Cai Wenjie, Liu Fanli, Xu Bolin, Wang Xuan, Hu Shuaicong, Wang Mingjie
School of Health Science and Engineering, University of Shanghai for Science and Technology, Shanghai, 200093, People's Republic of China.
Shanghai Key Laboratory of Bioactive Small Molecules, School of Basic Medical Science, Fudan University, Shanghai, 200032, People's Republic of China.
Physiol Meas. 2022 Jul 18;43(7). doi: 10.1088/1361-6579/ac7939.
. Automatic electrocardiogram (ECG) interpretation based on deep learning methods is attracting increasing attention. In this study, we propose a novel method to accurately classify multi-lead ECGs using deep residual neural networks.. ECG recordings from seven different open databases were provided by PhysioNet/Computing in Cardiology Challenge 2021. All the ECGs were pre-processed to obtain the same sampling rate. The label inconsistency among the databases was corrected by adding or removing specific labels. A label mask was created to filter out potentially incorrectly labelled data. Five models based on deep residual convolutional neural networks were optimized using an asymmetric loss function to classify multi-lead ECGs.. The proposed method achieved an official challenge score of 0.54, 0.52, 0.50, 0.51, and 0.50 on twelve-lead, six-lead, four-lead, three-lead, and two-lead ECG test sets, respectively. These scores were ranked 5th, 3rd, 7th, 5th and 7th, respectively, in the challenge.. The proposed method can correct the differential labeling tendency of databases from different sources and exhibits good generalization for classifying multi-lead ECGs in the hidden test set. The proposed models have the potential for clinical applications.
基于深度学习方法的自动心电图（ECG）解读正受到越来越多的关注。在本研究中，我们提出了一种使用深度残差神经网络对多导联心电图进行准确分类的新方法。2021年心肺生理数据挑战赛（PhysioNet/Computing in Cardiology Challenge）提供了来自七个不同公开数据库的心电图记录。所有心电图均经过预处理以获得相同的采样率。通过添加或删除特定标签来纠正数据库之间的标签不一致问题。创建了一个标签掩码以过滤掉可能错误标记的数据。使用非对称损失函数对基于深度残差卷积神经网络的五个模型进行优化，以对多导联心电图进行分类。所提出的方法在十二导联、六导联、四导联、三导联和两导联心电图测试集上分别取得了0.54、0.52、0.50、0.51和0.50的官方挑战赛分数。这些分数在挑战赛中分别排名第5、第3、第7、第5和第7。所提出的方法可以纠正来自不同来源数据库的差异标记倾向，并且在隐藏测试集中对多导联心电图分类表现出良好的泛化能力。所提出的模型具有临床应用潜力。
