Abstract
Convolutional neural networks (CNNs) can estimate electrocardiogram (ECG)-based heart age. We compared three published CNNs in the Tromsø Study cohort (7,108 participants) for accuracy, agreement, and prognostic value. Mean absolute error versus chronological age was 6.8, 7.8, and 6.4 years. Correlations with age were ~0.71–0.73 and agreement across CNNs was high (overall ICC 0.86). Using Cox models, we estimated hazard ratios per SD of δ-age (ECG age minus chronological age) for myocardial infarction, stroke, cardiovascular mortality, and all-cause mortality; discrimination was quantified by cross-validated C-index. δ-age predicted higher risk across outcomes; associations were strongest for δ-age1 with myocardial infarction and all-cause mortality (HR 1.36 (1.11, 1.67) and 1.27 (1.08, 1.50)) and for δ-age2 with stroke and cardiovascular mortality (HR 1.45 (1.17, 1.80) and 1.48 (1.07, 2.05)). C-indices were similar across models. Despite architectural and training-set differences, CNNs yielded consistent ECG ages and comparable risk prediction in an external population.
Similar content being viewed by others
Data availability
Data may be obtained from a third party and are not publicly available. The data supporting the findings in this study are available through an application directed to The Tromsø Study by following the steps presented on their webpage. https://uit.no/research/tromsostudy.
Code availability
The underlying code for this study is available in the GitHub repository (https://github.com/Arya200196/PhD_ECG-age-comparison).
References
Li, X. et al. Accelerated aging mediates the associations of unhealthy lifestyles with cardiovascular disease, cancer, and mortality. J. Am. Geriatrics Soc. 72, 181–193 (2024).
Wu, J. W. et al. Biological age in healthy elderly predicts aging-related diseases including dementia. Sci. Rep. 11, 15929 (2021).
Attia, Z. I. et al. Age and sex estimation using artificial intelligence from standard 12-lead ECGs. Circ. Arrhythm. Electrophysiol. 12, e007284 (2019).
Horvath, S. & Raj, K. DNA methylation-based biomarkers and the epigenetic clock theory of ageing. Nat. Rev. Genet. 19, 371–384 (2018).
Rivero-Segura, N. A., Bello-Chavolla, O. Y., Barrera-Vazquez, O. S., Gutierrez-Robledo, L. M. & Gomez-Verjan, J. C. Promising biomarkers of human aging: in search of a multi-omics panel to understand the aging process from a multidimensional perspective. Ageing Res. Rev. 64, 101164 (2020).
Simm, A. et al. Potential biomarkers of ageing. Biol. Chem. 389, 257–265 (2008).
Smith, S. M., Vidaurre, D., Alfaro-Almagro, F., Nichols, T. E. & Miller, K. L. Estimation of brain age delta from brain imaging. Neuroimage 200, 528–539 (2019).
Guo, J. et al. Aging and aging-related diseases: from molecular mechanisms to interventions and treatments. Signal Transduct. Target Ther. 7, 391 (2022).
Bae, C.-Y. et al. Comparison of biological age prediction models using clinical biomarkers commonly measured in clinical practice settings: AI techniques vs. traditional statistical methods. Front. Anal. Sci. 1, https://doi.org/10.3389/frans.2021.709589 (2021).
Simonson, E. The effect of age on the electrocardiogram. Am. J. Cardiol. 29, 64–73 (1972).
Wong, N. D. et al. Atherosclerotic cardiovascular disease risk assessment: an American Society for Preventive Cardiology clinical practice statement. Am. J. Prev. Cardiol. 10, 100335 (2022).
Ladejobi, A. O. et al. The 12-lead electrocardiogram as a biomarker of biological age. Eur. Heart J. Digital Health 2, 379–389 (2021).
Khurshid, S. et al. ECG-based deep learning and clinical risk factors to predict atrial fibrillation. Circulation 145, 122–133 (2022).
Lima, E. M. et al. Deep neural network-estimated electrocardiographic age as a mortality predictor. Nat. Commun. 12, 5117 (2021).
Chang, C. H., Lin, C. S., Luo, Y. S., Lee, Y. T. & Lin, C. Electrocardiogram-based heart age estimation by a deep learning model provides more information on the incidence of cardiovascular disorders. Front. Cardiovasc. Med. 9, 754909 (2022).
Barros, A., German Mesner, I., Nguyen, N. R. & Moorman, J. R. Age prediction from 12-lead electrocardiograms using deep learning: a comparison of four models on a contemporary, freely available dataset. Physiol. Meas. 45, https://doi.org/10.1088/1361-6579/ad6746 (2024).
Alowais, S. A. et al. Revolutionizing healthcare: the role of artificial intelligence in clinical practice. BMC Med. Educ. 23, 689 (2023).
Saenz, A., Chen, E., Marklund, H. & Rajpurkar, P. The MAIDA initiative: establishing a framework for global medical-imaging data sharing. Lancet Digit Health 6, e6–e8 (2024).
Jacobsen, B. K., Eggen, A. E., Mathiesen, E. B., Wilsgaard, T. & Njolstad, I. Cohort profile: the Tromso Study. Int. J. Epidemiol. 41, 961–967 (2012).
Hopstock, L. A. et al. The seventh survey of the Tromso Study (Tromso7) 2015-2016: study design, data collection, attendance, and prevalence of risk factors and disease in a multipurpose population-based health survey. Scand. J. Public Health 50, 919–929 (2022).
Shin, H. C. et al. Deep convolutional neural networks for computer-aided detection: CNN architectures, dataset characteristics and transfer learning. IEEE Trans. Med. Imaging 35, 1285–1298 (2016).
Van Den Oord, A. et al. Wavenet: a generative model for raw audio. Preprint at https://arxiv.org/abs/1609.03499 (2016).
Franceschi, J.-Y., Dieuleveut, A. & Jaggi, M. Unsupervised scalable representation learning for multivariate time series. In Advances in Neural Information Processing Systems 32 (NIPS, 2019).
Bos, M. N. et al. Automated Comprehensive Interpretation of 12-lead Electrocardiograms Using Pre-trained Exponentially Dilated Causal Convolutional Neural Networks. 2020 Computing in Cardiology, 1-4 (2020).
Mannsverk, J. et al. Trends in modifiable risk factors are associated with declining incidence of hospitalized and nonhospitalized acute coronary heart disease in a population. Circulation 133, 74–81 (2016).
Carlsson, M. et al. Temporal trends in incidence and case fatality of intracerebral hemorrhage: the Tromso study 1995-2012. Cerebrovasc. Dis. Extra 6, 40–49 (2016).
Varmdal, T. et al. Data from national health registers as endpoints for the Tromsø study: correctness and completeness of stroke diagnoses. Scand. J. Public Health 51, 1042–1049 (2023).
Varmdal, T. et al. Validating acute myocardial infarction diagnoses in national health registers for use as endpoint in research: the Tromso study. Clin. Epidemiol 13, 675–682 (2021).
McGraw, K. O. & Wong, S. P. Forming inferences about some intraclass correlation coefficients. Psychol. Methods 1, 30–46 (1996).
Lin, L. I. A concordance correlation coefficient to evaluate reproducibility. Biometrics 45, 255–268 (1989).
Refaeilzadeh, P., Tang, L. & Liu, H. In Encyclopedia of Database Systems (eds Liu, L. & Tamer ÖZsu, M.) 532–538 (Springer US, 2009).
Shah, M. et al. Environmental and genetic predictors of human cardiovascular ageing. Nat. Commun. 14, 4941 (2023).
Le Goallec, A. et al. Dissecting heart age using cardiac magnetic resonance videos, electrocardiograms, biobanks, and deep learning. Circulation 144, 12758 (2021).
Acknowledgements
This work was supported by Northern Norway Regional Health Authority, grant number HNF1636-22. The funder played no role in study design, data collection, analysis and interpretation of data, or the writing of this manuscript.
Funding
Open access funding provided by UiT The Arctic University of Norway (incl University Hospital of North Norway).
Author information
Authors and Affiliations
Contributions
O.I., D.A.L., and A.P.V. conceived and designed the study. T.W., H.S., and H.L. collected data for the study, Z.I.A. processed the data, A.P.V. and T.W. performed statistical analysis, E.D.B., R.v.E., R.R.v.d.L., F.L.J., D.A.L., H.S., O.I. interpreted the results. A.P.V. drafted the manuscript. O.I., F.J.L., T.W., H.S., H.L., Z.I.A, E.D.B., R.v.E., R.R.v.d.L., and D.A.L. critically revised and approved the manuscript. All authors read and approved the final manuscript.
Corresponding author
Ethics declarations
Competing interests
The authors declare no competing interests.
Additional information
Publisher’s note Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Open Access This article is licensed under a Creative Commons Attribution 4.0 International License, which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if changes were made. The images or other third party material in this article are included in the article’s Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article’s Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit http://creativecommons.org/licenses/by/4.0/.
About this article
Cite this article
Panthalanickal Vijayakumar, A., Wilsgaard, T., Schirmer, H. et al. Electrocardiogram derived heart age models agreement, accuracy and predictive ability in the Tromsø study. npj Aging (2026). https://doi.org/10.1038/s41514-026-00344-2
Received:
Accepted:
Published:
DOI: https://doi.org/10.1038/s41514-026-00344-2
