Qi Ji, Zhang Ruiqing, Shen Yang, Chang Shijie, Sha Xiangzheng
Department of Biomedical Engineering, China Medical University, Shenyang, 110122.
The Fourth Affiliated Hospital of China Medical University, Shenyang, 110032.
Zhongguo Yi Liao Qi Xie Za Zhi. 2019 Mar 30;43(2):86-89. doi: 10.3969/j.issn.1671-7104.2019.02.003.
To classify Right Bundle Branch Block (RBBB),Left Bundle Branch Block (LBBB) and normal ECG signals automatically.
The MIT-BIH database was used as experimental data sources.The training set and test set were extracted for training and testing network models.Based on convolutional neural network,this paper proposed the core algorithm:sparse connection residual network.Compared the sparse connected residual network with classic network models,then evaluated the recognition effect of the model.
The accuracy of the test set the MIT-BIH database was 95.2%,the result is better than classic network models.
The algorithm proposed in this paper can assist doctors in the diagnosis of heart block related disease and place a high value on clinical application.
自动分类右束支传导阻滞（RBBB）、左束支传导阻滞（LBBB）和正常心电图信号。
将麻省理工学院-贝斯以色列女执事医疗中心（MIT-BIH）数据库用作实验数据源。提取训练集和测试集用于训练和测试网络模型。基于卷积神经网络，本文提出了核心算法：稀疏连接残差网络。将稀疏连接残差网络与经典网络模型进行比较，然后评估模型的识别效果。
麻省理工学院-贝斯以色列女执事医疗中心（MIT-BIH）数据库测试集的准确率为95.2%，结果优于经典网络模型。
本文提出的算法可辅助医生诊断心脏传导阻滞相关疾病，具有较高的临床应用价值。
