{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,24]],"date-time":"2026-08-24T09:22:58Z","timestamp":1787563378270,"version":"build-2736575974"},"reference-count":32,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2022,7,13]],"date-time":"2022-07-13T00:00:00Z","timestamp":1657670400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Cardiovasc. Med."],"abstract":"<jats:p>Cardiogenic shock (CS) is a severe condition with in-hospital mortality of up to 50%. Patients who develop CS may have previous cardiac history, but that may not always be the case, adding to the challenges in optimally identifying and managing these patients. Patients may present to a medical facility with CS or develop CS while in the emergency department (ED), in a general inpatient ward (WARD) or in the critical care unit (CC). While different clinical pathways for management exist once CS is recognized, there are challenges in identifying the patients in a timely manner, in all settings, in a timeframe that will allow proper management. We therefore developed and evaluated retrospectively a machine learning model based on the XGBoost (XGB) algorithm which runs automatically on patient data from the electronic health record (EHR). The algorithm was trained on 8 years of de-identified data (from 2010 to 2017) collected from a large regional healthcare system. The input variables include demographics, vital signs, laboratory values, some orders, and specific pre-existing diagnoses. The model was designed to make predictions 2 h prior to the need of first CS intervention (inotrope, vasopressor, or mechanical circulatory support). The algorithm achieves an overall area under curve (AUC) of 0.87 (0.81 in CC, 0.84 in ED, 0.97 in WARD), which is considered useful for clinical use. The algorithm can be refined based on specific elements defining patient subpopulations, for example presence of acute myocardial infarction (AMI) or congestive heart failure (CHF), further increasing its precision when a patient has these conditions. The top-contributing risk factors learned by the model are consistent with existing clinical findings. Our conclusion is that a useful machine learning model can be used to predict the development of CS. This manuscript describes the main steps of the development process and our results.<\/jats:p>","DOI":"10.3389\/fcvm.2022.862424","type":"journal-article","created":{"date-parts":[[2022,7,13]],"date-time":"2022-07-13T01:14:42Z","timestamp":1657674882000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":32,"title":["Early Prediction of Cardiogenic Shock Using Machine Learning"],"prefix":"10.3389","volume":"9","author":[{"given":"Yale","family":"Chang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Corneliu","family":"Antonescu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shreyas","family":"Ravindranath","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Junzi","family":"Dong","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mingyu","family":"Lu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Francesco","family":"Vicario","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lisa","family":"Wondrely","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Pam","family":"Thompson","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dennis","family":"Swearingen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Deepak","family":"Acharya","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2022,7,13]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"278","DOI":"10.1016\/j.jacc.2016.10.022","article-title":"Percutaneous mechanical circulatory support versus intra-aortic balloon pump in cardiogenic shock after acute myocardial infarction","volume":"69","author":"Ouweneel","year":"2017","journal-title":"J Am Coll Cardiol"},{"key":"B2","doi-asserted-by":"publisher","first-page":"29","DOI":"10.1002\/ccd.28329","article-title":"SCAI clinical expert consensus statement on the classification of cardiogenic shock: this document was endorsed by the American College of Cardiology (ACC), the American Heart Association (AHA), the Society of Critical Care Medicine (SCCM), and the Society of Thoracic Surgeons (STS) in April (2019)","volume":"94","author":"Baran","year":"2019","journal-title":"Catheteriz Cardiovasc Interv"},{"key":"B3","doi-asserted-by":"publisher","first-page":"255","DOI":"10.1097\/CRD.0000000000000190","article-title":"Predictors of outcomes in myocardial infarction and cardiogenic shock","volume":"26","author":"Acharya","year":"2018","journal-title":"Cardiol Rev"},{"key":"B4","doi-asserted-by":"publisher","first-page":"879","DOI":"10.1016\/j.jchf.2020.09.005","article-title":"A standardized and comprehensive approach to the management of cardiogenic shock","volume":"8","author":"Tehrani","year":"2020","journal-title":"JACC Heart Fail"},{"key":"B5","doi-asserted-by":"publisher","first-page":"47","DOI":"10.7326\/0003-4819-131-1-199907060-00010","article-title":"Cardiogenic shock","volume":"131","author":"Hollenberg","year":"1999","journal-title":"Ann Internal Med"},{"key":"B6","doi-asserted-by":"publisher","first-page":"668","DOI":"10.1016\/0735-1097(95)00215-P","article-title":"Contemporary reperfusion therapy for cardiogenic shock: the GUSTO-I trial experience","volume":"26","author":"Holmes","year":"1995","journal-title":"J Am Coll Cardiol"},{"key":"B7","doi-asserted-by":"crossref","first-page":"p. 161","DOI":"10.1145\/1143844.1143865","article-title":"An empirical comparison of supervised learning algorithms","volume-title":"Proceedings of the 23rd International Conference on Machine Learning","author":"Caruana","year":"2006"},{"key":"B8","doi-asserted-by":"crossref","first-page":"p. 785","DOI":"10.1145\/2939672.2939785","article-title":"Xgboost: A scalable tree boosting system","volume-title":"Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining","author":"Chen","year":"2016"},{"key":"B9","doi-asserted-by":"publisher","first-page":"e232","DOI":"10.1161\/CIR.0000000000000525","article-title":"Contemporary management of cardiogenic shock: a scientific statement from the American Heart Association","volume":"136","author":"Van Diepen","year":"2017","journal-title":"Circulation"},{"key":"B10","doi-asserted-by":"publisher","first-page":"828","DOI":"10.1016\/S0195-668X(02)00844-8","article-title":"Early revascularization is associated with improved survival in elderly patients with acute myocardial infarction complicated by cardiogenic shock: a report from the SHOCK Trial Registry","volume":"24","author":"Dzavik","year":"2003","journal-title":"Eur Heart J"},{"key":"B11","doi-asserted-by":"publisher","first-page":"811","DOI":"10.1007\/s00134-004-2166-z","article-title":"Body temperature alterations in the critically ill","volume":"30","author":"Bota","year":"2004","journal-title":"Intens Care Med"},{"key":"B12","doi-asserted-by":"publisher","first-page":"197","DOI":"10.1136\/hrt.2010.195511","article-title":"Quantitative troponin and death, cardiogenic shock, cardiac arrest and new heart failure in patients with non-ST-segment elevation acute coronary syndromes (NSTE ACS): insights from the Global Registry of Acute Coronary Events","volume":"97","author":"Jolly","year":"2011","journal-title":"Heart"},{"key":"B13","doi-asserted-by":"publisher","first-page":"175","DOI":"10.1097\/SHK.0000000000001360","article-title":"High-sensitivity troponin T predicts postoperative cardiogenic shock requiring mechanical circulatory support in patients with valve disease","volume":"53","author":"Duchnowski","year":"2020","journal-title":"Shock"},{"key":"B14","doi-asserted-by":"crossref","DOI":"10.21236\/ADA164453","volume-title":"Learning Internal Representations by Error Propagation","author":"Rumelhart","year":"1985"},{"key":"B15","article-title":"An empirical evaluation of generic convolutional and recurrent networks for sequence modeling","volume-title":"arXiv preprint arXiv:180301271","author":"Bai","year":"2018"},{"key":"B16","first-page":"p. 4768","article-title":"A unified approach to interpreting model predictions","volume-title":"Proceedings of the 31st International Conference on Neural Information Processing Systems","author":"Lundberg","year":"2017"},{"key":"B17","doi-asserted-by":"publisher","first-page":"e000590","DOI":"10.1161\/JAHA.113.000590","article-title":"Trends in incidence, management, and outcomes of cardiogenic shock complicating ST-elevation myocardial infarction in the United States","volume":"3","author":"Kolte","year":"2014","journal-title":"J Am Heart Assoc"},{"key":"B18","doi-asserted-by":"publisher","first-page":"48","DOI":"10.1016\/j.ijcard.2016.10.033","article-title":"The association of admission blood glucose level with the clinical picture and prognosis in cardiogenic shock-results from the CardShock study","volume":"226","author":"Kataja","year":"2017","journal-title":"Int J Cardiol"},{"key":"B19","doi-asserted-by":"publisher","first-page":"21","DOI":"10.1016\/S0002-8703(99)70241-3","article-title":"Cardiogenic shock complicating acute myocardial infarction: predictors of death","volume":"138","author":"Hasdai","year":"1999","journal-title":"Am Heart J"},{"key":"B20","doi-asserted-by":"publisher","first-page":"45","DOI":"10.1177\/2048872616683526","article-title":"Baseline serum bicarbonate levels independently predict short-term mortality in critically ill patients with ischaemic cardiogenic shock","volume":"7","author":"Wigger","year":"2018","journal-title":"Eur Heart J Acute Cardiovasc Care"},{"key":"B21","doi-asserted-by":"publisher","first-page":"501","DOI":"10.1002\/ejhf.260","article-title":"Clinical picture and risk prediction of short-term mortality in cardiogenic shock","volume":"17","author":"Harjola","year":"2015","journal-title":"Eur J Heart Fail"},{"key":"B22","doi-asserted-by":"publisher","first-page":"136","DOI":"10.1016\/S0735-1097(99)00508-2","article-title":"Predictors of cardiogenic shock after thrombolytic therapy for acute myocardial infarction","volume":"35","author":"Hasdai","year":"2000","journal-title":"J Am Coll Cardiol"},{"key":"B23","doi-asserted-by":"publisher","first-page":"117","DOI":"10.1161\/CIRCOUTCOMES.115.002359","article-title":"Decade-long trends (2001-2011) in the incidence and hospital death rates associated with the in-hospital development of cardiogenic shock after acute myocardial infarction","volume":"9","author":"Goldberg","year":"2016","journal-title":"Circ Cardiovasc Qual Outcomes"},{"key":"B24","doi-asserted-by":"publisher","first-page":"1913","DOI":"10.1016\/j.jacc.2017.02.027","article-title":"Risk stratification for patients in cardiogenic shock after acute myocardial infarction","volume":"69","author":"P\u00f6ss","year":"2017","journal-title":"J Am Coll Cardiol"},{"key":"B25","doi-asserted-by":"publisher","first-page":"7","DOI":"10.1177\/2048872617706503","article-title":"Risk factors of late cardiogenic shock and mortality in ST-segment elevation myocardial infarction patients","volume":"7","author":"Obling","year":"2018","journal-title":"Eur Heart J Acute Cardiovasc Care"},{"key":"B26","doi-asserted-by":"publisher","first-page":"60","DOI":"10.1016\/j.ijcard.2018.06.036","article-title":"Hospital mortality and thirty day readmission among patients with non-acute myocardial infarction related cardiogenic shock","volume":"270","author":"Shah","year":"2018","journal-title":"Int J Cardiol"},{"key":"B27","doi-asserted-by":"publisher","first-page":"931","DOI":"10.3390\/jcm9040931","article-title":"Patient characteristics, treatment and outcome in non-ischemic vs. ischemic cardiogenic shock","volume":"9","author":"Schrage","year":"2020","journal-title":"J Clin Med"},{"key":"B28","doi-asserted-by":"publisher","first-page":"2090","DOI":"10.1093\/eurheartj\/ehy127","article-title":"Predicting the development of in-hospital cardiogenic shock in patients with ST-segment elevation myocardial infarction treated by primary percutaneous coronary intervention: the ORBI risk score","volume":"39","author":"Auffret","year":"2018","journal-title":"Eur Heart J"},{"key":"B29","doi-asserted-by":"publisher","first-page":"1805","DOI":"10.1093\/eurheartj\/ehw302","article-title":"Moving beyond regression techniques in cardiovascular risk prediction: applying machine learning to address analytic challenges","volume":"38","author":"Goldstein","year":"2017","journal-title":"Eur Heart J"},{"key":"B30","doi-asserted-by":"publisher","first-page":"e020085","DOI":"10.1161\/JAHA.120.020085","article-title":"Phenotyping cardiogenic shock","volume":"10","author":"Zweck","year":"2021","journal-title":"J Am Heart Assoc"},{"key":"B31","doi-asserted-by":"publisher","first-page":"1162","DOI":"10.21037\/atm-21-2905","article-title":"Development of a machine learning model to predict the risk of late cardiogenic shock in patients with ST-segment elevation myocardial infarction","volume":"9","author":"Bai","year":"2021","journal-title":"Ann Transl Med"},{"key":"B32","doi-asserted-by":"publisher","DOI":"10.1016\/j.jscai.2022.100308","article-title":"Using machine learning for early prediction of cardiogenic shock in patients with acute heart failure","author":"Rahman","year":"2022","journal-title":"J SCAI"}],"container-title":["Frontiers in Cardiovascular Medicine"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fcvm.2022.862424\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,13]],"date-time":"2022-07-13T01:14:50Z","timestamp":1657674890000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fcvm.2022.862424\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,7,13]]},"references-count":32,"alternative-id":["10.3389\/fcvm.2022.862424"],"URL":"https:\/\/doi.org\/10.3389\/fcvm.2022.862424","relation":{},"ISSN":["2297-055X"],"issn-type":[{"value":"2297-055X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,7,13]]},"article-number":"862424"}}