{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,21]],"date-time":"2026-05-21T22:06:08Z","timestamp":1779401168191,"version":"3.53.1"},"reference-count":40,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2026,1,8]],"date-time":"2026-01-08T00:00:00Z","timestamp":1767830400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2026,2,3]],"date-time":"2026-02-03T00:00:00Z","timestamp":1770076800000},"content-version":"vor","delay-in-days":26,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/100018703","name":"HORIZON EUROPE European Innovation Council","doi-asserted-by":"publisher","award":["101080430"],"award-info":[{"award-number":["101080430"]}],"id":[{"id":"10.13039\/100018703","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["npj Digit. Med."],"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>\n                    Heart failure (HF) patients have complex health profiles that existing risk models fail to capture. We developed TRisk, a Transformer-based artificial intelligence survival model for predicting mortality using routine electronic health records (EHR) in HF patients. Using UK data from 403,534 HF patients across 1418 English general practices, we trained and validated TRisk and compared it against MAGGIC-EHR, the MAGGIC model adapted for use on routine EHR by substituting variables (e.g. left-ventricular ejection fraction) that are not routinely available. External validation was conducted on 21,767 patients from USA hospitals. In the UK cohort, TRisk achieved a concordance index (\n                    <jats:italic>C<\/jats:italic>\n                    -index): 0.845 (95% CI: 0.841, 0.849), outperforming MAGGIC-EHR (\n                    <jats:italic>C<\/jats:italic>\n                    -index: 0.728 [0.723, 0.733]) for 36-month mortality prediction. In subgroup analyses, TRisk demonstrated less variability in predictive performance by sex, age, and baseline characteristics compared to MAGGIC-EHR, suggesting less biased modelling. Evaluating TRisk in USA data via transfer learning yielded a\n                    <jats:italic>C<\/jats:italic>\n                    -index of 0.802 (0.789, 0.816). Explainability analysis revealed TRisk captured established risk factors while identifying underappreciated ones, particularly cancers and hepatic failure, with cancers maintaining prognostic utility even a decade before baseline. TRisk provides more accurate, well-calibrated mortality prediction using routine data across international healthcare settings, demonstrating potential for improved risk stratification in patients with HF.\n                  <\/jats:p>","DOI":"10.1038\/s41746-025-02296-5","type":"journal-article","created":{"date-parts":[[2026,1,8]],"date-time":"2026-01-08T06:19:13Z","timestamp":1767853153000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["A transformer-based survival model for prediction of all-cause mortality in patients with heart failure: a multi-cohort study"],"prefix":"10.1038","volume":"9","author":[{"given":"Shishir","family":"Rao","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Nouman","family":"Ahmed","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Gholamreza","family":"Salimi-Khorshidi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Christopher","family":"Yau","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Huimin","family":"Su","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Nathalie","family":"Conrad","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Folkert W.","family":"Asselbergs","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mark","family":"Woodward","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Rod","family":"Jackson","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"John GF","family":"Cleland","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kazem","family":"Rahimi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,1,8]]},"reference":[{"key":"2296_CR1","doi-asserted-by":"publisher","first-page":"572","DOI":"10.1016\/S0140-6736(17)32520-5","volume":"391","author":"N Conrad","year":"2018","unstructured":"Conrad, N. et al. Temporal trends and patterns in heart failure incidence: a population-based study of 4 million individuals. Lancet 391, 572\u2013580 (2018).","journal-title":"Lancet"},{"key":"2296_CR2","doi-asserted-by":"publisher","first-page":"440","DOI":"10.1016\/j.jchf.2014.04.008","volume":"2","author":"K Rahimi","year":"2014","unstructured":"Rahimi, K. et al. Risk prediction in patients with heart failure. A Syst. Rev. Anal. JACC Heart Fail 2, 440\u2013446 (2014).","journal-title":"A Syst. Rev. Anal. JACC Heart Fail"},{"key":"2296_CR3","doi-asserted-by":"publisher","first-page":"1404","DOI":"10.1093\/eurheartj\/ehs337","volume":"34","author":"SJ Pocock","year":"2013","unstructured":"Pocock, S. J. et al. Predicting survival in heart failure: a risk score based on 39 372 patients from 30 studies. Eur. Heart J. 34, 1404\u20131413 (2013).","journal-title":"Eur. Heart J."},{"key":"2296_CR4","doi-asserted-by":"publisher","first-page":"1424","DOI":"10.1161\/CIRCULATIONAHA.105.584102","volume":"113","author":"WC Levy","year":"2006","unstructured":"Levy, W. C. et al. The Seattle heart failure model: prediction of survival in heart failure. Circulation 113, 1424\u20131433 (2006).","journal-title":"Circulation"},{"key":"2296_CR5","first-page":"13","volume":"28","author":"SS Khanam","year":"2018","unstructured":"Khanam, S. S. et al. Validation of the MAGGIC (meta-analysis global group in chronic heart failure) heart failure risk score and the effect of adding natriuretic peptide for predicting mortality after discharge in hospitalized patients with heart failure. PLoS One 28, 13 (2018).","journal-title":"PLoS One"},{"key":"2296_CR6","doi-asserted-by":"publisher","first-page":"173","DOI":"10.1111\/ejhf.32","volume":"16","author":"U Sartipy","year":"2014","unstructured":"Sartipy, U., Dahlstr\u00f6m, U., Edner, M. & Lund, L. H. Predicting survival in heart failure: Validation of the MAGGIC heart failure risk score in 51 043 patients from the Swedish Heart Failure Registry. Eur. J. Heart Fail 16, 173\u2013179 (2014).","journal-title":"Eur. J. Heart Fail"},{"key":"2296_CR7","doi-asserted-by":"publisher","first-page":"435","DOI":"10.1001\/jamacardio.2016.5036","volume":"2","author":"LA Allen","year":"2017","unstructured":"Allen, L. A. et al. Use of risk models to predict death in the next year among individual ambulatory patients with heart failure. JAMA Cardiol. 2, 435\u2013441 (2017).","journal-title":"JAMA Cardiol."},{"key":"2296_CR8","doi-asserted-by":"publisher","first-page":"457","DOI":"10.1001\/jamacardio.2024.0284","volume":"9","author":"K McDowell","year":"2024","unstructured":"McDowell, K. et al. Prognostic models for mortality and morbidity in heart failure with preserved ejection fraction. JAMA Cardiol. 9, 457\u2013465 (2024).","journal-title":"JAMA Cardiol."},{"key":"2296_CR9","doi-asserted-by":"publisher","first-page":"452","DOI":"10.1016\/j.jchf.2018.02.001","volume":"6","author":"M Canepa","year":"2018","unstructured":"Canepa, M. et al. Performance of prognostic risk scores in chronic heart failure patients enrolled in the European Society of Cardiology heart failure long-term registry. JACC Heart Fail 6, 452\u2013462 (2018).","journal-title":"JACC Heart Fail"},{"key":"2296_CR10","doi-asserted-by":"publisher","first-page":"1150","DOI":"10.1002\/ejhf.3230","volume":"26","author":"C Settergren","year":"2024","unstructured":"Settergren, C. et al. Cause-specific death in heart failure across the ejection fraction spectrum: A comprehensive assessment of over 100 000 patients in the Swedish Heart Failure Registry. Eur. J. Heart Fail 26, 1150\u20131159 (2024).","journal-title":"Eur. J. Heart Fail"},{"key":"2296_CR11","doi-asserted-by":"publisher","first-page":"1102","DOI":"10.1001\/jamacardio.2019.3593","volume":"4","author":"N Conrad","year":"2019","unstructured":"Conrad, N. et al. Temporal trends and patterns in mortality after incident heart failure: a longitudinal analysis of 86000 individuals. JAMA Cardiol. 4, 1102\u20131111 (2019).","journal-title":"JAMA Cardiol."},{"key":"2296_CR12","doi-asserted-by":"publisher","first-page":"26","DOI":"10.1002\/ejhf.1689","volume":"22","author":"MS Anker","year":"2020","unstructured":"Anker, M. S., H\u00fclsmann, M. & Cleland, J. G. What do patients with heart failure die from? A single assassin or a conspiracy?. Eur. J. Heart Fail. 22, 26\u201328 (2020).","journal-title":"Eur. J. Heart Fail."},{"key":"2296_CR13","unstructured":"NICE. Chronic Heart Failure in Adults: Diagnosis and Management NICE Guideline. www.nice.org.uk\/guidance\/ng106 (2018)."},{"key":"2296_CR14","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-020-62922-y","volume":"10","author":"Y Li","year":"2020","unstructured":"Li, Y. et al. BEHRT: transformer for electronic health records. Sci. Rep. 10, 7155 (2020).","journal-title":"Sci. Rep."},{"key":"2296_CR15","doi-asserted-by":"publisher","first-page":"100873","DOI":"10.1016\/j.landig.2025.03.005","volume":"7","author":"S Rao","year":"2025","unstructured":"Rao, S. et al. Refined selection of individuals for preventive cardiovascular disease treatment with a transformer-based risk model. Lancet Digit. Health 7, 100873 (2025).","journal-title":"Lancet Digit. Health"},{"key":"2296_CR16","doi-asserted-by":"publisher","first-page":"3362","DOI":"10.1109\/JBHI.2022.3148820","volume":"26","author":"S Rao","year":"2022","unstructured":"Rao, S. et al. An explainable transformer-based deep learning model for the prediction of incident heart failure. IEEE J. Biomed. Health Inf. 26, 3362\u20133372 (2022).","journal-title":"IEEE J. Biomed. Health Inf."},{"key":"2296_CR17","doi-asserted-by":"crossref","unstructured":"Rupp, M., Peter, O. & Pattipaka, T. ExBEHRT: extended transformer for electronic health records. in Trustworthy Machine Learning for Healthcare, Vol. 13932 73\u201384 (Springer, 2023).","DOI":"10.1007\/978-3-031-39539-0_7"},{"key":"2296_CR18","doi-asserted-by":"publisher","first-page":"1740","DOI":"10.1093\/ije\/dyz034","volume":"48","author":"A Wolf","year":"2019","unstructured":"Wolf, A. et al. Data resource profile: clinical practice research datalink (CPRD) aurum. Int J. Epidemiol. 48, 1740\u20131740g (2019).","journal-title":"Int J. Epidemiol."},{"key":"2296_CR19","doi-asserted-by":"publisher","DOI":"10.1038\/s41597-022-01899-x","volume":"10","author":"AEW Johnson","year":"2023","unstructured":"Johnson, A. E. W. et al. MIMIC-IV, a freely accessible electronic health record dataset. Sci. Data 10, 1 (2023).","journal-title":"Sci. Data"},{"key":"2296_CR20","unstructured":"Sundararajan, M., Taly, A. & Yan, Q. Axiomatic attribution for deep networks. in 34th International Conference on Machine Learning, ICML 2017 3319\u20133328 (ICML, 2017)."},{"key":"2296_CR21","doi-asserted-by":"publisher","first-page":"e078523","DOI":"10.1136\/bmj-2023-078523","volume":"385","author":"N Conrad","year":"2024","unstructured":"Conrad, N. et al. Trends in cardiovascular disease incidence among 22 million people in the UK over 20 years: population based study. BMJ 385, e078523 (2024).","journal-title":"BMJ"},{"key":"2296_CR22","doi-asserted-by":"publisher","first-page":"2059","DOI":"10.1016\/j.jacc.2015.08.878","volume":"66","author":"J Simpson","year":"2015","unstructured":"Simpson, J. et al. Comparing LCZ696 with enalapril according to baseline risk using the MAGGIC and EMPHASIS-HF risk scores an analysis of mortality and morbidity in PARADIGM-HF. J. Am. Coll. Cardiol. 66, 2059\u20132071 (2015).","journal-title":"J. Am. Coll. Cardiol."},{"key":"2296_CR23","unstructured":"NICOR. National Institute for Cardiovascular Outcomes Research (NICOR Heart Failure Audit: 2024 Summary Report, 2024)."},{"key":"2296_CR24","doi-asserted-by":"crossref","unstructured":"S Buuren, K. G.-O. Mice: multivariate imputation by chained equations in R. J. Stat. Softw. 45, 1\u201367 (2011).","DOI":"10.18637\/jss.v045.i03"},{"key":"2296_CR25","doi-asserted-by":"publisher","first-page":"513","DOI":"10.1161\/CIRCULATIONAHA.124.065473","volume":"150","author":"JJ Moslehi","year":"2024","unstructured":"Moslehi, J. J. Cardio-oncology: a new clinical frontier and novel platform for cardiovascular investigation. Circulation 150, 513\u2013515 (2024).","journal-title":"Circulation"},{"key":"2296_CR26","doi-asserted-by":"publisher","unstructured":"Xanthopoulos, A., Starling, R. C., Kitai, T. & Triposkiadis, F. Heart failure and liver disease: cardiohepatic interactions. JACC Heart Failure. https:\/\/doi.org\/10.1016\/j.jchf.2018.10.007 (2019).","DOI":"10.1016\/j.jchf.2018.10.007"},{"key":"2296_CR27","doi-asserted-by":"publisher","first-page":"1188","DOI":"10.1136\/heartjnl-2024-324301","volume":"110","author":"J Wong","year":"2024","unstructured":"Wong, J., Soh, C. H., Wang, B. & Marwick, T. Long-term risk of heart failure in adult cancer survivors: a systematic review and meta-analysis. Heart 110, 1188\u20131195 (2024).","journal-title":"Heart"},{"key":"2296_CR28","doi-asserted-by":"crossref","unstructured":"Hollingworth, W. et al. The healthcare costs of heart failure during the last five years of life: a retrospective cohort study. Int. J. Cardiol. 224, 132\u2013138 (2016).","DOI":"10.1016\/j.ijcard.2016.09.021"},{"key":"2296_CR29","unstructured":"NHS England. The Single Patient Record. https:\/\/www.england.nhs.uk\/digitaltechnology\/the-single-patient-record\/ (2020)."},{"key":"2296_CR30","doi-asserted-by":"crossref","unstructured":"Akter, S., Michael, K., Uddin, M. R., McCarthy, G. & Rahman, M. Transforming business using digital innovations: the application of AI, blockchain, cloud and data analytics. Ann. Oper. Res. 308, 7\u201339 (2022).","DOI":"10.1007\/s10479-020-03620-w"},{"key":"2296_CR31","doi-asserted-by":"publisher","first-page":"m3919","DOI":"10.1136\/bmj.m3919","volume":"371","author":"Y Li","year":"2020","unstructured":"Li, Y., Sperrin, M., Ashcroft, D. M. & Van Staa, T. P. Consistency of variety of machine learning and statistical models in predicting clinical risks of individual patients: Longitudinal cohort study using cardiovascular disease as exemplar. BMJ 371, m3919 (2020).","journal-title":"BMJ"},{"key":"2296_CR32","doi-asserted-by":"crossref","unstructured":"Van Staa, T. P., Gulliford, M., Ng, E. S. W., Goldacre, B. & Smeeth, L. Prediction of cardiovascular risk using framingham, ASSIGN and QRISK2: How well do they predict individual rather than population risk? PLoS One 9, e106455 (2014).","DOI":"10.1371\/journal.pone.0106455"},{"key":"2296_CR33","unstructured":"Goldstein, M., Han, X., Puli, A., Perotte, A. J. & Ranganath, R. X-CAL: explicit calibration for survival analysis. Adv. Neural Inf. Process. Syst. 33, 18296\u201318307 (2020)."},{"key":"2296_CR34","unstructured":"Tang, W., Ma, J., Mei, Q. & Zhu, J. SODEN: a scalable continuous-time survival model through ordinary differential equation networks. J. Mach. Learn. Res. 23, 34 (2022)."},{"key":"2296_CR35","doi-asserted-by":"crossref","unstructured":"Nakao, Y. M. et al. Prognosis, characteristics, and provision of care for patients with the unspecified heart failure electronic health record phenotype: a population-based linked cohort study of 95262 individuals. EClinicalMedicine 63, 102164 (2023).","DOI":"10.1016\/j.eclinm.2023.102164"},{"key":"2296_CR36","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":"2296_CR37","doi-asserted-by":"publisher","first-page":"565","DOI":"10.1177\/0272989X06295361","volume":"26","author":"AJ Vickers","year":"2006","unstructured":"Vickers, A. J. & Elkin, E. B. Decision curve analysis: a novel method for evaluating prediction models. Med. Decis. Mak. 26, 565\u2013574 (2006).","journal-title":"Med. Decis. Mak."},{"key":"2296_CR38","doi-asserted-by":"publisher","first-page":"583","DOI":"10.1093\/jamia\/ocad247","volume":"31","author":"C Reich","year":"2024","unstructured":"Reich, C. et al. OHDSI standardized vocabularies\u2014a large-scale centralized reference ontology for international data harmonization. J. Am. Med. Inform. Assoc. 31, 583\u2013590 (2024).","journal-title":"J. Am. Med. Inform. Assoc."},{"key":"2296_CR39","doi-asserted-by":"crossref","unstructured":"Wang, X. et al. Systematic approach to outcome assessment from coded electronic healthcare records in the DaRe2THINK NHS-embedded randomized trial. Eur. Heart J. Digit. Health 3, 426\u2013436 (2022).","DOI":"10.1101\/2022.05.24.22275434"},{"key":"2296_CR40","doi-asserted-by":"publisher","first-page":"e078378","DOI":"10.1136\/bmj-2023-078378","volume":"385","author":"GS Collins","year":"2024","unstructured":"Collins, G. S. et al. TRIPOD+AI statement: updated guidance for reporting clinical prediction models that use regression or machine learning methods. BMJ 385, e078378 (2024).","journal-title":"BMJ"}],"container-title":["npj Digital Medicine"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s41746-025-02296-5","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41746-025-02296-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41746-025-02296-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,3]],"date-time":"2026-02-03T10:46:07Z","timestamp":1770115567000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s41746-025-02296-5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1,8]]},"references-count":40,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2026,12]]}},"alternative-id":["2296"],"URL":"https:\/\/doi.org\/10.1038\/s41746-025-02296-5","relation":{},"ISSN":["2398-6352"],"issn-type":[{"value":"2398-6352","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,1,8]]},"assertion":[{"value":"1 October 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"16 December 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"8 January 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"K.R. is Editor-in-Chief of BMJ Heart. K.R. reports consulting fees from Medtronic CRDN and Lucem Health; honoraria or fees from BMJ Heart, PLoS Medicine, AstraZeneca Middle East and Africa Region, Medscape, Radcliffe Cardiology, and WebMD Medscape UK; and grants from the National Institute for Health and Care Research (NIHR), the Medical Research Council, the British Heart Foundation, the Novo Nordisk Foundation, Horizon Europe, and Roche. S.R. is a methodological advisor for BMJ Heart. S.R. reports consultancy fees from Lucem Health and grants from Oxford University Hospital Trust. N.C. reports grants from Wellcome Trust. F.W.A. is an editor for European Heart Journal. All other authors declare no competing interests.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"118"}}