Background: Cardiovascular diseases (CVD) are the leading cause of death globally. Electrocardiogram (ECG) analysis can provide thoroughly assessment for different CVDs efficiently. We propose a multi-task group bidirectional long short-term memory (MTGBi-LSTM) framework to intelligent recognize multiple CVDs based on multi-lead ECG signals. Methods: This model employs a Group Bi-LSTM (GBi-LSTM) and Residual Group Convolutional Neural Network (Res-GCNN) to learn the dual feature representation of ECG space and time series. GBi-LSTM is divided into Global Bi-LSTM and Intra-Group Bi-LSTM, which can learn the features of each ECG lead and the relationship between leads. Then, through attention mechanism, the different lead information of ECG is integrated to make the model to possess the powerful feature discriminability. Through multi-task learning, the model can fully mine the association information between diseases and obtain more accurate diagnostic results. In addition, we propose a dynamic weighted loss function to better quantify the loss to overcome the imbalance between classes. Results: Based on more than 170,000 clinical 12-lead ECG analysis, the MTGBi-LSTM method achieved accuracy, precision, recall and F1 of 88.86%, 90.67%, 94.19% and 92.39%, respectively. The experimental results show that the proposed MTGBi-LSTM method can reliably realize ECG analysis and provide an effective tool for computer-aided diagnosis of CVD.

中文翻译：

---

多任务组 Bi-LSTM 网络在心电图分类上的应用

背景：心血管疾病（CVD）是全球主要的死亡原因。心电图 (ECG) 分析可以有效地为不同的 CVD 提供全面的评估。我们提出了一种多任务组双向长短期记忆 (MTGBi-LSTM) 框架，以基于多导联心电图信号智能识别多个 CVD。方法：该模型采用 Group Bi-LSTM (GBi-LSTM) 和 Residual Group Convolutional Neural Network (Res-GCNN) 来学习 ECG 空间和时间序列的双重特征表示。GBi-LSTM分为Global Bi-LSTM和Intra-Group Bi-LSTM，可以学习每个心电导联的特征以及导联之间的关系。然后，通过注意力机制，整合心电图的不同导联信息，使模型具有强大的特征判别能力。通过多任务学习，该模型可以充分挖掘疾病之间的关联信息，获得更准确的诊断结果。此外，我们提出了一个动态加权损失函数来更好地量化损失以克服类之间的不平衡。结果：基于超过 170,000 次临床 12 导联心电图分析，MTGBi-LSTM 方法的准确率、准确率、召回率和 F1 分别达到 88.86%、90.67%、94.19% 和 92.39%。实验结果表明，所提出的MTGBi-LSTM方法能够可靠地实现心电图分析，为CVD的计算机辅助诊断提供了有效的工具。基于超过 170,000 条临床 12 导联心电图分析，MTGBi-LSTM 方法的准确率、准确率、召回率和 F1 分别达到了 88.86%、90.67%、94.19% 和 92.39%。实验结果表明，所提出的MTGBi-LSTM方法能够可靠地实现心电图分析，为CVD的计算机辅助诊断提供了有效的工具。基于超过 170,000 条临床 12 导联心电图分析，MTGBi-LSTM 方法的准确率、准确率、召回率和 F1 分别达到了 88.86%、90.67%、94.19% 和 92.39%。实验结果表明，所提出的MTGBi-LSTM方法能够可靠地实现心电图分析，为CVD的计算机辅助诊断提供了有效的工具。