{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,22]],"date-time":"2026-07-22T08:00:40Z","timestamp":1784707240025,"version":"3.55.0"},"reference-count":57,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2026,7,5]],"date-time":"2026-07-05T00:00:00Z","timestamp":1783209600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2026,7,22]],"date-time":"2026-07-22T00:00:00Z","timestamp":1784678400000},"content-version":"vor","delay-in-days":17,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/501100000833","name":"rosetrees trust","doi-asserted-by":"crossref","award":["FS\/ICRF\/24\/26128"],"award-info":[{"award-number":["FS\/ICRF\/24\/26128"]}],"id":[{"id":"10.13039\/501100000833","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100000274","name":"British Heart Foundation","doi-asserted-by":"crossref","award":["PG\/22\/11159"],"award-info":[{"award-number":["PG\/22\/11159"]}],"id":[{"id":"10.13039\/501100000274","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["npj Cardiovasc Health"],"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>\n                    Sudden arrhythmic death remains a major clinical risk in ischemic heart disease (IHD), underscoring the need for improved risk stratification. Late gadolinium enhancement cardiac magnetic resonance (LGE-CMR) provides measures of scar burden and heterogeneity, but its incremental prognostic value beyond conventional markers such as left ventricular ejection fraction remains uncertain. We analysed two independent IHD cohorts (Dataset 1:\n                    <jats:italic>n<\/jats:italic>\n                    \u2009=\u2009399, 54 events; National Research Ethics Service approvals 07\/H0708\/83 and 09\/H0504\/104+5; Dataset 2:\n                    <jats:italic>n<\/jats:italic>\n                    \u2009=\u2009424, 50 events; derived from the prospectively registered REVIVED-BCIS2 trial, ISRCTN45979711, registered 20 November 2012)using clinical and LGE-CMR-derived variables to evaluate the contribution of LGE-CMR features, and compare machine learning-based survival modelling approaches. A brute-force feature-selection strategy identified optimal predictor subsets for Cox proportional hazards models, Random Survival Forests, and DeepSurv, evaluated using cross-cohort and pooled validation strategies. Scar entropy consistently emerged as a strong predictor of major arrhythmic events. Non-linear approaches outperformed Cox regression, with DeepSurv demonstrating superior generalization across cohorts and Random Survival Forests showing robust performance in pooled analyses. These findings support scar heterogeneity as an important prognostic marker and suggest that machine-learning survival models may improve arrhythmic risk prediction in patients with IHD.\n                  <\/jats:p>","DOI":"10.1038\/s44325-026-00142-5","type":"journal-article","created":{"date-parts":[[2026,7,4]],"date-time":"2026-07-04T22:26:36Z","timestamp":1783203996000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Improving arrhythmic risk prediction using cardiac magnetic resonance within deep learning in ischemic heart disease"],"prefix":"10.1038","volume":"3","author":[{"given":"Ahmet","family":"Sen","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Richard E.","family":"Jones","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Holly","family":"Morgan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hassan","family":"Zaidi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Brian P.","family":"Halliday","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Daniel J.","family":"Hammersley","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Amedeo","family":"Chiribiri","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Divaka","family":"Perera","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sanjay K.","family":"Prasad","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Martin J.","family":"Bishop","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,7,5]]},"reference":[{"key":"142_CR1","doi-asserted-by":"publisher","first-page":"6","DOI":"10.1016\/j.hlc.2018.08.026","volume":"28","author":"CX Wong","year":"2019","unstructured":"Wong, C. X. et al. Epidemiology of sudden cardiac death: global and regional perspectives. Heart Lung Circ. 28, 6\u201314 (2019).","journal-title":"Heart Lung Circ."},{"key":"142_CR2","doi-asserted-by":"publisher","first-page":"S118","DOI":"10.1016\/j.jelectrocard.2007.06.023","volume":"40","author":"R Mehra","year":"2007","unstructured":"Mehra, R. Global public health problem of sudden cardiac death. J. Electrocardiol. 40, S118\u2013S122 (2007).","journal-title":"J. Electrocardiol."},{"key":"142_CR3","doi-asserted-by":"publisher","first-page":"111","DOI":"10.15420\/aer.2018:15:2","volume":"7","author":"NT Srinivasan","year":"2018","unstructured":"Srinivasan, N. T. & Schilling, R. J. Sudden cardiac death and arrhythmias. Arrhythm. Electrophysiol. Rev. 7, 111 (2018).","journal-title":"Arrhythm. Electrophysiol. Rev."},{"key":"142_CR4","doi-asserted-by":"publisher","DOI":"10.1186\/s12872-018-0851-z","volume":"18","author":"M Albanese","year":"2018","unstructured":"Albanese, M. et al. In-hospital major arrhythmias, arrhythmic death and resuscitation after successful primary percutaneous intervention for acute transmural infarction: a retrospective single-centre cohort study. BMC Cardiovasc. Disord. 18, 116 (2018).","journal-title":"BMC Cardiovasc. Disord."},{"key":"142_CR5","doi-asserted-by":"publisher","first-page":"euad203","DOI":"10.1093\/europace\/euad203","volume":"25","author":"J Tfelt-Hansen","year":"2023","unstructured":"Tfelt-Hansen, J. et al. Risk stratification of sudden cardiac death: a review. Europace 25, euad203 (2023).","journal-title":"Europace"},{"key":"142_CR6","doi-asserted-by":"publisher","first-page":"737","DOI":"10.1111\/pace.13969","volume":"43","author":"J Gould","year":"2020","unstructured":"Gould, J. et al. High mean entropy calculated from cardiac mri texture analysis is associated with antitachycardia pacing failure. Pacing Clin. Electrophysiol. 43, 737\u2013745 (2020).","journal-title":"Pacing Clin. Electrophysiol."},{"key":"142_CR7","doi-asserted-by":"publisher","first-page":"3411","DOI":"10.1007\/s00330-023-10362-3","volume":"34","author":"W-X Wang","year":"2024","unstructured":"Wang, W.-X. et al. Left ventricular entropy is a novel predictor of major adverse cardiac events (MACE) in patients with coronary atherosclerosis: a multi-center study. Eur. Radiol. 34, 3411\u20133421 (2024).","journal-title":"Eur. Radiol."},{"key":"142_CR8","first-page":"628","volume":"16","author":"RE Jones","year":"2023","unstructured":"Jones, R. E. et al. Comprehensive phenotypic characterization of late gadolinium enhancement predicts sudden cardiac death in coronary artery disease. Cardiovasc. Imaging 16, 628\u2013638 (2023).","journal-title":"Cardiovasc. Imaging"},{"key":"142_CR9","doi-asserted-by":"crossref","unstructured":"Srivats, S. et al. Sudden cardiac arrest: Limitations in risk-stratification and treatment, and the potential for digital technologies and artificial intelligence to improve prediction and outcomes. Prog. Cardiovasc. Dis. 91, 144\u2013166 (2025).","DOI":"10.1016\/j.pcad.2025.06.005"},{"key":"142_CR10","doi-asserted-by":"publisher","first-page":"202","DOI":"10.1161\/01.CIR.96.1.202","volume":"96","author":"P Savard","year":"1997","unstructured":"Savard, P. et al. Risk stratification after myocardial infarction using signal-averaged electrocardiographic criteria adjusted for sex, age, and myocardial infarction location. Circulation 96, 202\u2013213 (1997).","journal-title":"Circulation"},{"key":"142_CR11","doi-asserted-by":"publisher","first-page":"288","DOI":"10.1016\/j.jacc.2007.08.058","volume":"51","author":"I Goldenberg","year":"2008","unstructured":"Goldenberg, I. et al. Risk stratification for primary implantation of a cardioverter-defibrillator in patients with ischemic left ventricular dysfunction. J. Am. Coll. Cardiol. 51, 288\u2013296 (2008).","journal-title":"J. Am. Coll. Cardiol."},{"key":"142_CR12","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-018-28327-8","volume":"8","author":"AM Ga\u00f1\u00e1n-Calvo","year":"2018","unstructured":"Ga\u00f1\u00e1n-Calvo, A. M., Hnatkova, K., Romero-Calvo, \u00c1, Fajardo-L\u00f3pez, J. & Malik, M. Risk stratifiers for arrhythmic and non-arrhythmic mortality after acute myocardial infarction. Sci. Rep. 8, 9897 (2018).","journal-title":"Sci. Rep."},{"key":"142_CR13","first-page":"248","volume":"34","author":"C DR","year":"1972","unstructured":"DR, C. Regression models and life tables. JR Stat. Soc. 34, 248\u2013275 (1972).","journal-title":"JR Stat. Soc."},{"key":"142_CR14","doi-asserted-by":"publisher","first-page":"1345","DOI":"10.1093\/ije\/dyq063","volume":"39","author":"S Thompson","year":"2010","unstructured":"Thompson, S. et al. Statistical methods for the time-to-event analysis of individual participant data from multiple epidemiological studies. Int. J. Epidemiol. 39, 1345\u20131359 (2010).","journal-title":"Int. J. Epidemiol."},{"key":"142_CR15","doi-asserted-by":"publisher","first-page":"431","DOI":"10.1038\/sj.bjc.6601119","volume":"89","author":"MJ Bradburn","year":"2003","unstructured":"Bradburn, M. J., Clark, T. G., Love, S. B. & Altman, D. G. Survival analysis part ii: multivariate data analysis\u2013an introduction to concepts and methods. Br. J. Cancer 89, 431\u2013436 (2003).","journal-title":"Br. J. Cancer"},{"key":"142_CR16","doi-asserted-by":"publisher","first-page":"e70161","DOI":"10.1002\/sim.70161","volume":"44","author":"PC Austin","year":"2025","unstructured":"Austin, P. C. & Giardiello, D. The impact of violation of the proportional hazards assumption on the calibration of the Cox proportional hazards model. Stat. Med. 44, e70161 (2025).","journal-title":"Stat. Med."},{"key":"142_CR17","doi-asserted-by":"publisher","first-page":"334","DOI":"10.1038\/s44161-022-00041-9","volume":"1","author":"DM Popescu","year":"2022","unstructured":"Popescu, D. M. et al. Arrhythmic sudden death survival prediction using deep learning analysis of scarring in the heart. Nat. cardiovascular Res. 1, 334\u2013343 (2022).","journal-title":"Nat. cardiovascular Res."},{"key":"142_CR18","doi-asserted-by":"publisher","first-page":"1302811","DOI":"10.1155\/2021\/1302811","volume":"2021","author":"S Abd ElHafeez","year":"2021","unstructured":"Abd ElHafeez, S. et al. Methods to analyze time-to-event data: the Cox regression analysis. Oxid. Med. Cell. Longev. 2021, 1302811 (2021).","journal-title":"Oxid. Med. Cell. Longev."},{"key":"142_CR19","doi-asserted-by":"publisher","DOI":"10.1186\/s12933-024-02302-2","volume":"23","author":"N Jiang","year":"2024","unstructured":"Jiang, N., Wu, Y. & Li, C. Limitations of using Cox proportional hazards model in cardiovascular research. Cardiovasc. Diabetol. 23, 219 (2024).","journal-title":"Cardiovasc. Diabetol."},{"key":"142_CR20","doi-asserted-by":"publisher","first-page":"305","DOI":"10.1111\/cts.12541","volume":"11","author":"X Gong","year":"2018","unstructured":"Gong, X., Hu, M. & Zhao, L. Big data toolsets to pharmacometrics: application of machine learning for time-to-event analysis. Clin. Transl. Sci. 11, 305\u2013311 (2018).","journal-title":"Clin. Transl. Sci."},{"key":"142_CR21","first-page":"0449","volume":"6","author":"Z Wang","year":"2026","unstructured":"Wang, Z. et al. Survival Modeling Using Deep Learning, Machine Learning, and Statistical Methods: A Comparative Analysis for Predicting Mortality After Hospital Admission. Health Data Science 6, 0449 (2026).","journal-title":"Health Data Science"},{"key":"142_CR22","doi-asserted-by":"publisher","first-page":"110234","DOI":"10.1016\/j.knosys.2022.110234","volume":"262","author":"M Krzyzi\u0144ski","year":"2023","unstructured":"Krzyzi\u0144ski, M., Spytek, M., Baniecki, H. & Biecek, P. Survshap (t): time-dependent explanations of machine learning survival models. Knowl.-Based Syst. 262, 110234 (2023).","journal-title":"Knowl.-Based Syst."},{"key":"142_CR23","doi-asserted-by":"publisher","first-page":"841","DOI":"10.1214\/08-AOAS169","volume":"2","author":"H Ishwaran","year":"2008","unstructured":"Ishwaran, H., Kogalur, U. B., Blackstone, E. H. & Lauer, M. S. Random survival forests. Ann. Appl. Stat. 2, 841\u2013860 (2008).","journal-title":"Ann. Appl. Stat."},{"key":"142_CR24","doi-asserted-by":"publisher","DOI":"10.1186\/s12874-018-0482-1","volume":"18","author":"JL Katzman","year":"2018","unstructured":"Katzman, J. L. et al. Deepsurv: personalized treatment recommender system using a Cox proportional hazards deep neural network. BMC Med. Res. Methodol. 18, 24 (2018).","journal-title":"BMC Med. Res. Methodol."},{"key":"142_CR25","doi-asserted-by":"publisher","first-page":"708406","DOI":"10.3389\/fcvm.2021.758635","volume":"8","author":"Y Ye","year":"2021","unstructured":"Ye, Y. et al. Scar entropy from late gadolinium enhancement cardiac magnetic resonance imaging for the prediction of ventricular arrhythmias in hypertrophic cardiomyopathy. Front. Cardiovasc. Med. 8, 708406 (2021).","journal-title":"Front. Cardiovasc. Med."},{"key":"142_CR26","first-page":"e035678","volume":"14","author":"R Lusk","year":"2025","unstructured":"Lusk, R. et al. Random survival forests improve cardiovascular risk prediction compared with Cox models: evidence from a population-based cohort. J. Am. Heart Assoc. 14, e035678 (2025).","journal-title":"J. Am. Heart Assoc."},{"key":"142_CR27","doi-asserted-by":"publisher","first-page":"1082778","DOI":"10.3389\/fcvm.2023.1082778","volume":"10","author":"HA Zaidi","year":"2023","unstructured":"Zaidi, H. A. et al. Machine learning analysis of complex late gadolinium enhancement patterns to improve risk prediction of major arrhythmic events. Front. Cardiovasc. Med. 10, 1082778 (2023).","journal-title":"Front. Cardiovasc. Med."},{"key":"142_CR28","doi-asserted-by":"publisher","first-page":"131","DOI":"10.1007\/s10840-016-0213-7","volume":"48","author":"M Pimentel","year":"2017","unstructured":"Pimentel, M. et al. Predictors of serious arrhythmic events in patients with nonischemic heart failure. J. Interv. Card. Electrophysiol. 48, 131\u2013139 (2017).","journal-title":"J. Interv. Card. Electrophysiol."},{"key":"142_CR29","doi-asserted-by":"publisher","first-page":"e0297793","DOI":"10.1371\/journal.pone.0297793","volume":"19","author":"M Coriano","year":"2024","unstructured":"Coriano, M. et al. Deep learning-based prediction of major arrhythmic events in dilated cardiomyopathy: a proof of concept study. PLoS ONE 19, e0297793 (2024).","journal-title":"PLoS ONE"},{"key":"142_CR30","doi-asserted-by":"publisher","first-page":"2045","DOI":"10.1002\/ejhf.2288","volume":"23","author":"P Gentile","year":"2021","unstructured":"Gentile, P. et al. Post-discharge arrhythmic risk stratification of patients with acute myocarditis and life-threatening ventricular tachyarrhythmias. Eur. J. Heart Fail. 23, 2045\u20132054 (2021).","journal-title":"Eur. J. Heart Fail."},{"key":"142_CR31","doi-asserted-by":"crossref","unstructured":"Ishida, S. et al. Risk stratification of major arrhythmia events in Japanese patients with Brugada syndrome using machine learning models. Heart Rhythm O2 6, 987\u2013994 (2025).","DOI":"10.1016\/j.hroo.2025.04.009"},{"key":"142_CR32","doi-asserted-by":"publisher","first-page":"6","DOI":"10.1186\/s13040-025-00510-4","volume":"19","author":"P Lukyanenko","year":"2026","unstructured":"Lukyanenko, P. et al. Deep survival analysis from adult and pediatric electrocardiograms: a multi-center benchmark study. BioData Mining 19, 6 (2026).","journal-title":"BioData Mining"},{"key":"142_CR33","doi-asserted-by":"publisher","first-page":"299","DOI":"10.1253\/circj.CJ-21-0622","volume":"86","author":"X Zhou","year":"2022","unstructured":"Zhou, X. et al. Deep learning-based recurrence prediction of atrial fibrillation after catheter ablation. Circ. J. 86, 299\u2013308 (2022).","journal-title":"Circ. J."},{"key":"142_CR34","doi-asserted-by":"publisher","first-page":"480","DOI":"10.1016\/j.jacep.2018.12.005","volume":"5","author":"AF Androulakis","year":"2019","unstructured":"Androulakis, A. F. et al. Entropy as a novel measure of myocardial tissue heterogeneity for prediction of ventricular arrhythmias and mortality in post-infarct patients. JACC Clin. Electrophysiol. 5, 480\u2013489 (2019).","journal-title":"JACC Clin. Electrophysiol."},{"key":"142_CR35","doi-asserted-by":"publisher","first-page":"758635","DOI":"10.3389\/fcvm.2021.758635","volume":"8","author":"Y Ye","year":"2021","unstructured":"Ye, Y. et al. Mean scar entropy by late gadolinium enhancement cardiac magnetic resonance is associated with ventricular arrhythmias events in hypertrophic cardiomyopathy. Front. Cardiovasc. Med. 8, 758635 (2021).","journal-title":"Front. Cardiovasc. Med."},{"key":"142_CR36","doi-asserted-by":"publisher","first-page":"1177","DOI":"10.1016\/j.jcmg.2018.07.003","volume":"12","author":"RG Muthalaly","year":"2019","unstructured":"Muthalaly, R. G. et al. Left ventricular entropy is a novel predictor of arrhythmic events in patients with dilated cardiomyopathy receiving defibrillators for primary prevention. JACC Cardiovasc. Imaging 12, 1177\u20131184 (2019).","journal-title":"JACC Cardiovasc. Imaging"},{"key":"142_CR37","doi-asserted-by":"crossref","unstructured":"Wu, K. C. Myocardial tissue characterization to predict ventricular arrhythmic risk: road well-traveled but so far to go. Cardiovasc. Imaging 16, 639\u2013641 (2023).","DOI":"10.1016\/j.jcmg.2022.12.017"},{"key":"142_CR38","first-page":"1173","volume":"18","author":"H Morgan","year":"2025","unstructured":"Morgan, H. et al. Myocardial scar and arrhythmic risk stratification in ischemic left ventricular systolic dysfunction. Cardiovasc. Imaging 18, 1173\u20131175 (2025).","journal-title":"Cardiovasc. Imaging"},{"key":"142_CR39","first-page":"A11477","volume":"140","author":"BP Halliday","year":"2019","unstructured":"Halliday, B. P. et al. Improving arrhythmic risk stratification in non-ischemic dilated cardiomyopathy through the evaluation of novel scar characteristics using cmr. Circulation 140, A11477\u2013A11477 (2019).","journal-title":"Circulation"},{"key":"142_CR40","doi-asserted-by":"publisher","first-page":"238","DOI":"10.1016\/j.jacep.2020.08.036","volume":"7","author":"G Balaban","year":"2021","unstructured":"Balaban, G. et al. Late-gadolinium enhancement interface area and electrophysiological simulations predict arrhythmic events in patients with nonischemic dilated cardiomyopathy. Clin. Electrophysiol. 7, 238\u2013249 (2021).","journal-title":"Clin. Electrophysiol."},{"key":"142_CR41","doi-asserted-by":"publisher","first-page":"e040517","DOI":"10.1161\/JAHA.124.040517","volume":"14","author":"DJ Hammersley","year":"2025","unstructured":"Hammersley, D. J. et al. Fibrosis entropy is associated with life-threatening arrhythmia in nonischemic cardiomyopathy. J. Am. Heart Assoc. 14, e040517 (2025).","journal-title":"J. Am. Heart Assoc."},{"key":"142_CR42","doi-asserted-by":"publisher","first-page":"496","DOI":"10.1080\/01621459.1999.10474144","volume":"94","author":"JP Fine","year":"1999","unstructured":"Fine, J. P. & Gray, R. J. A proportional hazards model for the subdistribution of a competing risk. J. Am. Stat. Assoc. 94, 496\u2013509 (1999).","journal-title":"J. Am. Stat. Assoc."},{"key":"142_CR43","doi-asserted-by":"publisher","first-page":"862","DOI":"10.1161\/CIRCULATIONAHA.123.065300","volume":"148","author":"D Perera","year":"2023","unstructured":"Perera, D. et al. Arrhythmia and death following percutaneous revascularization in ischemic left ventricular dysfunction: prespecified analyses from the revived-bcis2 trial. Circulation 148, 862\u2013871 (2023).","journal-title":"Circulation"},{"key":"142_CR44","doi-asserted-by":"publisher","first-page":"1351","DOI":"10.1056\/NEJMoa2206606","volume":"387","author":"D Perera","year":"2022","unstructured":"Perera, D. et al. Percutaneous revascularization for ischemic left ventricular dysfunction. N. Engl. J. Med. 387, 1351\u20131360 (2022).","journal-title":"N. Engl. J. Med."},{"key":"142_CR45","doi-asserted-by":"publisher","unstructured":"REVIVED-BCIS2 Investigators. Revived-bcis2 trial protocol version 8.1. https:\/\/doi.org\/10.1186\/ISRCTN45979711 (2018).","DOI":"10.1186\/ISRCTN45979711"},{"key":"142_CR46","doi-asserted-by":"publisher","first-page":"150","DOI":"10.1016\/j.jcmg.2010.11.015","volume":"4","author":"AS Flett","year":"2011","unstructured":"Flett, A. S. et al. Evaluation of techniques for the quantification of myocardial scar of differing etiology using cardiac magnetic resonance. JACC Cardiovasc. Imaging 4, 150\u2013156 (2011).","journal-title":"JACC Cardiovasc. Imaging"},{"key":"142_CR47","doi-asserted-by":"publisher","first-page":"187","DOI":"10.1111\/j.2517-6161.1972.tb00899.x","volume":"34","author":"DR Cox","year":"1972","unstructured":"Cox, D. R. Regression models and life-tables. J. R. Stat. Soc. Ser. B 34, 187\u2013220 (1972).","journal-title":"J. R. Stat. Soc. Ser. B"},{"key":"142_CR48","doi-asserted-by":"publisher","first-page":"1317","DOI":"10.21105\/joss.01317","volume":"4","author":"C Davidson-Pilon","year":"2019","unstructured":"Davidson-Pilon, C. lifelines: survival analysis in python. J. Open Source Softw. 4, 1317 (2019).","journal-title":"J. Open Source Softw."},{"key":"142_CR49","first-page":"1","volume":"21","author":"S P\u00f6lsterl","year":"2020","unstructured":"P\u00f6lsterl, S. scikit-survival: a library for time-to-event analysis built on top of scikit-learn. J. Mach. Learn. Res. 21, 1\u20136 (2020).","journal-title":"J. Mach. Learn. Res."},{"key":"142_CR50","unstructured":"Chollet, F. keras. https:\/\/github.com\/fchollet\/keras (2015)."},{"key":"142_CR51","unstructured":"Abadi, M. et al. TensorFlow: Large-scale machine learning on heterogeneous systems. https:\/\/www.tensorflow.org\/ (2015)."},{"key":"142_CR52","unstructured":"Harrell, F. E. & Levy, D. G. Regression modeling strategies. R package version 6\u20133 (Springer, 2022)."},{"key":"142_CR53","doi-asserted-by":"publisher","first-page":"2529","DOI":"10.1002\/(SICI)1097-0258(19990915\/30)18:17\/18<2529::AID-SIM274>3.0.CO;2-5","volume":"18","author":"E Graf","year":"1999","unstructured":"Graf, E., Schmoor, C., Sauerbrei, W. & Schumacher, M. Assessment and comparison of prognostic classification schemes for survival data. Stat. Med. 18, 2529\u20132545 (1999).","journal-title":"Stat. Med."},{"key":"142_CR54","doi-asserted-by":"publisher","first-page":"92","DOI":"10.1111\/j.0006-341X.2005.030814.x","volume":"61","author":"PJ Heagerty","year":"2005","unstructured":"Heagerty, P. J. & Zheng, Y. Survival model predictive accuracy and ROC curves. Biometrics 61, 92\u2013105 (2005).","journal-title":"Biometrics"},{"key":"142_CR55","first-page":"1","volume":"57","author":"RJ Tibshirani","year":"1993","unstructured":"Tibshirani, R. J. & Efron, B. An introduction to the bootstrap. Monogr. Stat. Appl. Probab. 57, 1\u2013436 (1993).","journal-title":"Monogr. Stat. Appl. Probab."},{"key":"142_CR56","doi-asserted-by":"crossref","unstructured":"Austin, P. C., Harrell, F. E. & van Klaveren, D. Graphical calibration curves and the integrated calibration index (ICI) for survival models. Stat. Med. 39, 2714\u20132742 (2020).","DOI":"10.1002\/sim.8570"},{"key":"142_CR57","doi-asserted-by":"publisher","first-page":"420","DOI":"10.4187\/respcare.00811","volume":"56","author":"J Villar","year":"2011","unstructured":"Villar, J. et al. A risk tertiles model for predicting mortality in patients with acute respiratory distress syndrome: age, plateau pressure, and PaO2\/FIO2at ARDS onset can predict mortality. Respir. Care 56, 420\u2013428 (2011).","journal-title":"Respir. Care"}],"container-title":["npj Cardiovascular Health"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s44325-026-00142-5","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s44325-026-00142-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s44325-026-00142-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,22]],"date-time":"2026-07-22T07:01:40Z","timestamp":1784703700000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s44325-026-00142-5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,5]]},"references-count":57,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2026,12]]}},"alternative-id":["142"],"URL":"https:\/\/doi.org\/10.1038\/s44325-026-00142-5","relation":{},"ISSN":["2948-2836"],"issn-type":[{"value":"2948-2836","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7,5]]},"assertion":[{"value":"29 January 2026","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"23 June 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"5 July 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"The authors declare no competing interests.","order":1,"name":"Ethics","label":"Competing interests","group":{"name":"EthicsHeading","label":"Ethics"}}],"article-number":"42"}}