{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,13]],"date-time":"2026-10-13T18:18:33Z","timestamp":1791915513207,"version":"4.3.4"},"reference-count":41,"publisher":"Oxford University Press (OUP)","issue":"6","license":[{"start":{"date-parts":[[2025,10,6]],"date-time":"2025-10-06T00:00:00Z","timestamp":1759708800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100018722","name":"Jaap Schouten Foundation","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100018722","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,11,20]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Aims<\/jats:title>\n                    <jats:p>We aimed to compare performances of conventional survival models with machine learning (ML) survival models for incident heart failure (HF) in men and women without prevalent HF, cardiomyopathy (CM) or ischaemic heart disease (IHD), and to identify potential high-risk precursors overlooked by conventional survival models.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods and results<\/jats:title>\n                    <jats:p>We predicted 10-year risk of incident HF in 266 306 women (2894 events) and 212 061 men (4213 events). We constructed multivariable Cox models, first using \u223c 400 baseline characteristics, and subsequently only those remaining after LASSO stability selection. We also used Random Survival Forest (RSF) and eXtreme Gradient Survival Boosting (XGBoost). Performances were assessed using internal cross validation and hold-out sets, with C-indices, calibration curves and net-benefit analyses. Model performances were comparable during internal validation: XGBoost (C-index \u00b1 SE) (men: 0.79 \u00b1 0.0040, women: 0.83 \u00b1 0.0023) showed similar performance to the multivariable Cox model (men: 0.80 \u00b1 0.0031, women: 0.83 \u00b1 0.0022) and Cox models after LASSO stability selection, while RSF showed numerically slightly lower performance (men: 0.78 \u00b1 0.0025, women: 0.81 \u00b1 0.0015). Findings were similar in the hold-out sets. Age, cystatin-C, lifetime treatments\/medications, other heart disease, systolic blood pressure, and spirometry measures were identified as high-risk factors in both model types for both sexes. Additionally, sex-specific and model-specific risk factors were identified.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>Machine learning models and Cox proportional hazard models performed well and similarly for 10-year incident HF risk prediction in the general population. However, sex-specific and model-specific risk predictors were found. Spirometry measures, rarely included in existing models, were identified as important risk factors. Our results suggest that ML models for HF prediction in the general population reveal insights that would otherwise remain unnoticed.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1093\/ehjdh\/ztaf118","type":"journal-article","created":{"date-parts":[[2025,10,4]],"date-time":"2025-10-04T11:47:05Z","timestamp":1759578425000},"page":"1234-1245","source":"Crossref","is-referenced-by-count":4,"title":["High-dimensional machine learning models for prediction of heart failure in more than 400 000 men and women from the UK Biobank"],"prefix":"10.1093","volume":"6","author":[{"given":"Thomas F","family":"Kok","sequence":"first","affiliation":[{"name":"Department of Cardiology, Erasmus MC, Thorax Centre, Cardiovascular Institute , P.O. Box 2040, 3000 CA, Rotterdam ,","place":["The Netherlands"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Navin","family":"Suthahar","sequence":"additional","affiliation":[{"name":"Department of Cardiology, Erasmus MC, Thorax Centre, Cardiovascular Institute , P.O. Box 2040, 3000 CA, Rotterdam ,","place":["The Netherlands"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jesse H","family":"Krijthe","sequence":"additional","affiliation":[{"name":"Pattern Recognition and Bioinformatics, TU Delft, Faculty of Electrical Engineering, Mathematics and Computer Science , van Mourik Broekmanweg 6, 2628XE, Delft ,","place":["The Netherlands"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4775-9140","authenticated-orcid":false,"given":"Rudolf A","family":"de Boer","sequence":"additional","affiliation":[{"name":"Department of Cardiology, Erasmus MC, Thorax Centre, Cardiovascular Institute , P.O. Box 2040, 3000 CA, Rotterdam ,","place":["The Netherlands"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2559-7128","authenticated-orcid":false,"given":"Eric","family":"Boersma","sequence":"additional","affiliation":[{"name":"Department of Cardiology, Erasmus MC, Thorax Centre, Cardiovascular Institute , P.O. Box 2040, 3000 CA, Rotterdam ,","place":["The Netherlands"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2115-9745","authenticated-orcid":false,"given":"Isabella","family":"Kardys","sequence":"additional","affiliation":[{"name":"Department of Cardiology, Erasmus MC, Thorax Centre, Cardiovascular Institute , P.O. Box 2040, 3000 CA, Rotterdam ,","place":["The Netherlands"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"286","published-online":{"date-parts":[[2025,10,6]]},"reference":[{"key":"2025111918523759600_ztaf118-B1","first-page":"e0213653","article-title":"Evaluating risk prediction models for adults with heart failure: a systematic literature review","volume":"14","author":"Di Tanna","year":"2020","journal-title":"PLoS One"},{"key":"2025111918523759600_ztaf118-B2","doi-asserted-by":"crossref","first-page":"e0213653","DOI":"10.1371\/journal.pone.0213653","article-title":"Cardiovascular disease risk prediction using automated machine learning: a prospective study of 423,604 UK Biobank participants","volume":"14","author":"Alaa","year":"2019","journal-title":"PLoS One"},{"key":"2025111918523759600_ztaf118-B3","doi-asserted-by":"crossref","first-page":"175","DOI":"10.1093\/ehjdh\/ztac054","article-title":"What drives performance in machine learning models for predicting heart failure outcome?","volume":"4","author":"Gutman","year":"2022","journal-title":"Eur Heart J Digit Health"},{"key":"2025111918523759600_ztaf118-B4","first-page":"261","article-title":"Implementation of machine learning model to predict heart failure disease","volume":"10","author":"Alotaibi","year":"2019","journal-title":"Int J Adv Comput Sci Appl"},{"key":"2025111918523759600_ztaf118-B5","doi-asserted-by":"crossref","first-page":"430","DOI":"10.1016\/j.ahj.2011.12.013","article-title":"Sex differences in in-hospital mortality in acute decompensated heart failure with reduced and preserved ejection fraction","volume":"163","author":"Hsich","year":"2012","journal-title":"Am Heart J"},{"key":"2025111918523759600_ztaf118-B6","doi-asserted-by":"crossref","first-page":"3859","DOI":"10.1093\/eurheartj\/ehz835","article-title":"Sex differences in heart failure","volume":"40","author":"Lam","year":"2019","journal-title":"Eur Heart J"},{"key":"2025111918523759600_ztaf118-B7","doi-asserted-by":"crossref","first-page":"198","DOI":"10.1161\/CIRCULATIONAHA.118.034271","article-title":"Sex differences in cardiovascular pathophysiology: why women are overrepresented in heart failure with preserved ejection fraction","volume":"138","author":"Beale","year":"2018","journal-title":"Circulation"},{"key":"2025111918523759600_ztaf118-B8","doi-asserted-by":"crossref","first-page":"3068","DOI":"10.1161\/01.CIR.0000039105.49749.6F","article-title":"Lifetime risk for developing congestive heart failure: the Framingham Heart Study","volume":"106","author":"Lloyd-Jones","year":"2002","journal-title":"Circulation"},{"key":"2025111918523759600_ztaf118-B9","doi-asserted-by":"crossref","first-page":"e002883","DOI":"10.1161\/CIRCHEARTFAILURE.115.002883","article-title":"Risk factors for incident hospitalized heart failure with preserved versus reduced ejection fraction in a multiracial cohort of postmenopausal women","volume":"9","author":"Eaton","year":"2016","journal-title":"Circ Heart Fail"},{"key":"2025111918523759600_ztaf118-B10","doi-asserted-by":"crossref","first-page":"639","DOI":"10.2217\/14622416.6.6.639","article-title":"UK Biobank: from concept to reality","volume":"6","author":"Ollier","year":"2005","journal-title":"Pharmacogenomics"},{"key":"2025111918523759600_ztaf118-B11","doi-asserted-by":"crossref","first-page":"1980","DOI":"10.1016\/S0140-6736(07)60924-6","article-title":"UK Biobank: bank on it","volume":"369","author":"Palmer","year":"2007","journal-title":"Lancet"},{"key":"2025111918523759600_ztaf118-B12","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1186\/1745-6215-16-S2-O68","article-title":"Challenges of linking to routine healthcare records in UK Biobank","volume":"16","author":"Adamska","year":"2015","journal-title":"Trials"},{"key":"2025111918523759600_ztaf118-B13","doi-asserted-by":"crossref","first-page":"417","DOI":"10.1111\/j.1467-9868.2010.00740.x","article-title":"Stability selection","volume":"72","author":"Meinshausen","year":"2010","journal-title":"J R Stat Soc Series B Stat Methodol"},{"key":"2025111918523759600_ztaf118-B14","doi-asserted-by":"crossref","first-page":"267","DOI":"10.1111\/j.2517-6161.1996.tb02080.x","article-title":"Regression shrinkage and selection via the lasso","volume":"58","author":"Tibshirani","year":"1996","journal-title":"J R Stat Soc Series B Stat Methodol"},{"key":"2025111918523759600_ztaf118-B15","doi-asserted-by":"crossref","first-page":"213","DOI":"10.1023\/A:1018917218956","article-title":"Weak greedy algorithms [*] this research was supported by National Science Foundation grant DMS 9970326 and by ONR grant N00014-96-1-1003","volume":"12","author":"Temlyakov","year":"2000","journal-title":"Adv Comput Math"},{"key":"2025111918523759600_ztaf118-B16","first-page":"841","article-title":"Random survival forests","volume":"2","author":"Ishwaran","year":"2008","journal-title":"Ann Appl Sci"},{"key":"2025111918523759600_ztaf118-B17","doi-asserted-by":"crossref","first-page":"5","DOI":"10.1023\/A:1010933404324","article-title":"Random forests","volume":"45","author":"Breiman","year":"2001","journal-title":"Mach Learn"},{"key":"2025111918523759600_ztaf118-B18","author":"Chen"},{"key":"2025111918523759600_ztaf118-B19","doi-asserted-by":"crossref","first-page":"559","DOI":"10.1002\/sim.2324","article-title":"Confidence intervals for an effect size measure based on the Mann\u2013Whitney statistic. Part 2: asymptotic methods and evaluation","volume":"25","author":"Newcombe","year":"2006","journal-title":"Stat Med"},{"key":"2025111918523759600_ztaf118-B20","doi-asserted-by":"crossref","first-page":"2543","DOI":"10.1001\/jama.1982.03320430047030","article-title":"Evaluating the yield of medical tests","volume":"247","author":"Harrell","year":"1982","journal-title":"JAMA"},{"key":"2025111918523759600_ztaf118-B21","doi-asserted-by":"crossref","first-page":"2388","DOI":"10.1016\/j.jacc.2019.02.057","article-title":"10-year risk equations for incident heart failure in the general population","volume":"73","author":"Khan","year":"2019","journal-title":"J Am Coll Cardiol"},{"key":"2025111918523759600_ztaf118-B22","doi-asserted-by":"crossref","first-page":"2370","DOI":"10.1161\/CIRCULATIONAHA.120.053134","article-title":"Development and validation of machine learning\u2013based race-specific models to predict 10-year risk of heart failure: a multicohort analysis","volume":"143","author":"Segar","year":"2021","journal-title":"Circulation"},{"key":"2025111918523759600_ztaf118-B23","doi-asserted-by":"crossref","first-page":"6968","DOI":"10.1038\/s41598-021-86327-7","article-title":"Explainable machine learning can outperform Cox regression predictions and provide insights in breast cancer survival","volume":"11","author":"Moncada-Torres","year":"2021","journal-title":"Sci Rep"},{"key":"2025111918523759600_ztaf118-B24","doi-asserted-by":"crossref","first-page":"e23","DOI":"10.5808\/gi.22036","article-title":"Comparison of survival prediction models for pancreatic cancer: Cox model versus machine learning models","volume":"20","author":"Kim","year":"2022","journal-title":"Genomics Inform"},{"key":"2025111918523759600_ztaf118-B25","doi-asserted-by":"crossref","first-page":"812276","DOI":"10.3389\/fcvm.2022.812276","article-title":"Comparing machine learning models and statistical models for predicting heart failure events: a systematic review and meta-analysis","volume":"9","author":"Sun","year":"2022","journal-title":"Front Cardiovasc Med"},{"key":"2025111918523759600_ztaf118-B26","doi-asserted-by":"crossref","first-page":"706","DOI":"10.1016\/j.ejheart.2006.01.010","article-title":"Heart failure and chronic obstructive pulmonary disease: an ignored combination?","volume":"8","author":"Rutten","year":"2006","journal-title":"Eur J Heart Fail"},{"key":"2025111918523759600_ztaf118-B27","doi-asserted-by":"crossref","first-page":"711","DOI":"10.1136\/bmj.313.7059.711","article-title":"Impaired lung function and mortality risk in men and women: findings from the Renfrew and Paisley prospective population study","volume":"313","author":"Hole","year":"1996","journal-title":"Bmj"},{"key":"2025111918523759600_ztaf118-B28","doi-asserted-by":"crossref","first-page":"497","DOI":"10.7326\/0003-4819-142-7-200504050-00008","article-title":"Cystatin C concentration as a risk factor for heart failure in older adults","volume":"142","author":"Sarnak","year":"2005","journal-title":"Ann Intern Med"},{"key":"2025111918523759600_ztaf118-B29","doi-asserted-by":"crossref","first-page":"1251","DOI":"10.1001\/jama.289.10.1251","article-title":"Plasma homocysteine and risk for congestive heart failure in adults without prior myocardial infarction","volume":"289","author":"Vasan","year":"2003","journal-title":"JAMA"},{"key":"2025111918523759600_ztaf118-B30","doi-asserted-by":"crossref","first-page":"1932","DOI":"10.1373\/clinchem.2009.128397","article-title":"Cystatin C and cardiovascular risk","volume":"55","author":"Taglieri","year":"2009","journal-title":"Clin Chem"},{"key":"2025111918523759600_ztaf118-B31","doi-asserted-by":"crossref","first-page":"256","DOI":"10.1016\/j.cardfail.2008.10.030","article-title":"Prognostic value of high-sensitivity C-reactive protein in heart failure: a systematic review","volume":"15","author":"Ara\u00fajo","year":"2009","journal-title":"J Card Fail"},{"key":"2025111918523759600_ztaf118-B32","doi-asserted-by":"crossref","first-page":"514","DOI":"10.1016\/j.ahj.2006.02.023","article-title":"C-reactive protein and risk of heart failure. The Rotterdam study","volume":"152","author":"Kardys","year":"2006","journal-title":"Am Heart J"},{"key":"2025111918523759600_ztaf118-B33","doi-asserted-by":"crossref","first-page":"1951","DOI":"10.3390\/jcm11071951","article-title":"Red blood cell distribution width in heart failure: pathophysiology, prognostic role, controversies and dilemmas","volume":"11","author":"Xanthopoulos","year":"2022","journal-title":"J Clin Med"},{"key":"2025111918523759600_ztaf118-B34","doi-asserted-by":"crossref","first-page":"6","DOI":"10.4330\/wjc.v10.i2.6","article-title":"Red blood cell distribution width in heart failure: a narrative review","volume":"10","author":"Lippi","year":"2018","journal-title":"World J Cardiol"},{"key":"2025111918523759600_ztaf118-B35","doi-asserted-by":"crossref","first-page":"1879","DOI":"10.2337\/diacare.27.8.1879","article-title":"The incidence of congestive heart failure in type 2 diabetes: an update","volume":"27","author":"Nichols","year":"2004","journal-title":"Diabetes Care"},{"key":"2025111918523759600_ztaf118-B36","doi-asserted-by":"crossref","first-page":"104259","DOI":"10.1016\/j.ebiom.2022.104259","article-title":"Sex differences in the association of fasting glucose with HbA1c, and their consequences for mortality: a Mendelian randomization study","volume":"84","author":"Yang","year":"2022","journal-title":"EBioMedicine"},{"key":"2025111918523759600_ztaf118-B37","doi-asserted-by":"crossref","first-page":"883","DOI":"10.1016\/j.ahj.2007.11.043","article-title":"Albumin levels predict survival in patients with systolic heart failure","volume":"155","author":"Horwich","year":"2008","journal-title":"Am Heart J"},{"key":"2025111918523759600_ztaf118-B38","doi-asserted-by":"crossref","first-page":"365","DOI":"10.1002\/clc.23153","article-title":"Low serum albumin: a significant predictor of reduced survival in patients with chronic heart failure","volume":"42","author":"Gotsman","year":"2019","journal-title":"Clin Cardiol"},{"key":"2025111918523759600_ztaf118-B39","doi-asserted-by":"crossref","first-page":"47","DOI":"10.1053\/j.ajkd.2011.02.391","article-title":"High-normal albuminuria and risk of heart failure in the community","volume":"58","author":"Blecker","year":"2011","journal-title":"Am J Kidney Dis"},{"key":"2025111918523759600_ztaf118-B40","doi-asserted-by":"crossref","first-page":"e002989","DOI":"10.1161\/CIRCGEN.120.002989","article-title":"Serum albumin and incident heart failure: insights from epidemiological and Mendelian randomization studies","volume":"13","author":"Zhuang","year":"2020","journal-title":"Circ Genom Precis Med"},{"key":"2025111918523759600_ztaf118-B41","doi-asserted-by":"crossref","first-page":"1026","DOI":"10.1093\/aje\/kwx246","article-title":"Comparison of sociodemographic and health-related characteristics of UK Biobank participants with those of the general population","volume":"186","author":"Fry","year":"2017","journal-title":"Am J Epidemiol"}],"container-title":["European Heart Journal - Digital Health"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/ehjdh\/advance-article-pdf\/doi\/10.1093\/ehjdh\/ztaf118\/64519351\/ztaf118.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/ehjdh\/article-pdf\/6\/6\/1234\/64519351\/ztaf118.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/ehjdh\/article-pdf\/6\/6\/1234\/64519351\/ztaf118.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,19]],"date-time":"2025-11-19T23:52:49Z","timestamp":1763596369000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/ehjdh\/article\/6\/6\/1234\/8275817"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,6]]},"references-count":41,"journal-issue":{"issue":"6","published-online":{"date-parts":[[2025,10,6]]},"published-print":{"date-parts":[[2025,11,20]]}},"URL":"https:\/\/doi.org\/10.1093\/ehjdh\/ztaf118","relation":{},"ISSN":["2634-3916"],"issn-type":[{"value":"2634-3916","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2025,11]]},"published":{"date-parts":[[2025,10,6]]}}}