Abstract
Biological sex is closely linked to patterns embedded within the electrocardiogram (ECG) with essential health and disease implications. We report multicenter verification of an AI-enabled ECG model to predict biological sex across pediatric development. A previously published Mayo Clinic model confirmed puberty-linked AUROC gradient during external validation at Texas Children’s Hospital (pre-puberty AUROC 0.64, peri-puberty AUROC 0.84, post-puberty AUROC 0.94). This phenomenon was replicated at Boston Children’s Hospital. Saliency mapping revealed established sex-related electrophysiologic patterns.
Data availability
Patient-level data are not publicly available due to privacy restrictions. Aggregate metrics and analysis scripts may be shared upon reasonable request and institutional approvals/material transfer agreements as applicable.
Code availability
Code available on reasonable request to individual sites.
References
Saarel, E. V. et al. Electrocardiograms in healthy North American children in the digital age. Circ. Arrhythm. Electrophysiol. 11, e005808 (2018).
Giudicessi, J. R., Noseworthy, P. A. & Ackerman, M. J. The QT interval: an emerging vital sign for the precision medicine era? Circulation 139, 2711–2713 (2019).
Conrath, C. Gender differences in the long QT syndrome: effects of β-adrenoceptor blockade. Cardiovasc. Res. 53, 770–776 (2002).
Peguero, J. G. et al. Electrocardiographic criteria for the diagnosis of left ventricular hypertrophy. J. Am. Coll. Cardiol. 69, 1694–1703 (2017).
Attia, Z. I. et al. Age and sex estimation using artificial intelligence from standard 12-lead ECGs. Circ. Arrhythm. Electrophysiol. 12, e007284 (2019).
Naser, J. A. et al. Artificial intelligence-augmented electrocardiogram in determining sex. Mayo Clin. Proc. 98, 541–548 (2023).
O’Sullivan, D. et al. Pediatric sex estimation using AI-enabled ECG analysis: influence of pubertal development. NPJ Digit. Med. 7, 176 (2024).
Mayourian, J. et al. Pediatric ECG-based deep learning to predict left ventricular dysfunction and remodeling. Circulation 149, 917–931 (2024).
Dickinson, D. F. The normal ECG in childhood and adolescence. Heart 91, 1626–1630 (2005).
Kurokawa, J., Kodama, M., Clancy, C. E. & Furukawa, T. Sex hormonal regulation of cardiac ion channels in drug-induced QT syndromes. Pharmacol. Ther. 168, 23–28 (2016).
Locati, E. H. et al. Age- and sex-related differences in clinical manifestations in patients with congenital long-QT syndrome: findings from the international LQTS registry. Circulation 97, 2237–2244 (1998).
Di Diego, J. M. et al. Ionic and cellular basis for the predominance of the Brugada syndrome phenotype in males. Circulation 106, 2004–2011 (2002).
Stramba-Badiale, M., Spagnolo, D., Bosi, G. & Schwartz, P. J. Are gender differences in QTc present at birth? MISNES Investigators. Multicenter Italian Study on Neonatal Electrocardiography and Sudden Infant Death Syndrome. Am. J. Cardiol. 75, 1277–1278 (1995).
Hughes, J. W. et al. Performance of a convolutional neural network and explainability technique for 12-lead electrocardiogram interpretation. JAMA Cardiol. 6, 1285–1295 (2021).
Author information
Authors and Affiliations
Contributions
D.O’S., J.M., S.A., L.P., and J.D. contributed to data collection and data management. D.O’S., J.M., S.A., T.N., S.A.M., M.M., J.K.T., and J.D. contributed to study coordination. J.M., K.L., I.Z.A., D.O’S., and S.A. performed data analysis. D.O’S. and J.M. created the tables and figures. D.O’S., J.M., S.A., I.Z.A., P.A.F., F.L.-J., T.N., S.A.M., M.M., T.D., J.N.J., S.V., D.J.P., J.J.K., J.K.T., L.P., K.L., and J.D. contributed to study design and/or critical review of the manuscript. All authors contributed to data interpretation, revised the manuscript, and read and approved the final version.
Corresponding author
Ethics declarations
Competing interests
D.O’S., J.M., S.A., K.L., T.D., L.P., J.D., J.N.J., S.V., D.J.P., J.J.K., J.T., S.A.M., T.N., and M.M. report no conflicts of interest. I.Z.A. holds an ownership interest in Xai.health and serves as an advisor to Anumana.ai and AliveCor. F.L.-J. acts as an advisor to Anumana, receives royalties as a patent beneficiary from Anumana, consults for Kento, and serves as an advisor to Novo Nordisk and Wiseacre. P.A.F. has financial interests with Anumana, Eko Health, and AliveCor.
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-NonCommercial-NoDerivatives 4.0 International License, which permits any non-commercial use, sharing, 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 you modified the licensed material. You do not have permission under this licence to share adapted material derived from this article or parts of it. 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-nc-nd/4.0/.
About this article
Cite this article
O’Sullivan, D., Mayourian, J., Anjewierden, S. et al. Multicenter validation of AI-enabled ECG for pediatric biological sex prediction. npj Digit. Med. (2026). https://doi.org/10.1038/s41746-026-02416-9
Received:
Accepted:
Published:
DOI: https://doi.org/10.1038/s41746-026-02416-9
