{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,15]],"date-time":"2026-04-15T01:18:30Z","timestamp":1776215910920,"version":"3.50.1"},"reference-count":29,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2023,2,6]],"date-time":"2023-02-06T00:00:00Z","timestamp":1675641600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2023,2,6]],"date-time":"2023-02-06T00:00:00Z","timestamp":1675641600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["npj Digit. Med."],"abstract":"<jats:title>Abstract<\/jats:title><jats:p>The feasibility and value of linking electrocardiogram (ECG) data to longitudinal population-level administrative health data to facilitate the development of a learning healthcare system has not been fully explored. We developed ECG-based machine learning models to predict risk of mortality among patients presenting to an emergency department or hospital for any reason. Using the 12-lead ECG traces and measurements from 1,605,268 ECGs from 748,773 healthcare episodes of 244,077 patients (2007\u20132020) in Alberta, Canada, we developed and validated ResNet-based Deep Learning (DL) and gradient boosting-based XGBoost (XGB) models to predict 30-day, 1-year, and 5-year mortality. The models for 30-day, 1-year, and 5-year mortality were trained on 146,173, 141,072, and 111,020 patients and evaluated on 97,144, 89,379, and 55,650 patients, respectively. In the evaluation cohort, 7.6%, 17.3%, and 32.9% patients died by 30-days, 1-year, and 5-years, respectively. ResNet models based on ECG traces alone had good-to-excellent performance with area under receiver operating characteristic curve (AUROC) of 0.843 (95% CI: 0.838\u20130.848), 0.812 (0.808\u20130.816), and 0.798 (0.792\u20130.803) for 30-day, 1-year and 5-year prediction, respectively; and were superior to XGB models based on ECG measurements with AUROC of 0.782 (0.776\u20130.789), 0.784 (0.780\u20130.788), and 0.746 (0.740\u20130.751). This study demonstrates the validity of ECG-based DL mortality prediction models at the population-level that can be leveraged for prognostication at point of care.<\/jats:p>","DOI":"10.1038\/s41746-023-00765-3","type":"journal-article","created":{"date-parts":[[2023,2,6]],"date-time":"2023-02-06T11:02:50Z","timestamp":1675681370000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":28,"title":["Towards artificial intelligence-based learning health system for population-level mortality prediction using electrocardiograms"],"prefix":"10.1038","volume":"6","author":[{"given":"Weijie","family":"Sun","sequence":"first","affiliation":[]},{"given":"Sunil Vasu","family":"Kalmady","sequence":"additional","affiliation":[]},{"given":"Nariman","family":"Sepehrvand","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5916-1050","authenticated-orcid":false,"given":"Amir","family":"Salimi","sequence":"additional","affiliation":[]},{"given":"Yousef","family":"Nademi","sequence":"additional","affiliation":[]},{"given":"Kevin","family":"Bainey","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2724-4086","authenticated-orcid":false,"given":"Justin A.","family":"Ezekowitz","sequence":"additional","affiliation":[]},{"given":"Russell","family":"Greiner","sequence":"additional","affiliation":[]},{"given":"Abram","family":"Hindle","sequence":"additional","affiliation":[]},{"given":"Finlay A.","family":"McAlister","sequence":"additional","affiliation":[]},{"given":"Roopinder K.","family":"Sandhu","sequence":"additional","affiliation":[]},{"given":"Padma","family":"Kaul","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2023,2,6]]},"reference":[{"key":"765_CR1","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1056\/NEJMp2103872","volume":"385","author":"JM McGinnis","year":"2021","unstructured":"McGinnis, J. M., Fineberg, H. V. & Dzau, V. J. Advancing the learning health system. N. Engl. J. Med. 385, 1\u20135 (2021).","journal-title":"N. Engl. J. Med."},{"key":"765_CR2","doi-asserted-by":"publisher","first-page":"2231","DOI":"10.1161\/CIRCULATIONAHA.120.048015","volume":"142","author":"JA Ezekowitz","year":"2020","unstructured":"Ezekowitz, J. A. et al. Is there a sex gap in surviving an acute coronary syndrome or subsequent development of heart failure? Circulation 142, 2231\u20132239 (2020).","journal-title":"Circulation"},{"key":"765_CR3","doi-asserted-by":"publisher","first-page":"3377","DOI":"10.1111\/jgs.17425","volume":"69","author":"DS Lee","year":"2021","unstructured":"Lee, D. S. et al. Predictors of mortality among long-term care residents with SARS-CoV-2 infection. J. Am. Geriatr. Soc. 69, 3377\u20133388 (2021).","journal-title":"J. Am. Geriatr. Soc."},{"key":"765_CR4","doi-asserted-by":"publisher","first-page":"1390","DOI":"10.1111\/jep.13579","volume":"27","author":"JA Staples","year":"2021","unstructured":"Staples, J. A. et al. External validation of the modified LACE+, LACE+, and LACE scores to predict readmission or death after hospital discharge. J. Eval. Clin. Pract. 27, 1390\u20131397 (2021).","journal-title":"J. Eval. Clin. Pract."},{"key":"765_CR5","doi-asserted-by":"publisher","first-page":"e006646","DOI":"10.1161\/CIRCOUTCOMES.120.006646","volume":"14","author":"B Sarak","year":"2021","unstructured":"Sarak, B. et al. Lipid testing, lipid-modifying therapy, and PCSK9 (Proprotein Convertase Subtilisin-Kexin Type 9) inhibitor eligibility in 27,979 patients with incident acute coronary syndrome. Circ. Cardiovasc. Qual. Outcomes 14, e006646 (2021).","journal-title":"Circ. Cardiovasc. Qual. Outcomes"},{"key":"765_CR6","doi-asserted-by":"publisher","first-page":"77","DOI":"10.1016\/j.cjca.2021.09.021","volume":"38","author":"M Orlandi","year":"2022","unstructured":"Orlandi, M. et al. The introduction of direct oral anticoagulants has not resolved treatment gaps for frail patients with nonvalvular atrial fibrillation. Can. J. Cardiol. 38, 77\u201384 (2022).","journal-title":"Can. J. Cardiol."},{"key":"765_CR7","doi-asserted-by":"publisher","first-page":"e022330","DOI":"10.1161\/JAHA.121.022330","volume":"10","author":"FA McAlister","year":"2021","unstructured":"McAlister, F. A. et al. Statins and SARS\u2010CoV\u20102 infection: results of a population\u2010based prospective cohort study of 469 749 adults from 2 Canadian provinces. J. Am. Heart Assoc. 10, e022330 (2021).","journal-title":"J. Am. Heart Assoc."},{"key":"765_CR8","doi-asserted-by":"publisher","first-page":"195","DOI":"10.1093\/ehjqcco\/qcab002","volume":"8","author":"RK Sandhu","year":"2022","unstructured":"Sandhu, R. K. et al. Concurrent use of P-glycoprotein or cytochrome 3A4 drugs and non-vitamin K antagonist oral anticoagulants in non-valvular atrial fibrillation. Eur. Heart J. Qual. Care. Clin. Outcomes 8, 195\u2013201 (2022).","journal-title":"Eur. Heart J. Qual. Care. Clin. Outcomes"},{"key":"765_CR9","doi-asserted-by":"publisher","first-page":"520","DOI":"10.1016\/j.jelectrocard.2014.04.006","volume":"47","author":"N Dianati Maleki","year":"2014","unstructured":"Dianati Maleki, N., Ehteshami Afshar, A. & Armstrong, P. W. Use of electrocardiogram indices of myocardial ischemia for risk stratification and decision making of reperfusion strategies. J. Electrocardiol. 47, 520\u2013524 (2014).","journal-title":"J. Electrocardiol."},{"key":"765_CR10","doi-asserted-by":"publisher","first-page":"4717","DOI":"10.1093\/eurheartj\/ehab649","volume":"42","author":"ZI Attia","year":"2021","unstructured":"Attia, Z. I., Harmon, D. M., Behr, E. R. & Friedman, P. A. Application of artificial intelligence to the electrocardiogram. Eur. Heart J. 42, 4717\u20134730 (2021).","journal-title":"Eur. Heart J."},{"key":"765_CR11","doi-asserted-by":"publisher","first-page":"S61","DOI":"10.1016\/j.jelectrocard.2019.08.008","volume":"57S","author":"A Minchol\u00e9","year":"2019","unstructured":"Minchol\u00e9, A., Camps, J., Lyon, A. & Rodr\u00edguez, B. Machine learning in the electrocardiogram. J. Electrocardiol. 57S, S61\u2013S64 (2019).","journal-title":"J. Electrocardiol."},{"key":"765_CR12","doi-asserted-by":"publisher","unstructured":"Sun, W., et al. ECG for high-throughput screening of multiple diseases: Proof-of-concept using multi-diagnosis deep learning from population-based datasets. Medical Imaging meets NeurIPS. https:\/\/doi.org\/10.48550\/arXiv.2210.06291 (2021).","DOI":"10.48550\/arXiv.2210.06291"},{"key":"765_CR13","doi-asserted-by":"publisher","first-page":"1019","DOI":"10.1016\/j.ahj.2008.09.005","volume":"156","author":"RM Califf","year":"2008","unstructured":"Califf, R. M. The benefits of moving quality to a national level. Am. Heart J. 156, 1019\u20131022 (2008).","journal-title":"Am. Heart J."},{"key":"765_CR14","doi-asserted-by":"publisher","first-page":"886","DOI":"10.1038\/s41591-020-0870-z","volume":"26","author":"S Raghunath","year":"2020","unstructured":"Raghunath, S. et al. Prediction of mortality from 12-lead electrocardiogram voltage data using a deep neural network. Nat. Med. 26, 886\u2013891 (2020).","journal-title":"Nat. Med."},{"key":"765_CR15","doi-asserted-by":"publisher","first-page":"444","DOI":"10.1001\/jamacardio.2019.0766","volume":"4","author":"MD Samsky","year":"2019","unstructured":"Samsky, M. D. et al. Trends in readmissions and length of stay for patients hospitalized with heart failure in Canada and the United States. Jama. Cardiol. 4, 444\u2013453 (2019).","journal-title":"Jama. Cardiol."},{"key":"765_CR16","doi-asserted-by":"publisher","first-page":"523","DOI":"10.1016\/j.jchf.2013.07.004","volume":"1","author":"P Kaul","year":"2013","unstructured":"Kaul, P. et al. Differences in treatment, outcomes, and quality of life among patients with heart failure in Canada and the United States. JACC Heart Fail 1, 523\u2013530 (2013).","journal-title":"JACC Heart Fail"},{"key":"765_CR17","doi-asserted-by":"publisher","first-page":"1754","DOI":"10.1161\/01.CIR.0000142671.06167.91","volume":"110","author":"P Kaul","year":"2004","unstructured":"Kaul, P. et al. Long-term mortality of patients with acute myocardial infarction in the United States and Canada: Comparison of patients enrolled in global utilization of Streptokinase and t-PA for Occluded Coronary Arteries (GUSTO)-I. Circulation 110, 1754\u20131760 (2004).","journal-title":"Circulation"},{"key":"765_CR18","unstructured":"Philips Professional Healthcare. IntelliSpace ECG, ECG management system. Available online at: https:\/\/www.usa.philips.com\/healthcare\/product\/HC860426\/intellispace-ecg-ecg-management-system (2022)."},{"key":"765_CR19","doi-asserted-by":"crossref","unstructured":"Chen, T. & Guestrin, C. XGBoost: A Scalable Tree Boosting System. In Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (pp. 785\u2013794). New York, NY, USA: ACM. (2016).","DOI":"10.1145\/2939672.2939785"},{"key":"765_CR20","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-020-15432-4","volume":"11","author":"AH Ribeiro","year":"2020","unstructured":"Ribeiro, A. H. et al. Automatic diagnosis of the 12-lead ECG using a deep neural network. Nat. Commun. 11, 1760 (2020).","journal-title":"Nat. Commun."},{"key":"765_CR21","doi-asserted-by":"crossref","unstructured":"Prechelt, L. Early Stopping - But When? in Neural Networks: Tricks of the Trade (eds. Orr, G. B. & M\u00fcller, K.-R.) 55\u201369 (1998).","DOI":"10.1007\/3-540-49430-8_3"},{"key":"765_CR22","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S. & Sun, J. Deep residual learning for image recognition. In Proceedings IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 770\u2013778 (2016).","DOI":"10.1109\/CVPR.2016.90"},{"key":"765_CR23","doi-asserted-by":"publisher","unstructured":"Kingma, D. P. & Ba, J. Adam: A method for stochastic optimization. Published as a conference paper at the 3rd International Conference for Learning Representations, San Diego. https:\/\/doi.org\/10.48550\/arXiv.1412.6980 (2015).","DOI":"10.48550\/arXiv.1412.6980"},{"key":"765_CR24","doi-asserted-by":"publisher","first-page":"32","DOI":"10.1002\/1097-0142(1950)3:1<32::AID-CNCR2820030106>3.0.CO;2-3","volume":"3","author":"WJ Youden","year":"1950","unstructured":"Youden, W. J. Index for rating diagnostic tests. Cancer 3, 32\u201335 (1950).","journal-title":"Cancer"},{"key":"765_CR25","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1175\/1520-0493(1950)078<0001:VOFEIT>2.0.CO;2","volume":"78","author":"GW Brier","year":"1950","unstructured":"Brier, G. W. Verification of forecasts expressed in terms of probability. Mon. Weather. Rev. 78, 1\u20133 (1950).","journal-title":"Mon. Weather. Rev."},{"key":"765_CR26","doi-asserted-by":"publisher","first-page":"1389","DOI":"10.1109\/LSP.2014.2337313","volume":"21","author":"X Sun","year":"2014","unstructured":"Sun, X. & Xu, W. Fast implementation of DeLong\u2019s Algorithm for comparing the areas under correlated receiver operating characteristic curves. IEEE Signal Process. Lett. 21, 1389\u20131393 (2014).","journal-title":"IEEE Signal Process. Lett."},{"key":"765_CR27","doi-asserted-by":"publisher","unstructured":"Selvaraju, R. R. et al. Grad-CAM: Visual Explanations from Deep Networks via Gradient-Based Localization. 2017 IEEE International Conference on Computer Vision (ICCV) https:\/\/doi.org\/10.1109\/iccv.2017.74 (2017).","DOI":"10.1109\/iccv.2017.74"},{"key":"765_CR28","doi-asserted-by":"publisher","first-page":"56","DOI":"10.1038\/s42256-019-0138-9","volume":"2","author":"SM Lundberg","year":"2020","unstructured":"Lundberg, S. M. et al. From local explanations to global understanding with explainable AI for trees. Nat. Mach. Intell. 2, 56\u201367 (2020).","journal-title":"Nat. Mach. Intell."},{"key":"765_CR29","doi-asserted-by":"publisher","first-page":"W1","DOI":"10.7326\/M14-0698","volume":"162","author":"KGM Moons","year":"2015","unstructured":"Moons, K. G. M. et al. Transparent reporting of a multivariable prediction model for Individual Prognosis or Diagnosis (TRIPOD): explanation and elaboration. Ann. Intern. Med. 162, W1\u2013W73 (2015).","journal-title":"Ann. Intern. Med."}],"container-title":["npj Digital Medicine"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s41746-023-00765-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41746-023-00765-3","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41746-023-00765-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,2,6]],"date-time":"2023-02-06T11:27:19Z","timestamp":1675682839000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s41746-023-00765-3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,2,6]]},"references-count":29,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2023,12]]}},"alternative-id":["765"],"URL":"https:\/\/doi.org\/10.1038\/s41746-023-00765-3","relation":{},"ISSN":["2398-6352"],"issn-type":[{"value":"2398-6352","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,2,6]]},"assertion":[{"value":"26 August 2022","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"21 January 2023","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"6 February 2023","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","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"21"}}