3KG: Contrastive Learning of 12-Lead Electrocardiograms using Physiologically-Inspired Augmentations

Bryan Gopal, Ryan Han, Gautham Raghupathi, Andrew Ng, Geoff Tison, Pranav Rajpurkar
Proceedings of Machine Learning for Health, PMLR 158:156-167, 2021.

Abstract

We propose 3KG, a physiologically-inspired contrastive learning approach that generates views using 3D augmentations of the 12-lead electrocardiogram. We evaluate representation quality by fine-tuning a linear layer for the downstream task of 23-class diagnosis on the PhysioNet 2020 challenge training data and find that 3KG achieves a 9.1% increase in mean AUC over the best self-supervised baseline when trained on 1% of labeled data. Our empirical analysis shows that combining spatial and temporal augmentations produces the strongest representations. In addition, we investigate the effect of this physiologically-inspired pretraining on downstream performance on different disease subgroups and find that 3KG makes the greatest gains for conduction and rhythm abnormalities. Our method allows for flexibility in incorporating other self-supervised strategies and highlights the potential for similar modality-specific augmentations for other biomedical signals.

Cite this Paper

BibTeX
@InProceedings{pmlr-v158-gopal21a, title = {3KG: Contrastive Learning of 12-Lead Electrocardiograms using Physiologically-Inspired Augmentations}, author = {Gopal, Bryan and Han, Ryan and Raghupathi, Gautham and Ng, Andrew and Tison, Geoff and Rajpurkar, Pranav}, booktitle = {Proceedings of Machine Learning for Health}, pages = {156--167}, year = {2021}, editor = {Roy, Subhrajit and Pfohl, Stephen and Rocheteau, Emma and Tadesse, Girmaw Abebe and Oala, Luis and Falck, Fabian and Zhou, Yuyin and Shen, Liyue and Zamzmi, Ghada and Mugambi, Purity and Zirikly, Ayah and McDermott, Matthew B. A. and Alsentzer, Emily}, volume = {158}, series = {Proceedings of Machine Learning Research}, month = {04 Dec}, publisher = {PMLR}, pdf = {https://proceedings.mlr.press/v158/gopal21a/gopal21a.pdf}, url = {https://proceedings.mlr.press/v158/gopal21a.html}, abstract = {We propose 3KG, a physiologically-inspired contrastive learning approach that generates views using 3D augmentations of the 12-lead electrocardiogram. We evaluate representation quality by fine-tuning a linear layer for the downstream task of 23-class diagnosis on the PhysioNet 2020 challenge training data and find that 3KG achieves a 9.1% increase in mean AUC over the best self-supervised baseline when trained on 1% of labeled data. Our empirical analysis shows that combining spatial and temporal augmentations produces the strongest representations. In addition, we investigate the effect of this physiologically-inspired pretraining on downstream performance on different disease subgroups and find that 3KG makes the greatest gains for conduction and rhythm abnormalities. Our method allows for flexibility in incorporating other self-supervised strategies and highlights the potential for similar modality-specific augmentations for other biomedical signals.} }
Endnote
%0 Conference Paper %T 3KG: Contrastive Learning of 12-Lead Electrocardiograms using Physiologically-Inspired Augmentations %A Bryan Gopal %A Ryan Han %A Gautham Raghupathi %A Andrew Ng %A Geoff Tison %A Pranav Rajpurkar %B Proceedings of Machine Learning for Health %C Proceedings of Machine Learning Research %D 2021 %E Subhrajit Roy %E Stephen Pfohl %E Emma Rocheteau %E Girmaw Abebe Tadesse %E Luis Oala %E Fabian Falck %E Yuyin Zhou %E Liyue Shen %E Ghada Zamzmi %E Purity Mugambi %E Ayah Zirikly %E Matthew B. A. McDermott %E Emily Alsentzer %F pmlr-v158-gopal21a %I PMLR %P 156--167 %U https://proceedings.mlr.press/v158/gopal21a.html %V 158 %X We propose 3KG, a physiologically-inspired contrastive learning approach that generates views using 3D augmentations of the 12-lead electrocardiogram. We evaluate representation quality by fine-tuning a linear layer for the downstream task of 23-class diagnosis on the PhysioNet 2020 challenge training data and find that 3KG achieves a 9.1% increase in mean AUC over the best self-supervised baseline when trained on 1% of labeled data. Our empirical analysis shows that combining spatial and temporal augmentations produces the strongest representations. In addition, we investigate the effect of this physiologically-inspired pretraining on downstream performance on different disease subgroups and find that 3KG makes the greatest gains for conduction and rhythm abnormalities. Our method allows for flexibility in incorporating other self-supervised strategies and highlights the potential for similar modality-specific augmentations for other biomedical signals.
APA
Gopal, B., Han, R., Raghupathi, G., Ng, A., Tison, G. & Rajpurkar, P.. (2021). 3KG: Contrastive Learning of 12-Lead Electrocardiograms using Physiologically-Inspired Augmentations. Proceedings of Machine Learning for Health, in Proceedings of Machine Learning Research 158:156-167 Available from https://proceedings.mlr.press/v158/gopal21a.html.

Related Material