A Two-Phase Multilabel ECG Classification Using One-Dimensional Convolutional Neural Network and Modified Labels
Ľubomír Antoni, Erik Bruoth, Peter Bugata, Dávid Gajdoš, Šimon Horvát, David E. Hudak, Vladimíra Kmečová, Richard Staňa, Monika Staňková, Alexander Szabari, Gabriela Vozáriková
Abstract
Within PhysioNet/Computing in Cardiology Challenge 2021, we developed a two-phase method of automatic ECG recording classification. In the first phase, we pre-trained a model on a large training set with our proposed mapping of original labels to the SNOMED codes, using threevalued labels. To solve the multilabel binary classification task, we used a deep convolutional neural network, which is a 1D variant of the popular ResNet50 network. In the second phase, we performed fine-tuning for the Challenge metric and conditions. Our team CeZIS took 6 <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">th</sup> , 3 <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">rd</sup> , 5th, 4 <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">th</sup> , and 5th places for the 12-lead, 6-lead, 4-lead, 3-lead, and 2-lead versions of the hidden test set, respectively, with a score of 0.52 for each lead configuration.