Key result
Deep representation learning of 12-lead ECGs identified latent factors strongly associated with cardiac diseases, including a 2.72-fold increased odds of bundle branch block per standard deviation increase in latent factor 28.
Why the study?
Conventional fragmented ECG analyses ignore high dimensionality, potentially missing subtle cardiac biological information, whereas deep representation learning may reveal novel insights.
Observational (n=41,927)
Yes
Odds Ratio: 2.72 (95% CI 2.46–3.01)
Deep representation learning of 12-lead ECGs extracts latent factors that capture novel structural, functional, and genetic information beyond traditional ECG parameters, offering new insights into cardiovascular health.
ECG VAE representations may capture overlooked signals; hypothesis-generating and requires prospective validation before any clinical role.
Background Conventional approaches to analysing electrocardiograms (ECG) in fragmented parameters (such as the PR interval) ignored the high dimensionality of data which might result in omission of subtle information content relevant the cardiac biology. Deep representation learning of ECG may reveal novel insights. Methods We finetuned an unsupervised variational auto-encoder (VAE), originally trained on over 1.1 million 12-lead ECG, to learn the underlying distributions of the median beat ECG morphology of 41,927 UK Biobank participants. We explored the relationship between the latent representations (latent factors) and traditional ECG parameters, cardiac magnetic resonance (CMR)-derived structural and functional phenotypes. We assessed the association of the latent factors with various cardiac and cardiometabolic diseases and further investigated their predictive value for cardiovascular mortality. Finally, we studied genetic components of the latent factors by genome wide association study (GWAS). Results The latent factors showed differential correlation patterns with conventional ECG parameters with the highest correlations observed in factor 8 and PR interval (r=0.76). Multivariable analyses of the ECG latent factors recapitulated CMR-derived parameters with a better performance for the left ventricle than the right. We saw higher performance in models for structural parameters than functional parameters and observed the highest adjusted R 2 of 0.488 for left ventricular LV end-diastolic mass (LVEDM). The latent factors showed strong association with cardiac diseases. This included bundle branch block and latent factor 28 (OR= 2.72 [95% confidence interval CI,2.46-3.01] per standard deviation, SD change); per SD change of latent factor 27 was associated with cardiomyopathy (OR=2.38, 95%CI 1.97-2.89) and heart failure (OR=1.94, 95%CI 1.71-2.21). In the GWAS of the latent factors, we identified 170 genetic loci with 29 not previously associated with electrocardiographic traits. Following up with bioinformatic analyses, we found the genetic signals involved in cardiac development, contractility and electrophysiology. Conclusions Deep representation learning of 12-lead ECG provided not only clinically meaningful but also novel insights into cardiac biology and cardiovascular health.
No takes yet. Share an insight, caveat, or question.
Yeung et al. (2023) conducted an observational in General population (n=41,927). ECG latent factors (deep representation learning) was evaluated on Bundle branch block (OR 2.72, 95% CI 2.46-3.01). Deep representation learning of 12-lead ECGs identified latent factors strongly associated with cardiac diseases, including a 2.72-fold increased odds of bundle branch block per standard deviation increase in latent factor 28.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: