Studying accelerated cardiovascular ageing in Russian adults through a novel deep-learning ECG biomarker
Background: A non-invasive, easy-to-access marker of accelerated
cardiac ageing would provide novel insights into the mechanisms and
aetiology of cardiovascular disease (CVD) as well as contribute to risk
stratification of those who have not had a heart or circulatory event.
Our hypothesis is that differences between an ECG-predicted and
chronologic age of participants (δage) would reflect accelerated or
decelerated cardiovascular ageing
Methods: A convolutional neural network model trained on over
700,000 ECGs from the Mayo Clinic in the U.S.A was used to predict
the age of 4,542 participants in the Know Your Heart study conducted
in two cities in Russia (2015-2018). Thereafter, δage was used in linear
Open Peer Review
Reviewer Status AWAITING PEER REVIEW
Any reports and responses or comments on the
article can be found at the end of the article.
Page 1 of 12
Wellcome Open Research 2021, 6:12 Last updated: 31 JAN 2021
Corresponding author: Ernest Diez Benavente (Ernest.DiezBenavente@lshtm.ac.uk)
Author roles: Diez Benavente E: Conceptualization, Data Curation, Formal Analysis, Visualization, Writing – Original Draft Preparation,
Writing – Review & Editing; Jimenez-Lopez F: Conceptualization, Supervision, Writing – Review & Editing; Attia ZI: Data Curation, Formal
Analysis, Writing – Review & Editing; Malyutina S: Data Curation, Formal Analysis, Funding Acquisition, Writing – Review & Editing;
Kudryavtsev A: Data Curation, Formal Analysis, Funding Acquisition, Project Administration, Writing – Review & Editing; Ryabikov A:
Data Curation, Formal Analysis, Investigation, Writing – Review & Editing; Friedman PA: Supervision, Writing – Review & Editing; Kapa S:
Supervision, Writing – Review & Editing; Voevoda M: Supervision, Writing – Review & Editing; Perel P: Conceptualization, Supervision,
Writing – Review & Editing; Schirmer H: Conceptualization, Writing – Review & Editing; Hughes AD: Conceptualization, Writing – Review
& Editing; Clark TG: Conceptualization, Supervision, Writing – Review & Editing; Leon DA: Conceptualization, Funding Acquisition,
Supervision, Writing – Review & Editing
Competing interests: No competing interests were disclosed.
Grant information: TGC received funding from the MRC UK (Grant no. MR/K000551/1, MR/M01360X/1, MR/N010469/1, MR/R020973/1)
and BBSRC UK (BB/R013063/1). Know Your Heart (KYH) is a component of the International Project on Cardiovascular Disease in Russia
(IPCDR) funded by a Wellcome Trust Strategic Award , UiT The Arctic University of. Norway (UiT), Norwegian Institute of Public
Health, and Norwegian Ministry of Health and Social Affairs.
The funders had no role in study design, data collection and analysis, decision to publish, or preparation of the manuscript.
Copyright: © 2021 Diez Benavente E et al. This is an open access article distributed under the terms of the Creative Commons
Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly
How to cite this article: Diez Benavente E, Jimenez-Lopez F, Attia ZI et al. Studying accelerated cardiovascular ageing in Russian
adults through a novel deep-learning ECG biomarker [version 1; peer review: awaiting peer review] Wellcome Open Research
2021, 6:12 https://doi.org/10.12688/wellcomeopenres.16499.1
First published: 25 Jan 2021, 6:12 https://doi.org/10.12688/wellcomeopenres.16499.1
regression models to assess associations with known CVD risk factors
and markers of cardiac abnormalities.
Results: The biomarker δage (mean: +5.32 years) was strongly and
positively associated with established risk factors for CVD: blood
pressure, body mass index (BMI), total cholesterol and smoking.
Additionally, δage had strong independent positive associations with
markers of structural cardiac abnormalities: N-terminal pro b-type
natriuretic peptide (NT-proBNP), high sensitivity cardiac troponin T
(hs-cTnT) and pulse wave velocity, a valid marker of vascular ageing.
Conclusion: The difference between the ECG-age obtained from a
convolutional neural network and chronologic age (δage) contains
information about the level of exposure of an individual to established
CVD risk factors and to markers of cardiac damage in a way that is
consistent with it being a biomarker of accelerated cardiovascular
(vascular) ageing. Further research is needed to explore whether
these associations are seen in populations with different risks of CVD
events, and to better understand the underlying mechanisms