Deep Discriminative Domain Generalization with Adversarial Feature Learning for Classifying ECG Signals

Zuogang Shang, Zhibin Zhao, Hui Fang, Samuel Relton, Darcy Murphy, Zoe Hancox, Ruqiang Yan, David Wong

Research output: Chapter in Book/Report/Conference proceedingChapterpeer-review

73 Downloads (Pure)


Introduction: The goal of the 2021 PhysioNet/CinC challenge is to classify cardiac abnormalities from ECGs and evaluate the diagnostic potential of reduced-lead ECGs. Here, we describe the classification model created by the team 'AIHealthcare'. Methods: ECGs were downsampled to 300 Hz and filtered by wavelet. ECGs were randomly clipped or zero-padded to 4,096 samples. We modified an SE-ResNet to perform multi-task classification of both dataset and disease. We used a gradient reversal layer as part of an adversarial feature learning scheme to learn domain-invariant and discriminative representations. Results: We trained our domain-invariant model on 5 datasets, keeping one data set (Ningbo) for local validation. We also trained a baseline SE-ResNet using the same training data. In validation on the held-out data set, the domain-invariant model had a higher Challenge metric than the baseline model. Our entry was not officially ranked in the Challenge, as we did not have a successful entry during the unofficial phase of the Challenge. Conclusion: The domain-invariant model performed better than the baseline model in local held-out datasets, suggesting that this method may help improve generalisation performance.

Original languageEnglish
Title of host publicationComputing in Cardiology
ISBN (Electronic)9781665479165
Publication statusPublished - 2021
Event2021 Computing in Cardiology (CinC) - Brno, Czech Republic
Duration: 13 Sep 202115 Sep 2021

Publication series

NameComputing in Cardiology


Conference2021 Computing in Cardiology (CinC)


Dive into the research topics of 'Deep Discriminative Domain Generalization with Adversarial Feature Learning for Classifying ECG Signals'. Together they form a unique fingerprint.

Cite this