TY - GEN
T1 - Automatic 12-lead ECG Classification Using a Convolutional Network Ensemble
AU - Ribeiro, Antonio H.
AU - Gedon, Daniel
AU - Teixeira, Daniel Martins
AU - Ribeiro, Manoel Horta
AU - Ribeiro, Antonio L.Pinho
AU - Schon, Thomas B.
AU - Meira, Wagner
N1 - Publisher Copyright:
© 2020 Creative Commons; the authors hold their copyright.
PY - 2020/9/13
Y1 - 2020/9/13
N2 - The 12-lead electrocardiogram (ECG) is a major diagnostic test for cardiovascular diseases and enhanced automated analysis tools might lead to more reliable diagnosis and improved clinical practice. Deep neural networks are models composed of stacked transformations that learn tasks by examples. Inspired by the success of these models in computer vision, we propose an end-to-end approach for the task at hand. We trained deep convolutional neural network models in the heterogeneous dataset provided in the Physionet 2020 Challenge and used an ensemble of seven of these convolutional models for the classification of abnormalities present in the ECG records. Ensembles use the output of multiple models to generate a combined prediction and are known to improve performance and generalization when compared to the individual models. In our submission, we use an ensemble of neural networks with the architecture similar to the one described in Nat Commun 11, 1760 (2020) for 12-lead ECGs classification. Our approach achieved a challenge validation score of 0.657, and full test score of 0.132, placing us, the 'Code Team', in 28 out of 41 in the official ranking.
AB - The 12-lead electrocardiogram (ECG) is a major diagnostic test for cardiovascular diseases and enhanced automated analysis tools might lead to more reliable diagnosis and improved clinical practice. Deep neural networks are models composed of stacked transformations that learn tasks by examples. Inspired by the success of these models in computer vision, we propose an end-to-end approach for the task at hand. We trained deep convolutional neural network models in the heterogeneous dataset provided in the Physionet 2020 Challenge and used an ensemble of seven of these convolutional models for the classification of abnormalities present in the ECG records. Ensembles use the output of multiple models to generate a combined prediction and are known to improve performance and generalization when compared to the individual models. In our submission, we use an ensemble of neural networks with the architecture similar to the one described in Nat Commun 11, 1760 (2020) for 12-lead ECGs classification. Our approach achieved a challenge validation score of 0.657, and full test score of 0.132, placing us, the 'Code Team', in 28 out of 41 in the official ranking.
UR - http://www.scopus.com/inward/record.url?scp=85100928359&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85100928359&partnerID=8YFLogxK
U2 - 10.22489/CinC.2020.130
DO - 10.22489/CinC.2020.130
M3 - Conference contribution
AN - SCOPUS:85100928359
T3 - Computing in Cardiology
BT - 2020 Computing in Cardiology, CinC 2020
PB - IEEE Computer Society
T2 - 2020 Computing in Cardiology, CinC 2020
Y2 - 13 September 2020 through 16 September 2020
ER -