Deep Neural Network-Estimated Electrocardiographic Age as a Mortality Predictor
Open accessPublished version of a preprint
Abstract
The electrocardiogram (ECG) is the most commonly used exam for the evaluation of cardiovascular diseases. Here we propose that the age predicted by artificial intelligence (AI) from the raw ECG (ECG-age) can be a measure of cardiovascular health. A deep neural network is trained to predict a patient’s age from the 12-lead ECG in the CODE study cohort ( n = 1,558,415 patients). On a 15% hold-out split, patients with ECG-age more than 8 years greater than the chronological age have a higher mortality rate (hazard ratio (HR) 1.79, p < 0.001), whereas those with ECG-age more than 8 years smaller, have a lower mortality rate (HR 0.78, p < 0.001). Similar results are obtained in the external cohorts ELSA-Brasil ( n = 14,236) and SaMi-Trop ( n = 1,631). Moreover, even for apparent normal ECGs, the predicted ECG-age gap from the chronological age remains a statistically significant risk predictor. These results show that the AI-enabled analysis of the ECG can add prognostic information.
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
ECG waveforms contain latent signatures of biological age.
“Emerging evidence suggests that ECG waveforms contain latent signatures of ventricular dysfunction [4], structural heart disease [5], metabolic abnormalities [6], and broader physiologic characteristics such as biological age [7] and future mortality risk [8].”
From Deep Learning Applied to 12-Lead ECGs for Detection of Structural, Metabolic and Systemic Disease (2026) · cites this paper as [7]
Lima et al. trained a deep neural network to estimate age from 12-lead ECGs in the CODE study cohort, which included more than 1.5 million patients.
“Lima et al. trained a deep neural network to estimate age from 12-lead ECGs in the CODE study cohort, which included more than 1.5 million patients.”
From Deep Learning Applied to 12-Lead ECGs for Detection of Structural, Metabolic and Systemic Disease (2026) · cites this paper as [7]
The association between AI-estimated ECG age and mortality persisted among individuals with apparently normal ECGs.
“This association persisted even among individuals with apparently normal ECGs”
From Deep Learning Applied to 12-Lead ECGs for Detection of Structural, Metabolic and Systemic Disease (2026) · cites this paper as [7]
ECG-age, mortality-prediction, and disease-specific models illustrate how AI-derived outputs may function as quantitative markers of physiologic risk rather than simple diagnostic labels.
“As discussed above, ECG-age [7], mortality-prediction [8], and disease-specific models illustrate how AI-derived outputs may function as quantitative markers of physiologic risk rather than simple diagnostic labels.”
From Deep Learning Applied to 12-Lead ECGs for Detection of Structural, Metabolic and Systemic Disease (2026) · cites this paper as [7]
AI-derived ECG age may capture latent cardiovascular health or physiologic reserve not apparent through standard interpretation.
“suggesting that AI-derived ECG age may capture latent cardiovascular health or physiologic reserve not apparent through standard interpretation [7].”
From Deep Learning Applied to 12-Lead ECGs for Detection of Structural, Metabolic and Systemic Disease (2026) · cites this paper as [7]
Patients whose AI-estimated ECG age was more than eight years older than their chronological age had significantly higher mortality, while those whose ECG age was more than eight years younger had lower mortality.
“Patients whose AI-estimated ECG age was more than eight years older than their chronological age had significantly higher mortality, while those whose ECG age was more than eight years younger had lower mortality.”
From Deep Learning Applied to 12-Lead ECGs for Detection of Structural, Metabolic and Systemic Disease (2026) · cites this paper as [7]
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Cites
Deep Residual Learning for Image Recognition
He, K., Zhang, X., Ren, S., & Sun, J. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.90 · Cited by 235,474 · see citing works
Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification
He, K., Zhang, X., Ren, S., & Sun, J. (2015) · 2015 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2015.123 · Cited by 19,741 · see citing works
Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps
Simonyan, K., Vedaldi, A., & Zisserman, A. (2013) · arXiv · doi:10.48550/arxiv.1312.6034 · Cited by 5,370 · see citing works
Prediction of mortality from 12-lead electrocardiogram voltage data using a deep neural network
Raghunath, S., Ulloa Cerna, A. E., Jing, L., vanMaanen, D. P., Stough, J., Hartzel, D. N., Leader, J. B., Kirchner, H. L., Stumpe, M. C., Hafez, A., et al. (2020) · Nature Medicine · doi:10.1038/s41591-020-0870-z · Cited by 314 · see citing works
Flagged first, then by citations
Research works printed but not linked: 36
- [1]Topol EJ High-performance medicine: the convergence of human and artificial intelligence Nat. Med. 2019 25 44 56 10.1038/s41591-018-0300-7 30617339 · DOI · Paper page
- [2]Shah AP Rubin SA Errors in the computerized electrocardiogram interpretation of cardiac rhythm J. Electrocardiol. 2007 40 385 390 10.1016/j.jelectrocard.2007.03.008 17531257 · DOI
- [3]Ribeiro AH Automatic diagnosis of the 12-lead ECG using a deep neural network Nat. Commun. 2020 11 1760 10.1038/s41467-020-15432-4 32273514 PMC7145824 · DOI · Paper page
- [4]Hannun AY Cardiologist-level arrhythmia detection and classification in ambulatory electrocardiograms using a deep neural network Nat. Med. 2019 25 65 69 10.1038/s41591-018-0268-3 30617320 PMC6784839 · DOI · Paper page
- [6]Meira W Ribeiro ALP Oliveira DM Ribeiro AH Contextualized interpretable machine learning for medical diagnosis Commun. ACM 2020 63 56 58 10.1145/3416965 · DOI
- [7]Han X Deep learning models for electrocardiograms are susceptible to adversarial attack Nat. Med. 2020 26 360 363 10.1038/s41591-020-0791-x 32152582 PMC8096552 · DOI
- [9]Attia, Z. I. et al. An artificial intelligence-enabled ECG algorithm for the identification of patients with atrial fibrillation during sinus rhythm: a retrospective analysis of outcome prediction. Lancet394, 861–867 (2019). 31378392
- [10]Attia ZI Screening for cardiac contractile dysfunction using an artificial intelligence–enabled electrocardiogram Nat. Med. 2019 25 70 74 10.1038/s41591-018-0240-2 30617318 · DOI · Paper page
- [11]Ball RL Feiveson AH Schlegel TT Starc V Dabney AR Predicting ‘heart age’ using electrocardiography J. Pers. Med. 2014 4 65 78 10.3390/jpm4010065 25562143 PMC4251409 · DOI
- [12]Attia ZI Age and sex estimation using artificial intelligence from standard 12-lead ECGs Circ. Arrhythm. Electrophysiol. 2019 12 e007284 10.1161/CIRCEP.119.007284 31450977 PMC7661045 · DOI
- [13]Toya, T., Ahmad, A., Attia, Z. & Cohen‐Shelly, M. Vascular aging detected by peripheral endothelial dysfunction is associated with ecg‐derived physiological aging. J. Am. Heart Assoc.10, e018656 (2021). PMC7955452 33455414
- [14]Hamczyk MR Nevado RM Barettino A Fuster V Andrés V Biological versus chronological aging: JACC focus seminar J. Am. Coll. Cardiol. 2020 75 919 930 10.1016/j.jacc.2019.11.062 32130928 · DOI
- [15]Vicent L Martínez-Sellés M Electrocardiogeriatrics: ECG in advanced age J. Electrocardiol. 2017 50 698 700 10.1016/j.jelectrocard.2017.06.003 28623017 · DOI
- [16]Palhares DMF Normal limits of the electrocardiogram derived from a large database of Brazilian primary care patients BMC Cardiovasc. Disord. 2017 17 152 10.1186/s12872-017-0572-8 28610624 PMC5470250 · DOI
- [17]Ribeiro ALP Tele-electrocardiography and bigdata: the CODE (Clinical Outcomes in Digital Electrocardiography) study J. Electrocardiol. 2019 10.1016/j.jelectrocard.2019.09.008 31526573 · DOI
- [18]Pinto-Filho MM Major electrocardiographic abnormalities according to the minnesota coding system among brazilian adults (from the ELSA-Brasil Cohort Study) Am. J. Cardiol. 2017 119 2081 2087 10.1016/j.amjcard.2017.03.043 28450038 · DOI
- [19]Di Lorenzo Oliveira C Risk score for predicting 2-year mortality in patients with chagas cardiomyopathy from endemic areas: SaMi-Trop Cohort Study J. Am. Heart Assoc. 2020 9 e014176 10.1161/JAHA.119.014176 32157953 PMC7335521 · DOI
- [22]Soliman EZ Usefulness of maintaining a normal electrocardiogram over time for predicting cardiovascular health Am. J. Cardiol. 2017 119 249 255 10.1016/j.amjcard.2016.09.051 28126148 PMC5283845 · DOI
- [23]The Lancet Respiratory Medicine. Opening the black box of machine learning Lancet Respir. Med. 2018 6 801 10.1016/S2213-2600(18)30425-9 30343029 · DOI
- [24]Rezaeian P Association of major and minor electrocardiographic abnormalities with cardiovascular morbidity and mortality in the multi-ethnic study of atherosclerosis cohort J. Am. Coll. Cardiol. 2016 67 831 10.1016/S0735-1097(16)30832-4 · DOI
- [25]Pinto-Filho MM Prognostic value of electrocardiographic abnormalities in adults from the Brazilian longitudinal study of adults’ health Heart 2020 10.1136/heartjnl-2020-318097 33361354 · DOI
- [26]US Preventive Services Task Force. Screening for cardiovascular disease risk with electrocardiography: US preventive services task force recommendation statement JAMA 2018 319 2308 2314 10.1001/jama.2018.6848 29896632 · DOI
- [27]Cooney MT Cardiovascular risk age: concepts and practicalities Heart 2012 98 941 946 10.1136/heartjnl-2011-301478 22626902 · DOI
- [28]Groenewegen KA Vascular age to determine cardiovascular disease risk: a systematic review of its concepts, definitions, and clinical applications Eur. J. Prev. Cardiol. 2016 23 264 274 10.1177/2047487314566999 25609227 · DOI
- [29]Ribeiro ALP Implementation of a telecardiology system in the state of Minas Gerais: the Minas Telecardio Project Arq. Bras. Cardiol. 2010 95 70 78 10.1590/S0066-782X2010005000060 20563526 · DOI
- [30]Alkmim MB Improving patient access to specialized health care: the Telehealth Network of Minas Gerais, Brazil Bull. World Health Organ. 2012 90 373 378 10.2471/BLT.11.099408 22589571 PMC3341691 · DOI
- [31]Paixão GMM Evaluation of mortality in bundle branch block patients from an electronic cohort: Clinical Outcomes in Digital Electrocardiography (CODE) study J. Electrocardiol. 2019 10.1016/j.jelectrocard.2019.09.004 31653433 · DOI
- [32]Aquino EML Brazilian Longitudinal Study of Adult Health (ELSA-Brasil): objectives and design Am. J. Epidemiol. 2012 175 315 324 10.1093/aje/kwr294 22234482 · DOI
- [33]Schmidt MI Cohort profile: longitudinal study of adult health (ELSA-Brasil) Int. J. Epidemiol. 2015 44 68 75 10.1093/ije/dyu027 24585730 PMC4339754 · DOI
- [34]Cardoso CS Longitudinal study of patients with chronic Chagas cardiomyopathy in Brazil (SaMi-Trop project): a cohort profile BMJ Open 2016 6 e011181 10.1136/bmjopen-2016-011181 PMC4861110 27147390 · DOI
- [35]Brito BO Association between typical electrocardiographic abnormalities and NT-proBNP elevation in a large cohort of patients with Chagas disease from endemic area J. Electrocardiol. 2018 51 1039 1043 10.1016/j.jelectrocard.2018.08.031 30497727 PMC7001888 · DOI
- [36]He, K., Zhang, X., Ren, S. & Sun, J. Identity mappings in deep residual networks. in Computer Vision – ECCV 2016 630–645 (Springer International Publishing, 2016).
- [37]Ioffe, S. & Szegedy, C. Batch normalization: accelerating deep network training by reducing internal covariate shift. ICML'15: Proceedings of the 32nd International Conference on International Conference on Machine Learning (Association for Computing Machinery, 2015).
- [39]Scherer, D., Müller, A. & Behnke, S. Evaluation of pooling operations in convolutional architectures for object recognition. in Artificial Neural Networks – ICANN 2010 92–101 (Springer Berlin Heidelberg, 2010).
- [40]Kingma, D. P. & Ba, J. Adam: A method for stochastic optimization. Conference Paper at the 3rd International Conference for Learning Representations. https://iclr.cc/archive/2014/conference-proceedings/ (2014).
- [42]Strodthoff, N., Wagner, P., Schaeffter, T. & Samek, W. Deep Learning for ECG Analysis: Benchmarks and Insights from PTB-XL. IEEE J. Biomed. Health Inf.10.1109/jbhi.2020.3022989 (2020). 32903191 · DOI
Cited by
Sorted by citations
Chung, C. T., Lee, S., King, E., Liu, T., Armoundas, A. A., Bazoukis, G., & Tse, G. (2022) · International Journal of Arrhythmia · doi:10.1186/s42444-022-00075-x · Cited by 79 · see citing works
Pediatric ECG-Based Deep Learning to Predict Left Ventricular Dysfunction and Remodeling
Mayourian, J., La Cava, W. G., Vaid, A., Nadkarni, G. N., Ghelani, S. J., Mannix, R., Geva, T., Dionne, A., Alexander, M. E., Duong, S. Q., et al. (2024) · Circulation · doi:10.1161/circulationaha.123.067750 · Cited by 59 · see citing works
Explaining Deep Learning for ECG Analysis: Building Blocks for Auditing and Knowledge Discovery
Wagner, P., Mehari, T., Haverkamp, W., & Strodthoff, N. (2024) · Computers in Biology and Medicine · doi:10.1016/j.compbiomed.2024.108525 · Cited by 48 · see citing works
Hempel, P., Ribeiro, A. H., Vollmer, M., Bender, T., Dörr, M., Krefting, D., & Spicher, N. (2025) · npj Digital Medicine · doi:10.1038/s41746-024-01428-7 · Cited by 31 · see citing works
Self-citationDeep Learning Applied to 12-Lead ECGs for Detection of Structural, Metabolic and Systemic Disease
Shaulian, S., Zeltser, R., & Makaryus, A. N. (2026) · Diagnostics · doi:10.3390/diagnostics16172834
- Authors
- Lima, E. M., Ribeiro, A. H., Paixão, G. M. M., Ribeiro, M. H., Pinto-Filho, M. M., Gomes, P. R., Oliveira, D. M., Sabino, E. C., Duncan, B. B., Giatti, L., Barreto, S. M., Meira Jr, W., Schön, T. B., & Ribeiro, A. L. P.
- Affiliations
- Universidade Federal de Minas Gerais (BR)
- École Polytechnique Fédérale de Lausanne (CH)
- Universidade Federal do Rio Grande do Sul (BR)
- Uppsala University (SE)
- Corresponding author
- Ribeiro, Antônio H.
- Schön, Thomas B.
- ORCID
- Venue
- Nature Communications
- Published
- 2021-08-25
- Volume
- 12
- Issue
- 1
- Pages
- 5117-5117
- ISSN
- 2041-1723 (ISSN-L)
- PMC
- PMC8387361
- OpenAlex
- W3195084370
- Cited by
- 249
- References
- 4
- Citations by year
- 2026: 58 · 2025: 64 · 2024: 58 · 2023: 44 · 2022: 24 · 2021: 1
- FWCI
- 21.29
- Type
- journal article
- Language
- en
- Open access
- gold
- doi.org
- Locations
- Nature Communications (publishedVersion, cc-by)
- medRxiv (acceptedVersion, cc-by)
- Europe PMC (PubMed Central) (publishedVersion, other-oa)
- PubMed Central (publishedVersion, cc-by)
- PubMed (publishedVersion)
- LA Referencia (Red Federada de Repositorios Institucionales de Publicaciones Científicas) (publishedVersion, other-oa)
- Uppsala University Publications (Uppsala University) (submittedVersion, other-oa)
- RePEc: Research Papers in Economics (submittedVersion)
- DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
- Infoscience (Ecole Polytechnique Fédérale de Lausanne) (submittedVersion, cc-by-nc-nd)
- LA Referencia (Red Federada de Repositorios Institucionales de Publicaciones Científicas) (submittedVersion, cc-by-nc-sa)
- Funders
- Nvidia
- Coordenação de Aperfeiçoamento de Pessoal de Nível Superior
- Conselho Nacional de Desenvolvimento Científico e Tecnológico (01060212.00BA, 01 060115.00 SP, 01060300.00ES, 01 06 0010.00 RS, 01 06 0071.00 RJ, U19AI098461-06, 01 06 0278.00 MG)
- Knut och Alice Wallenbergs Stiftelse
- Fundação de Amparo à Pesquisa do Estado de Minas Gerais (01060212.00BA, 01060115.00SP, U19AI098461-06, 01060300.00ES,, 01060278.00MG)
- Uppsala Universitet
- National Institutes of Health (AI098461, P50 AI098461-02 and U19AI098461-06)
- National Institute of Allergy and Infectious Diseases (P50AI098461, U19AI098461, U01AI168383)
- Topics
- Health Sciences › Medicine › Cardiology and Cardiovascular Medicine › ECG Monitoring and Analysis
- Physical Sciences › Computer Science › Artificial Intelligence › Machine Learning in Healthcare
- Health Sciences › Medicine › Cardiology and Cardiovascular Medicine › Cardiac electrophysiology and arrhythmias
- Keywords
- deep neural network, mortality prediction, cardiovascular risk, 12-lead ECG, prognostic factors, ELSA-Brasil
- MeSH terms
- Adolescent, Adult, Age Factors, Aged, Cardiovascular Diseases, Child, Electrocardiography, Female, Humans, Male, Middle Aged, Cohort Studies, Neural Networks, Computer, Young Adult
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
