction model using Cox regression","volume":"35","author":"Hyung","year":"2017","journal-title":"JCO"},{"key":"2021120506081039100_ezab219-B13","doi-asserted-by":"crossref","first-page":"239","DOI":"10.1097\/00000542-197810000-00003","article-title":"ASA physical status classifications: a study of consistency of ratings","volume":"49","author":"Owens","year":"1978","journal-title":"Anesthesiology"},{"key":"2021120506081039100_ezab219-B14","doi-asserted-by":"crossref","first-page":"180","DOI":"10.1093\/ejcts\/ezv168","article-title":"Statistical and data reporting guidelines for the European Journal of Cardiothoracic Surgery and the Interactive Cardiovascular and Thoracic Surgery","volume":"48","author":"Hickey","year":"2015","journal-title":"Eur J Cardiothorac Surg"},{"key":"2021120506081039100_ezab219-B15","doi-asserted-by":"crossref","first-page":"112","DOI":"10.1093\/bioinformatics\/btr597","article-title":"MissForest\u2014non-parametric missing value imputation for mixed-type data","volume":"28","author":"Stekhofen","year":"2012","journal-title":"Bioinformatics"},{"key":"2021120506081039100_ezab219-B16","doi-asserted-by":"crossref","first-page":"1086","DOI":"10.1016\/j.ejcts.2009.11.021","article-title":"A preoperative risk prediction model for 30-day mortality following cardiac surgery in an Australian cohort","volume":"37","author":"Billah","year":"2010","journal-title":"Eur J Cardiothorac Surg"},{"key":"2021120506081039100_ezab219-B17","doi-asserted-by":"crossref","first-page":"482","DOI":"10.1016\/S0003-4975(03)00350-3","article-title":"Is 30-day mortality an adequate outcome statistic for patients considering heart valve replacement?","volume":"76","author":"Edwards","year":"2003","journal-title":"Ann Thorac Surg"},{"key":"2021120506081039100_ezab219-B18","doi-asserted-by":"crossref","first-page":"5","DOI":"10.1023\/A:1010933404324","article-title":"Random forests","volume":"45","author":"Breiman","year":"2001","journal-title":"Mach Learn"},{"key":"2021120506081039100_ezab219-B19","doi-asserted-by":"crossref","first-page":"436","DOI":"10.1038\/nature14539","article-title":"Deep learning","volume":"521","author":"LeCun","year":"2015","journal-title":"Nature"},{"key":"2021120506081039100_ezab219-B20","doi-asserted-by":"crossref","first-page":"1472","DOI":"10.1162\/neco.2006.18.6.1472","article-title":"Support vector machines for dyadic data","volume":"18","author":"Hochreiter","year":"2006","journal-title":"Neural Comput"},{"key":"2021120506081039100_ezab219-B21","doi-asserted-by":"crossref","first-page":"267","DOI":"10.1111\/j.2517-6161.1996.tb02080.x","article-title":"Regression shrinkage and selection via the Lasso","volume":"58","author":"Tibshirani","year":"1996","journal-title":"J R Statist Soc B"},{"key":"2021120506081039100_ezab219-B22","doi-asserted-by":"crossref","first-page":"837","DOI":"10.2307\/2531595","article-title":"Comparing areas under two or more correlated receiver operating characteristics curves: a nonparamentric approach","volume":"44","author":"DeLong","year":"1988","journal-title":"Biometrics"},{"key":"2021120506081039100_ezab219-B23","doi-asserted-by":"crossref","first-page":"61","DOI":"10.1007\/BF03007718","article-title":"A simple classification of the risk in cardiac surgery","volume":"30","author":"Paiement","year":"1983","journal-title":"Can Anaesth Soc J"},{"key":"2021120506081039100_ezab219-B24","doi-asserted-by":"crossref","first-page":"1574","DOI":"10.1016\/j.amjcard.2016.08.024","article-title":"Meta-analysis comparing established risk prediction models (EuroSCORE II, STS Score, and ACEF Score) for perioperative mortality during cardiac surgery","volume":"118","author":"Sullivan","year":"2016","journal-title":"Am J Cardiol"},{"key":"2021120506081039100_ezab219-B25","doi-asserted-by":"crossref","first-page":"S23","DOI":"10.1016\/j.athoracsur.2009.05.056","article-title":"The Society of Thoracic Surgeons 2008 cardiac surgery risk models: part 2\u2014isolated valve surgery","volume":"88","author":"O'Brien","year":"2009","journal-title":"Ann Thorac Surg"},{"key":"2021120506081039100_ezab219-B26","doi-asserted-by":"crossref","first-page":"3053","DOI":"10.1161\/CIRCULATIONAHA.108.842393","article-title":"Risk of assessing mortality risk in elective cardiac operations: age, creatinine, ejection fraction, and the law of parsimony","volume":"119","author":"Ranucci","year":"2009","journal-title":"Circulation"},{"key":"2021120506081039100_ezab219-B27","doi-asserted-by":"crossref","first-page":"417","DOI":"10.1016\/j.ijcard.2016.04.110","article-title":"Multimorbidity is strongly associated with long-term but not short-term mortality after cardiac valve replacement","volume":"215","author":"Krishnaswami","year":"2016","journal-title":"Int J Cardiol"},{"key":"2021120506081039100_ezab219-B28","doi-asserted-by":"crossref","first-page":"495","DOI":"10.5603\/CJ.a2015.0028","article-title":"Mortality in low- and very low-risk patients undergoing cardiac surgery: evaluation according to the EuroSCORE II as a new standard","volume":"22","author":"Borracci","year":"2015","journal-title":"Cardiol J"},{"key":"2021120506081039100_ezab219-B29","doi-asserted-by":"crossref","first-page":"539","DOI":"10.1093\/icvts\/ivt550","article-title":"Prospective validation of EuroSCORE II in patients undergoing cardiac surgery in Argentinean centres","volume":"18","author":"Borracci","year":"2014","journal-title":"Interact CardioVasc Thorac Surg"},{"key":"2021120506081039100_ezab219-B30","first-page":"22","article-title":"Investigating interpersonal competencies of cardiac surgery teams","volume":"49","author":"Fleming","year":"2006","journal-title":"Can J Surg"}],"container-title":["European Journal of Cardio-Thoracic Surgery"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/ejcts\/article-pdf\/60\/6\/1378\/41431955\/ezab219.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/ejcts\/article-pdf\/60\/6\/1378\/41431955\/ezab219.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,30]],"date-time":"2024-08-30T03:56:01Z","timestamp":1724990161000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/ejcts\/article\/60\/6\/1378\/6288030"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,5,29]]},"references-count":30,"journal-issue":{"issue":"6","published-online":{"date-parts":[[2021,5,29]]},"published-print":{"date-parts":[[2021,12,1]]}},"URL":"https:\/\/doi.org\/10.1093\/ejcts\/ezab219","relation":{},"ISSN":["1010-7940","1873-734X"],"issn-type":[{"value":"1010-7940","type":"print"},{"value":"1873-734X","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2021,12,1]]},"published":{"date-parts":[[2021,5,29]]}}}