{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,17]],"date-time":"2026-06-17T18:12:20Z","timestamp":1781719940008,"version":"3.54.5"},"reference-count":14,"publisher":"Ovid Technologies (Wolters Kluwer Health)","issue":"22","content-domain":{"domain":["www.ahajournals.org"],"crossmark-restriction":true},"short-container-title":["JAHA"],"published-print":{"date-parts":[[2021,11,16]]},"abstract":"<jats:sec xml:lang=\"en\">\n            <jats:title>Background<\/jats:title>\n            <jats:p xml:lang=\"en\">This study evaluated the role of supplementing Society of Thoracic Surgeons (STS) risk models for surgical aortic valve replacement with machine learning (ML).<\/jats:p>\n          <\/jats:sec>\n          <jats:sec xml:lang=\"en\">\n            <jats:title>Methods and Results<\/jats:title>\n            <jats:p xml:lang=\"en\">\n              Adults undergoing isolated surgical aortic valve replacement in the STS National Database between 2007 and 2017 were included. ML models for operative mortality and major morbidity were previously developed using extreme gradient boosting. Concordance and discordance in predicted risk between ML and STS models were defined using equal\u2010size tertile\u2010based thresholds of risk. Calibration metrics and discriminatory capability were compared between concordant and discordant patients. A total of 243\u00a0142 patients were included. Nearly all calibration metrics were improved in cases of concordance. Similarly, concordance indices improved substantially in cases of concordance for all models with the exception of deep sternal wound infection. The greatest improvements in concordant versus discordant cases were in renal failure: ML model (concordance index, 0.660 [95% CI, 0.632\u20130.687] discordant versus 0.808 [95% CI, 0.794\u20130.822] concordant) and STS model (concordance index, 0.573 [95% CI, 0.549\u20130.576] discordant versus 0.797 [95% CI, 0.782\u20130.811] concordant) (each\n              <jats:italic>P<\/jats:italic>\n              &lt;0.001). Excluding deep sternal wound infection, the concordance indices ranged from 0.549 to 0.660 for discordant cases and 0.674 to 0.808 for concordant cases.\n            <\/jats:p>\n          <\/jats:sec>\n          <jats:sec xml:lang=\"en\">\n            <jats:title>Conclusions<\/jats:title>\n            <jats:p xml:lang=\"en\">Supplementing ML models with existing STS models for surgical aortic valve replacement may have an important role in risk prediction and should be explored further. In particular, for the roughly 25% to 50% of patients demonstrating discordance in estimated risk between ML and STS, there appears to be a substantial decline in predictive performance suggesting vulnerability of the existing models in these patient subsets.<\/jats:p>\n          <\/jats:sec>","DOI":"10.1161\/jaha.120.019697","type":"journal-article","created":{"date-parts":[[2021,10,18]],"date-time":"2021-10-18T10:37:58Z","timestamp":1634553478000},"update-policy":"https:\/\/doi.org\/10.1161\/crossmarkpolicy","source":"Crossref","is-referenced-by-count":10,"title":["Supplementing Existing Societal Risk Models for Surgical Aortic Valve Replacement With Machine Learning for Improved Prediction"],"prefix":"10.1161","volume":"10","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8112-8345","authenticated-orcid":false,"given":"Arman","family":"Kilic","sequence":"first","affiliation":[{"name":"Division of Cardiac Surgery University of Pittsburgh Medical Center Pittsburgh PA"},{"name":"Division of Cardiothoracic Surgery Medical University of South Carolina"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Robert H.","family":"Habib","sequence":"additional","affiliation":[{"name":"The Society of Thoracic Surgeons Research Center Chicago IL"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"James K.","family":"Miller","sequence":"additional","affiliation":[{"name":"The Robotics Institute Carnegie Mellon University Pittsburgh PA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"David M.","family":"Shahian","sequence":"additional","affiliation":[{"name":"Department of Surgery Massachusetts General HospitalHarvard Medical School Boston MA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Joseph A.","family":"Dearani","sequence":"additional","affiliation":[{"name":"Department of Cardiovascular Surgery Mayo Clinic Rochester MN"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2372-0831","authenticated-orcid":false,"given":"Artur W.","family":"Dubrawski","sequence":"additional","affiliation":[{"name":"The Robotics Institute Carnegie Mellon University Pittsburgh PA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"276","reference":[{"key":"e_1_3_2_2_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.athoracsur.2009.09.045"},{"key":"e_1_3_2_3_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.athoracsur.2018.03.002"},{"key":"e_1_3_2_4_2","first-page":"1419","article-title":"The Society of Thoracic Surgeons 2018 adult cardiac surgery risk models: part 2\u2010statistical methods and results","volume":"105","author":"O\u2019Brien SM","year":"2018","unstructured":"O\u2019Brien SM, Feng L, He X, Xian Y, Jacobs JP, Badhwar V, Kurlansky PA, Furnary AP, Cleveland JC Jr, Lobdell KW, et al. The Society of Thoracic Surgeons 2018 adult cardiac surgery risk models: part 2\u2010statistical methods and results. Ann Thorac Surg. 2018;105:1419\u20131428.DOI: 10.1016\/j.athoracsur.2018.03.003.","journal-title":"Ann Thorac Surg"},{"key":"e_1_3_2_5_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.athoracsur.2019.09.049"},{"key":"e_1_3_2_6_2","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0169772"},{"key":"e_1_3_2_7_2","doi-asserted-by":"publisher","DOI":"10.3390\/jcm7100322"},{"key":"e_1_3_2_8_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.ahj.2009.03.023"},{"key":"e_1_3_2_9_2","unstructured":"The Society of Thoracic Surgeons Cardiac Surgery Database: database data collection. Available at: https:\/\/www.sts.org\/registries\u2010research\u2010center\/sts\u2010national\u2010database\/adult\u2010cardiac\u2010surgery\u2010database\/data\u2010collection. Accessed November 14 2019."},{"key":"e_1_3_2_10_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.athoracsur.2020.05.107"},{"key":"e_1_3_2_11_2","doi-asserted-by":"publisher","DOI":"10.1097\/EDE.0b013e3181c30fb2"},{"key":"e_1_3_2_12_2","doi-asserted-by":"publisher","DOI":"10.1038\/s41746-018-0029-1"},{"key":"e_1_3_2_13_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.athoracsur.2016.06.060"},{"key":"e_1_3_2_14_2","doi-asserted-by":"publisher","DOI":"10.1093\/icvts\/ivu102"},{"key":"e_1_3_2_15_2","doi-asserted-by":"publisher","DOI":"10.1186\/s12871-019-0738-2"}],"container-title":["Journal of the American Heart Association"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.ahajournals.org\/doi\/full\/10.1161\/JAHA.120.019697","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,5,13]],"date-time":"2024-05-13T11:17:11Z","timestamp":1715599031000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.ahajournals.org\/doi\/10.1161\/JAHA.120.019697"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,11,16]]},"references-count":14,"journal-issue":{"issue":"22","published-print":{"date-parts":[[2021,11,16]]}},"alternative-id":["10.1161\/JAHA.120.019697"],"URL":"https:\/\/doi.org\/10.1161\/jaha.120.019697","relation":{},"ISSN":["2047-9980"],"issn-type":[{"value":"2047-9980","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,11,16]]},"assertion":[{"value":"2020-10-08","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2020-12-21","order":1,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2021-10-18","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"e019697"}}