{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,20]],"date-time":"2026-08-20T09:24:26Z","timestamp":1787217866237,"version":"build-2736575974"},"reference-count":34,"publisher":"MDPI AG","issue":"8","license":[{"start":{"date-parts":[[2026,8,20]],"date-time":"2026-08-20T00:00:00Z","timestamp":1787184000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Life"],"abstract":"<jats:p>Preoperative risk stratification underpins consent, treatment selection, and quality benchmarking in cardiac surgery, a task served for two decades by regression-derived scores such as the European System for Cardiac Operative Risk Evaluation II (EuroSCORE II) and the Society of Thoracic Surgeons Predicted Risk of Mortality (STS PROM), together with procedure-specific tools. A rapidly expanding literature reports that machine learning (ML) models achieve higher discrimination than these scores, yet established scores remain the instruments actually used at the bedside. This narrative review examines that paradox. Drawing on studies emphasized between 2023 and 2026, we argue that the reported advantage of ML is real but modest. This advantage is driven primarily by improved discrimination, while key measures of clinical value, including calibration, net benefit, and external or temporal validation, are infrequently reported. We organize the evidence around a four-lens appraisal (discrimination, calibration, clinical utility, and generalizability) and show that most cardiac surgery ML studies focus only on discrimination. We then consider why superior discrimination has not changed practice and outline the evidence needed for an ML-based risk model to justify replacing an established scoring system. The current literature supports a measured conclusion: ML is a discrimination upgrade in search of clinical proof.<\/jats:p>","DOI":"10.3390\/life16081371","type":"journal-article","created":{"date-parts":[[2026,8,20]],"date-time":"2026-08-20T08:10:20Z","timestamp":1787213420000},"page":"1371","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Better Discrimination, Unchanged Practice: Are Machine Learning Models Ready to Replace Established Risk Scores in Cardiac Surgery? A Narrative Review"],"prefix":"10.3390","volume":"16","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5417-6392","authenticated-orcid":false,"given":"Dimitrios E.","family":"Magouliotis","sequence":"first","affiliation":[{"name":"Department of Cardiac Surgery Research, Lankenau Institute for Medical Research, Wynnewood, PA 19096, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1822-768X","authenticated-orcid":false,"given":"Serge","family":"Sicouri","sequence":"additional","affiliation":[{"name":"Department of Cardiac Surgery Research, Lankenau Institute for Medical Research, Wynnewood, PA 19096, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Vasiliki","family":"Androutsopoulou","sequence":"additional","affiliation":[{"name":"Department of Cardiothoracic Surgery, Faculty of Medicine, University of Thessaly, Biopolis, 41110 Larissa, Greece"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Prokopis-Andreas","family":"Zotos","sequence":"additional","affiliation":[{"name":"Department of Cardiothoracic Surgery, Faculty of Medicine, University of Thessaly, Biopolis, 41110 Larissa, Greece"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3754-6704","authenticated-orcid":false,"given":"Massimo","family":"Baudo","sequence":"additional","affiliation":[{"name":"Department of Cardiac Surgery Research, Lankenau Institute for Medical Research, Wynnewood, PA 19096, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0471-0910","authenticated-orcid":false,"given":"Basel","family":"Ramlawi","sequence":"additional","affiliation":[{"name":"Department of Cardiac Surgery Research, Lankenau Institute for Medical Research, Wynnewood, PA 19096, USA"},{"name":"Department of Cardiac Surgery, Lankenau Medical Center, Wynnewood, PA 19096, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2026,8,20]]},"reference":[{"key":"ref_1","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":"ref_2","doi-asserted-by":"crossref","first-page":"1411","DOI":"10.1016\/j.athoracsur.2018.03.002","article-title":"The Society of Thoracic Surgeons 2018 Adult Cardiac Surgery Risk Models: Part 1\u2014Background, Design Considerations, and Model Development","volume":"105","author":"Shahian","year":"2018","journal-title":"Ann. Thorac. Surg."},{"key":"ref_3","first-page":"1419","article-title":"The Society of Thoracic Surgeons 2018 Adult Cardiac Surgery Risk Models: Part 2\u2014Statistical Methods and Results","volume":"105","author":"Feng","year":"2018","journal-title":"Ann. Thorac. Surg."},{"key":"ref_4","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":"ref_5","doi-asserted-by":"crossref","first-page":"2183","DOI":"10.1093\/eurheartj\/ehx228","article-title":"The ACEF II Risk Score for cardiac surgery: Updated but still parsimonious","volume":"39","author":"Ranucci","year":"2018","journal-title":"Eur. Heart J."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"700","DOI":"10.1093\/ejcts\/ezaa156","article-title":"Prediction of mortality rate in acute type A dissection: The German Registry for Acute Type A Aortic Dissection score","volume":"58","author":"Czerny","year":"2020","journal-title":"Eur. J. Cardiothorac. Surg."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"1109","DOI":"10.1016\/j.athoracsur.2022.10.028","article-title":"The Penn Classification System for Malperfusion in Acute Type A Dissection: A 25-Year Experience","volume":"115","author":"Patrick","year":"2023","journal-title":"Ann. Thorac. Surg."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"2075","DOI":"10.1016\/j.jtcvs.2020.07.105","article-title":"Machine learning improves mortality risk prediction after cardiac surgery: Systematic review and meta-analysis","volume":"163","author":"Benedetto","year":"2022","journal-title":"J. Thorac. Cardiovasc. Surg."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"ezad183","DOI":"10.1093\/ejcts\/ezad183","article-title":"Comparison of machine learning techniques in prediction of mortality following cardiac surgery: Analysis of over 220 000 patients from a large national database","volume":"63","author":"Sinha","year":"2023","journal-title":"Eur. J. Cardiothorac. Surg."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"12","DOI":"10.1016\/j.jclinepi.2019.02.004","article-title":"A systematic review shows no performance benefit of machine learning over logistic regression for clinical prediction models","volume":"110","author":"Christodoulou","year":"2019","journal-title":"J. Clin. Epidemiol."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"1925","DOI":"10.1093\/eurheartj\/ehu207","article-title":"Towards better clinical prediction models: Seven steps for development and an ABCD for validation","volume":"35","author":"Steyerberg","year":"2014","journal-title":"Eur. Heart J."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"g7594","DOI":"10.1136\/bmj.g7594","article-title":"Transparent reporting of a multivariable prediction model for individual prognosis or diagnosis (TRIPOD): The TRIPOD statement","volume":"350","author":"Collins","year":"2015","journal-title":"BMJ"},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"W1","DOI":"10.7326\/M14-0698","article-title":"Transparent Reporting of a multivariable prediction model for Individual Prognosis or Diagnosis (TRIPOD): Explanation and elaboration","volume":"162","author":"Moons","year":"2015","journal-title":"Ann. Intern. Med."},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Van Calster, B., McLernon, D.J., van Smeden, M., Wynants, L., Steyerberg, E.W., and Topic Group \u2018Evaluating diagnostic tests and prediction models\u2019 of the STRATOS initiative (2019). Calibration: The Achilles heel of predictive analytics. BMC Med., 17.","DOI":"10.1186\/s12916-019-1466-7"},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"1323","DOI":"10.1016\/j.athoracsur.2019.09.042","article-title":"Artificial Intelligence and Machine Learning in Cardiovascular Health Care","volume":"109","author":"Kilic","year":"2020","journal-title":"Ann. Thorac. Surg."},{"key":"ref_16","first-page":"n2281","article-title":"Risk of bias in studies on prediction models developed using supervised machine learning techniques: Systematic review","volume":"375","author":"Damen","year":"2021","journal-title":"BMJ"},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"m1328","DOI":"10.1136\/bmj.m1328","article-title":"Prediction models for diagnosis and prognosis of covid-19: Systematic review and critical appraisal","volume":"369","author":"Wynants","year":"2020","journal-title":"BMJ"},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"51","DOI":"10.7326\/M18-1376","article-title":"PROBAST: A Tool to Assess the Risk of Bias and Applicability of Prediction Model Studies","volume":"170","author":"Wolff","year":"2019","journal-title":"Ann. Intern. Med."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"e048008","DOI":"10.1136\/bmjopen-2020-048008","article-title":"Protocol for development of a reporting guideline (TRIPOD-AI) and risk of bias tool (PROBAST-AI) for diagnostic and prognostic prediction model studies based on artificial intelligence","volume":"11","author":"Collins","year":"2021","journal-title":"BMJ Open"},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"e078378","DOI":"10.1136\/bmj-2023-078378","article-title":"TRIPOD+AI statement: Updated guidance for reporting clinical prediction models that use regression or machine learning methods","volume":"385","author":"Collins","year":"2024","journal-title":"BMJ"},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"871","DOI":"10.1093\/ejcts\/ezs562","article-title":"Design flaws in EuroSCORE II","volume":"43","author":"Collins","year":"2013","journal-title":"Eur. J. Cardiothorac. Surg."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"5","DOI":"10.1016\/j.athoracsur.2024.01.021","article-title":"EACTS\/STS Guidelines for Diagnosing and Treating Acute and Chronic Syndromes of the Aortic Organ","volume":"118","author":"Czerny","year":"2024","journal-title":"Ann. Thorac. Surg."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"12","DOI":"10.21037\/cdt-21-648","article-title":"Development of machine learning models for mortality risk prediction after cardiac surgery","volume":"12","author":"Fan","year":"2022","journal-title":"Cardiovasc. Diagn. Ther."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"1449","DOI":"10.1016\/j.jtcvs.2021.09.010","article-title":"Prediction of operative mortality for patients undergoing cardiac surgical procedures without established risk scores","volume":"165","author":"Ong","year":"2023","journal-title":"J. Thorac. Cardiovasc. Surg."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"e567","DOI":"10.1016\/j.jtcvs.2023.01.022","article-title":"Clinical utility of a deep-learning mortality prediction model for cardiac surgery decision making","volume":"166","author":"Allou","year":"2023","journal-title":"J. Thorac. Cardiovasc. Surg."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"478","DOI":"10.1186\/s13054-020-03179-9","article-title":"Prediction of the development of acute kidney injury following cardiac surgery by machine learning","volume":"24","author":"Tseng","year":"2020","journal-title":"Crit. Care"},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"269","DOI":"10.1002\/clc.23963","article-title":"Machine learning-based prediction of 1-year mortality in hypertensive patients undergoing coronary revascularization surgery","volume":"46","author":"Behnoush","year":"2023","journal-title":"Clin. Cardiol."},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"259","DOI":"10.1038\/s41586-023-05881-4","article-title":"Foundation models for generalist medical artificial intelligence","volume":"616","author":"Moor","year":"2023","journal-title":"Nature"},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"1773","DOI":"10.1038\/s41591-022-01981-2","article-title":"Multimodal biomedical AI","volume":"28","author":"Acosta","year":"2022","journal-title":"Nat. Med."},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"1996","DOI":"10.1038\/s41591-022-01961-6","article-title":"Steps to avoid overuse and misuse of machine learning in clinical research","volume":"28","author":"Volovici","year":"2022","journal-title":"Nat. Med."},{"key":"ref_31","unstructured":"Lundberg, S.M., and Lee, S.I. (2017). A unified approach to interpreting model predictions. Advances in Neural Information Processing Systems 30, Curran Associates, Inc."},{"key":"ref_32","doi-asserted-by":"crossref","unstructured":"Ribeiro, M.T., Singh, S., and Guestrin, C. (2016). \u2018Why should I trust you?\u2019: Explaining the predictions of any classifier. Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, Association for Computing Machinery.","DOI":"10.1145\/2939672.2939778"},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"565","DOI":"10.1177\/0272989X06295361","article-title":"Decision curve analysis: A novel method for evaluating prediction models","volume":"26","author":"Vickers","year":"2006","journal-title":"Med. Decis. Mak."},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"m441","DOI":"10.1136\/bmj.m441","article-title":"Calculating the sample size required for developing a clinical prediction model","volume":"368","author":"Riley","year":"2020","journal-title":"BMJ"}],"container-title":["Life"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2075-1729\/16\/8\/1371\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,20]],"date-time":"2026-08-20T08:35:54Z","timestamp":1787214954000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2075-1729\/16\/8\/1371"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,20]]},"references-count":34,"journal-issue":{"issue":"8","published-online":{"date-parts":[[2026,8]]}},"alternative-id":["life16081371"],"URL":"https:\/\/doi.org\/10.3390\/life16081371","relation":{},"ISSN":["2075-1729"],"issn-type":[{"value":"2075-1729","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,8,20]]}}}