A two-phase multilabel ECG classification method using a 1D convolutional neural network achieved a score of 0.52 across multiple lead configurations on the hidden test set.
A 1D ResNet50-based convolutional neural network with a two-phase training approach achieved competitive performance in automatic multilabel ECG classification across various lead configurations.
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 th , 3 rd , 5th, 4 th , 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.
Antoni et al. (Mon,) conducted a other in ECG recording classification. Two-phase multilabel ECG classification using 1D CNN was evaluated on Challenge metric score on hidden test set. A two-phase multilabel ECG classification method using a 1D convolutional neural network achieved a score of 0.52 across multiple lead configurations on the hidden test set.