Skip to main content

Lund University Publications

LUND UNIVERSITY LIBRARIES

Advanced electrocardiography heart age : a prognostic, explainable machine learning approach applicable to sinus and non-sinus rhythms

Al-Falahi, Zaidon S. ; Schlegel, Todd T. ; Palencia-Lamela, Israel ; Li, Annie ; Schelbert, Erik B. ; Niklasson, Louise ; Maanja, Maren ; Lindow, Thomas LU and Ugander, Martin LU (2025) In European Heart Journal - Digital Health 6(1). p.45-54
Abstract

Aims: An explainable advanced electrocardiography (A-ECG) Heart Age gap is the difference between A-ECG Heart Age and chronological age. This gap is an estimate of accelerated cardiovascular aging expressed in years of healthy human aging, and can intuitively communicate cardiovascular risk to the general population. However, existing A-ECG Heart Age requires sinus rhythm. We aim to develop and prognostically validate a revised, explainable A-ECG Heart Age applicable to both sinus and non-sinus rhythms. Methods and results: An A-ECG Heart Age excluding P-wave measures was derived from the 10-s 12-lead ECG in a derivation cohort using multivariable regression machine learning with Bayesian 5-min 12-lead A-ECG Heart Age as reference. The... (More)

Aims: An explainable advanced electrocardiography (A-ECG) Heart Age gap is the difference between A-ECG Heart Age and chronological age. This gap is an estimate of accelerated cardiovascular aging expressed in years of healthy human aging, and can intuitively communicate cardiovascular risk to the general population. However, existing A-ECG Heart Age requires sinus rhythm. We aim to develop and prognostically validate a revised, explainable A-ECG Heart Age applicable to both sinus and non-sinus rhythms. Methods and results: An A-ECG Heart Age excluding P-wave measures was derived from the 10-s 12-lead ECG in a derivation cohort using multivariable regression machine learning with Bayesian 5-min 12-lead A-ECG Heart Age as reference. The Heart Age was externally validated in a separate cohort of patients referred for cardiovascular magnetic resonance imaging by describing its association with heart failure hospitalization or death using Cox regression, and its association with comorbidities. In the derivation cohort (n = 2771), A-ECG Heart Age agreed with the 5-min Heart Age (R2 = 0.91, bias 0.0 ± 6.7 years), and increased with increasing comorbidity. In the validation cohort [n = 731, mean age 54 ± 15 years, 43% female, n = 139 events over 5.7 (4.8-6.7) years follow-up], increased A-ECG Heart Age gap (≥10 years) associated with events [hazard ratio, HR (95% confidence interval, CI) 2.04 (1.38-3.00), C-statistic 0.58 (0.54-0.62)], and the presence of hypertension, diabetes mellitus, hypercholesterolaemia, and heart failure (P ≤ 0.009 for all). Conclusion: An explainable A-ECG Heart Age gap applicable to both sinus and non-sinus rhythm associates with cardiovascular risk, cardiovascular morbidity, and survival.

(Less)
Please use this url to cite or link to this publication:
author
; ; ; ; ; ; ; and
organization
publishing date
type
Contribution to journal
publication status
published
subject
keywords
Accelerated aging, Advanced ECG analysis, ECG, Machine learning, Risk prediction
in
European Heart Journal - Digital Health
volume
6
issue
1
pages
10 pages
publisher
Oxford University Press
external identifiers
  • scopus:85216021890
  • pmid:39846063
ISSN
2634-3916
DOI
10.1093/ehjdh/ztae075
language
English
LU publication?
yes
additional info
Publisher Copyright: © 2024 The Author(s). Published by Oxford University Press on behalf of the European Society of Cardiology.
id
50b92e0a-382a-4007-87af-a57aeaf6efc4
date added to LUP
2025-04-09 15:10:32
date last changed
2025-04-23 15:35:28
@article{50b92e0a-382a-4007-87af-a57aeaf6efc4,
  abstract     = {{<p>Aims: An explainable advanced electrocardiography (A-ECG) Heart Age gap is the difference between A-ECG Heart Age and chronological age. This gap is an estimate of accelerated cardiovascular aging expressed in years of healthy human aging, and can intuitively communicate cardiovascular risk to the general population. However, existing A-ECG Heart Age requires sinus rhythm. We aim to develop and prognostically validate a revised, explainable A-ECG Heart Age applicable to both sinus and non-sinus rhythms. Methods and results: An A-ECG Heart Age excluding P-wave measures was derived from the 10-s 12-lead ECG in a derivation cohort using multivariable regression machine learning with Bayesian 5-min 12-lead A-ECG Heart Age as reference. The Heart Age was externally validated in a separate cohort of patients referred for cardiovascular magnetic resonance imaging by describing its association with heart failure hospitalization or death using Cox regression, and its association with comorbidities. In the derivation cohort (n = 2771), A-ECG Heart Age agreed with the 5-min Heart Age (R<sup>2</sup> = 0.91, bias 0.0 ± 6.7 years), and increased with increasing comorbidity. In the validation cohort [n = 731, mean age 54 ± 15 years, 43% female, n = 139 events over 5.7 (4.8-6.7) years follow-up], increased A-ECG Heart Age gap (≥10 years) associated with events [hazard ratio, HR (95% confidence interval, CI) 2.04 (1.38-3.00), C-statistic 0.58 (0.54-0.62)], and the presence of hypertension, diabetes mellitus, hypercholesterolaemia, and heart failure (P ≤ 0.009 for all). Conclusion: An explainable A-ECG Heart Age gap applicable to both sinus and non-sinus rhythm associates with cardiovascular risk, cardiovascular morbidity, and survival.</p>}},
  author       = {{Al-Falahi, Zaidon S. and Schlegel, Todd T. and Palencia-Lamela, Israel and Li, Annie and Schelbert, Erik B. and Niklasson, Louise and Maanja, Maren and Lindow, Thomas and Ugander, Martin}},
  issn         = {{2634-3916}},
  keywords     = {{Accelerated aging; Advanced ECG analysis; ECG; Machine learning; Risk prediction}},
  language     = {{eng}},
  month        = {{01}},
  number       = {{1}},
  pages        = {{45--54}},
  publisher    = {{Oxford University Press}},
  series       = {{European Heart Journal - Digital Health}},
  title        = {{Advanced electrocardiography heart age : a prognostic, explainable machine learning approach applicable to sinus and non-sinus rhythms}},
  url          = {{http://dx.doi.org/10.1093/ehjdh/ztae075}},
  doi          = {{10.1093/ehjdh/ztae075}},
  volume       = {{6}},
  year         = {{2025}},
}