{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,22]],"date-time":"2026-10-22T00:17:43Z","timestamp":1792628263592,"version":"4.5.0"},"reference-count":29,"publisher":"BMJ","issue":"9","funder":[{"name":"King\u2019s College Hospital Charity"}],"content-domain":{"domain":["bmj.com"],"crossmark-restriction":true},"short-container-title":["Heart"],"accepted":{"date-parts":[[2025,7,17]]},"published-print":{"date-parts":[[2026,5]]},"abstract":"<jats:sec>\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>Current risk scores inadequately predict long-term mortality after transcatheter aortic valve replacement (TAVR), limiting their ability to guide decisions around procedural futility. We aimed to develop and externally validate a machine learning (ML) model using only preprocedural variables to predict 1-year all-cause mortality.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>An ML model was trained on a retrospective cohort of 1025 TAVR patients using 52 clinical and echocardiographic variables. Feature selection and model tuning were performed via a multiobjective evolutionary algorithm to optimise predictive performance and model simplicity. The final model used 13 preprocedural variables and was externally validated in an independent cohort of 270 patients. Performance was compared with European System for Cardiac Operative Risk Evaluation II (EuroSCORE II), FRANCE-2 and TAVI2-SCORE using the area under the curve (AUC), calibration and net reclassification improvement (NRI).<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>The ML model demonstrated excellent discrimination, with AUCs of 0.81 in the discovery cohort and 0.84 in the external validation cohort. This exceeded the performance of EuroSCORE II (AUC: 0.61 and 0.70), FRANCE-2 (0.52 and 0.58) and TAVI2-SCORE (0.56 and 0.64). Calibration plots showed strong agreement between predicted and observed risks. NRI in the test set compared with FRANCE-2 was 0.62 (95% CI: 0.49 to 0.75); compared with TAVI2-SCORE, it was 0.36 (95% CI: 0.14 to 0.61). The final model incorporated age, atrial fibrillation, creatinine, haemoglobin, pulmonary function, frailty markers (Katz Index, poor mobility) and tricuspid regurgitation. Misclassification analysis revealed that most errors were clustered near the decision threshold, with no evidence of systematic bias. Performance was consistent across subgroups and robust to temporal and institutional variation.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>This externally validated ML model, using 13 routinely available variables, significantly outperforms existing risk scores in predicting 1-year mortality post-TAVR. Its simplicity and generalisability support its potential use in real-world clinical decision-making to identify patients at high risk of procedural futility.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1136\/heartjnl-2025-325928","type":"journal-article","created":{"date-parts":[[2025,7,25]],"date-time":"2025-07-25T17:20:13Z","timestamp":1753464013000},"page":"488-494","update-policy":"https:\/\/doi.org\/10.1136\/crossmarkpolicy","source":"Crossref","is-referenced-by-count":3,"title":["Parsimonious machine learning model to predict 1-year mortality and procedural futility after transcatheter aortic valve replacement"],"prefix":"10.1136","volume":"112","author":[{"given":"Apurva H","family":"Bharucha","sequence":"first","affiliation":[{"name":"Department of Cardiology, King\u2019s College Hospital NHS Foundation Trust, London, UK"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2173-1251","authenticated-orcid":false,"given":"Samuel","family":"Brown","sequence":"additional","affiliation":[{"name":"Department of Cardiology, King\u2019s College Hospital NHS Foundation Trust, London, UK"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Konstantinos","family":"Theofilatos","sequence":"additional","affiliation":[{"name":"King's College London British Heart Foundation Centre of Research Excellence, School of Cardiovascular Medicine and Sciences, King's College London, London, UK"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bhawana","family":"Singh","sequence":"additional","affiliation":[{"name":"Department of Cardiology, King\u2019s College Hospital NHS Foundation Trust, London, UK"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Victor","family":"Galusko","sequence":"additional","affiliation":[{"name":"Department of Cardiology, King\u2019s College Hospital NHS Foundation Trust, London, UK"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1879-7172","authenticated-orcid":false,"given":"Hashrul","family":"Rashid","sequence":"additional","affiliation":[{"name":"Cardiovascular Department, Guy\u2019s and St Thomas\u2019 NHS Foundation Trust, London, UK"},{"name":"Victorian Heart Institute, Monash University, Melbourne, Victoria, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hoda","family":"Abdelgawad","sequence":"additional","affiliation":[{"name":"Department of Cardiology, King\u2019s College Hospital NHS Foundation Trust, London, UK"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Rafal","family":"Dworakowski","sequence":"additional","affiliation":[{"name":"Department of Cardiology, King\u2019s College Hospital NHS Foundation Trust, London, UK"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7606-118X","authenticated-orcid":false,"given":"Alexandros","family":"Papachristidis","sequence":"additional","affiliation":[{"name":"Department of Cardiology, King\u2019s College Hospital NHS Foundation Trust, London, UK"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tiffany","family":"Patterson","sequence":"additional","affiliation":[{"name":"Cardiovascular Department, Guy\u2019s and St Thomas\u2019 NHS Foundation Trust, London, UK"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Simon R","family":"Redwood","sequence":"additional","affiliation":[{"name":"Cardiovascular Department, Guy\u2019s and St Thomas\u2019 NHS Foundation Trust, London, UK"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6031-2124","authenticated-orcid":false,"given":"Bernard","family":"Prendergast","sequence":"additional","affiliation":[{"name":"Cardiovascular Department, Guy\u2019s and St Thomas\u2019 NHS Foundation Trust, London, UK"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jonathan A","family":"Byrne","sequence":"additional","affiliation":[{"name":"Department of Cardiology, King\u2019s College Hospital NHS Foundation Trust, London, UK"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5963-0109","authenticated-orcid":false,"given":"Philip A","family":"MacCarthy","sequence":"additional","affiliation":[{"name":"Department of Cardiology, King\u2019s College Hospital NHS Foundation Trust, London, UK"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kevin","family":"O\u2019Gallagher","sequence":"additional","affiliation":[{"name":"Department of Cardiology, King\u2019s College Hospital NHS Foundation Trust, London, UK"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4304-5001","authenticated-orcid":false,"given":"Mehdi","family":"Eskandari","sequence":"additional","affiliation":[{"name":"Department of Cardiology, King\u2019s College Hospital NHS Foundation Trust, London, UK"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"239","published-online":{"date-parts":[[2025,7,25]]},"reference":[{"key":"2026041002050850000_112.9.488.1","doi-asserted-by":"publisher","DOI":"10.1016\/S0140-6736(15)60290-2"},{"key":"2026041002050850000_112.9.488.2","doi-asserted-by":"publisher","DOI":"10.1056\/NEJMoa1910555"},{"key":"2026041002050850000_112.9.488.3","doi-asserted-by":"publisher","DOI":"10.1056\/NEJMoa1103510"},{"key":"2026041002050850000_112.9.488.4","doi-asserted-by":"publisher","DOI":"10.1016\/j.jacc.2016.07.762"},{"key":"2026041002050850000_112.9.488.5","doi-asserted-by":"publisher","DOI":"10.1016\/j.jacc.2012.03.075"},{"key":"2026041002050850000_112.9.488.6","doi-asserted-by":"publisher","DOI":"10.1093\/eurheartj\/ehv756"},{"key":"2026041002050850000_112.9.488.7","doi-asserted-by":"publisher","DOI":"10.1093\/eurheartj\/ehab395"},{"key":"2026041002050850000_112.9.488.8","doi-asserted-by":"publisher","DOI":"10.1093\/ejcts\/ezs043"},{"key":"2026041002050850000_112.9.488.9","doi-asserted-by":"crossref","first-page":"796","DOI":"10.1016\/j.athoracsur.2013.09.012","article-title":"Comparison between different risk scoring algorithms on isolated conventional or transcatheter aortic valve replacement","volume":"97","author":"Wendt","year":"2014","journal-title":"Ann Thorac Surg"},{"key":"2026041002050850000_112.9.488.10","doi-asserted-by":"crossref","DOI":"10.1161\/JAHA.119.011972","article-title":"Clinical Prediction Models for Valvular Heart Disease","volume":"8","author":"Wessler","year":"2019","journal-title":"J Am Heart Assoc"},{"key":"2026041002050850000_112.9.488.11","doi-asserted-by":"publisher","DOI":"10.1016\/j.amjcard.2014.10.029"},{"key":"2026041002050850000_112.9.488.12","doi-asserted-by":"publisher","DOI":"10.1136\/heartjnl-2013-305314"},{"key":"2026041002050850000_112.9.488.13","doi-asserted-by":"crossref","first-page":"46","DOI":"10.1001\/jamacardio.2015.0326","article-title":"Development and Validation of a Risk Prediction Model for In-Hospital Mortality After Transcatheter Aortic Valve Replacement","volume":"1","author":"Edwards","year":"2016","journal-title":"JAMA Cardiol"},{"key":"2026041002050850000_112.9.488.14","doi-asserted-by":"crossref","first-page":"97","DOI":"10.1016\/j.ahj.2016.10.020","article-title":"Inadequacy of existing clinical prediction models for predicting mortality after transcatheter aortic valve implantation","volume":"184","author":"Martin","year":"2017","journal-title":"Am Heart J"},{"key":"2026041002050850000_112.9.488.15","article-title":"Update and, internal and temporal-validation of the FRANCE-2 and ACC-TAVI early-mortality prediction models for Transcatheter Aortic Valve Implantation (TAVI) using data from the Netherlands heart registration (NHR)","volume":"32","author":"Al-Farra","year":"2021","journal-title":"Int J Cardiol Heart Vasc"},{"key":"2026041002050850000_112.9.488.16","doi-asserted-by":"crossref","first-page":"33","DOI":"10.1016\/j.carrev.2020.08.010","article-title":"Artificial Intelligence Trumps TAVI2-SCORE and CoreValve Score in Predicting 1-Year Mortality Post-Transcatheter Aortic Valve Replacement","volume":"24","author":"Agasthi","year":"2021","journal-title":"Cardiovasc Revasc Med"},{"key":"2026041002050850000_112.9.488.17","doi-asserted-by":"crossref","first-page":"1343210","DOI":"10.3389\/fcvm.2024.1343210","article-title":"Harnessing the power of artificial intelligence in predicting all-cause mortality in transcatheter aortic valve replacement: a systematic review and meta-analysis","volume":"11","author":"Sazzad","year":"2024","journal-title":"Front Cardiovasc Med"},{"key":"2026041002050850000_112.9.488.18","doi-asserted-by":"crossref","first-page":"768","DOI":"10.1093\/ehjqcco\/qcad002","article-title":"Machine learning for prediction of all-cause mortality after transcatheter aortic valve implantation","volume":"9","author":"Kwiecinski","year":"2023","journal-title":"Eur Heart J Qual Care Clin Outcomes"},{"key":"2026041002050850000_112.9.488.19","first-page":"44","article-title":"Predicting long-term mortality in TAVI patients using machine learning techniques","volume":"8","author":"Penso","year":"2021","journal-title":"J Cardiovasc Dev Dis"},{"key":"2026041002050850000_112.9.488.20","doi-asserted-by":"crossref","first-page":"225","DOI":"10.1093\/ehjdh\/ztad021","article-title":"Development and validation of explainable machine learning models for risk of mortality in transcatheter aortic valve implantation: TAVI risk machine scores","volume":"4","author":"Leha","year":"2023","journal-title":"Eur Heart J Digit Health"},{"key":"2026041002050850000_112.9.488.21","doi-asserted-by":"crossref","first-page":"787246","DOI":"10.3389\/fcvm.2021.787246","article-title":"Local and Distributed Machine Learning for Inter-hospital Data Utilization: An Application for TAVI Outcome Prediction","volume":"8","author":"Lopes","year":"2021","journal-title":"Front Cardiovasc Med"},{"key":"2026041002050850000_112.9.488.22","doi-asserted-by":"publisher","DOI":"10.1007\/s12471-019-1285-7"},{"key":"2026041002050850000_112.9.488.23","doi-asserted-by":"publisher","DOI":"10.1016\/j.jcin.2017.07.025"},{"key":"2026041002050850000_112.9.488.24","doi-asserted-by":"crossref","first-page":"e1047","DOI":"10.4244\/EIJY15M11_12","article-title":"A meta-analysis of the impact of pre-existing and new-onset atrial fibrillation on clinical outcomes in patients undergoing transcatheter aortic valve implantation","volume":"12","author":"Sannino","year":"2016","journal-title":"EuroIntervention"},{"key":"2026041002050850000_112.9.488.25","doi-asserted-by":"crossref","first-page":"1121","DOI":"10.1016\/j.athoracsur.2017.11.018","article-title":"Association of Tricuspid Regurgitation With Transcatheter Aortic Valve Replacement Outcomes: A Report From The Society of Thoracic Surgeons\/American College of Cardiology Transcatheter Valve Therapy Registry","volume":"105","author":"McCarthy","year":"2018","journal-title":"Ann Thorac Surg"},{"key":"2026041002050850000_112.9.488.26","doi-asserted-by":"crossref","first-page":"783","DOI":"10.1016\/j.jacc.2022.05.006","article-title":"Evolution and Prognostic Impact of Cardiac Damage After Aortic Valve Replacement","volume":"80","author":"G\u00e9n\u00e9reux","year":"2022","journal-title":"J Am Coll Cardiol"},{"key":"2026041002050850000_112.9.488.27","doi-asserted-by":"publisher","DOI":"10.1093\/ehjqcco\/qcw030"},{"key":"2026041002050850000_112.9.488.28","doi-asserted-by":"crossref","first-page":"52","DOI":"10.1016\/j.ahj.2016.12.005","article-title":"Impact of frailty on mortality after transcatheter aortic valve implantation","volume":"185","author":"Kleczynski","year":"2017","journal-title":"Am Heart J"},{"key":"2026041002050850000_112.9.488.29","doi-asserted-by":"publisher","DOI":"10.7326\/0003-4819-112-12-949"}],"container-title":["Heart"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/syndication.highwire.org\/content\/doi\/10.1136\/heartjnl-2025-325928","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,10]],"date-time":"2026-04-10T09:05:45Z","timestamp":1775811945000},"score":1,"resource":{"primary":{"URL":"https:\/\/heart.bmj.com\/lookup\/doi\/10.1136\/heartjnl-2025-325928"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7,25]]},"references-count":29,"journal-issue":{"issue":"9","published-online":{"date-parts":[[2026,4,10]]},"published-print":{"date-parts":[[2026,5]]}},"alternative-id":["10.1136\/heartjnl-2025-325928"],"URL":"https:\/\/doi.org\/10.1136\/heartjnl-2025-325928","relation":{},"ISSN":["1355-6037","1468-201X"],"issn-type":[{"value":"1355-6037","type":"print"},{"value":"1468-201X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,7,25]]}}}