In-depth Benchmarking of Deep Neural Network Architectures for ECG Diagnosis

Naoki Nonaka, Jun Seita
Proceedings of the 6th Machine Learning for Healthcare Conference, PMLR 149:414-439, 2021.

Abstract

The electrocardiogram (ECG) is a widely used device to monitor the electrical activity of the heart. To diagnose various heart abnormalities, ECG diagnosis algorithms have been developed and deep neural networks (DNN) have been shown to achieve significant performance. Most of the DNN architectures used for ECG diagnosis models are adopted from architectures developed for image or natural language domain, and their performances have improved year by year in the original domains. In this work, we conduct in-depth benchmarking of DNN architectures for ECG diagnosis. Using three datasets, we compared nine DNN architectures for both multi-label classification settings evaluated with ROC- AUC score and multi-class classification settings evaluated with F1 scores. The results showed that one of classical architectures, ResNet-18, performed consistently better over most of architectures, suggesting there is room for developing DNN architecture tailored for ECG domain.

Cite this Paper

BibTeX
@InProceedings{pmlr-v149-nonaka21a, title = {In-depth Benchmarking of Deep Neural Network Architectures for ECG Diagnosis}, author = {Nonaka, Naoki and Seita, Jun}, booktitle = {Proceedings of the 6th Machine Learning for Healthcare Conference}, pages = {414--439}, year = {2021}, editor = {Jung, Ken and Yeung, Serena and Sendak, Mark and Sjoding, Michael and Ranganath, Rajesh}, volume = {149}, series = {Proceedings of Machine Learning Research}, month = {06--07 Aug}, publisher = {PMLR}, pdf = {https://proceedings.mlr.press/v149/nonaka21a/nonaka21a.pdf}, url = {https://proceedings.mlr.press/v149/nonaka21a.html}, abstract = {The electrocardiogram (ECG) is a widely used device to monitor the electrical activity of the heart. To diagnose various heart abnormalities, ECG diagnosis algorithms have been developed and deep neural networks (DNN) have been shown to achieve significant performance. Most of the DNN architectures used for ECG diagnosis models are adopted from architectures developed for image or natural language domain, and their performances have improved year by year in the original domains. In this work, we conduct in-depth benchmarking of DNN architectures for ECG diagnosis. Using three datasets, we compared nine DNN architectures for both multi-label classification settings evaluated with ROC- AUC score and multi-class classification settings evaluated with F1 scores. The results showed that one of classical architectures, ResNet-18, performed consistently better over most of architectures, suggesting there is room for developing DNN architecture tailored for ECG domain.} }
Endnote
%0 Conference Paper %T In-depth Benchmarking of Deep Neural Network Architectures for ECG Diagnosis %A Naoki Nonaka %A Jun Seita %B Proceedings of the 6th Machine Learning for Healthcare Conference %C Proceedings of Machine Learning Research %D 2021 %E Ken Jung %E Serena Yeung %E Mark Sendak %E Michael Sjoding %E Rajesh Ranganath %F pmlr-v149-nonaka21a %I PMLR %P 414--439 %U https://proceedings.mlr.press/v149/nonaka21a.html %V 149 %X The electrocardiogram (ECG) is a widely used device to monitor the electrical activity of the heart. To diagnose various heart abnormalities, ECG diagnosis algorithms have been developed and deep neural networks (DNN) have been shown to achieve significant performance. Most of the DNN architectures used for ECG diagnosis models are adopted from architectures developed for image or natural language domain, and their performances have improved year by year in the original domains. In this work, we conduct in-depth benchmarking of DNN architectures for ECG diagnosis. Using three datasets, we compared nine DNN architectures for both multi-label classification settings evaluated with ROC- AUC score and multi-class classification settings evaluated with F1 scores. The results showed that one of classical architectures, ResNet-18, performed consistently better over most of architectures, suggesting there is room for developing DNN architecture tailored for ECG domain.
APA
Nonaka, N. & Seita, J.. (2021). In-depth Benchmarking of Deep Neural Network Architectures for ECG Diagnosis. Proceedings of the 6th Machine Learning for Healthcare Conference, in Proceedings of Machine Learning Research 149:414-439 Available from https://proceedings.mlr.press/v149/nonaka21a.html.

Related Material