Ping An Technology, Beijing, People's Republic of China.
Saw Swee Hock School of Public Health, National University Health System, National University of Singapore, Singapore.
Physiol Meas. 2021 Jun 29;42(6). doi: 10.1088/1361-6579/ac08e6.
. Cardiovascular disease is a major threat to health and one of the primary causes of death globally. The 12-lead ECG is a cheap and commonly accessible tool to identify cardiac abnormalities. Early and accurate diagnosis will allow early treatment and intervention to prevent severe complications of cardiovascular disease. Our objective is to develop an algorithm that automatically identifies 27 ECG abnormalities from 12-lead ECG databases.. Firstly, a series of pre-processing methods were proposed and applied on various data sources in order to mitigate the problem of data divergence. Secondly, we ensembled two SE_ResNet models and one rule-based model to enhance the performance of various ECG abnormalities' classification. Thirdly, we introduce a Sign Loss to tackle the problem of class imbalance, and thus improve the model's generalizability.. In the PhysioNet/Computing in Cardiology Challenge (2020), our proposed approach achieved a challenge validation score of 0.682, and a full test score of 0.514, placed us 3rd out of 40 in the official ranking.. We proposed an accurate and robust predictive framework that combines deep neural networks and clinical knowledge to automatically classify multiple ECG abnormalities. Our framework is able to identify 27 ECG abnormalities from multi-lead ECG signals regardless of discrepancies in data sources and the imbalance of data labeling. We trained our framework on five datasets and validated it on six datasets from various countries. The outstanding performance demonstrate the effectiveness of our proposed framework.
心血管疾病是对健康的主要威胁之一，也是全球主要死因之一。12 导联心电图是一种廉价且普遍可获得的工具，可用于识别心脏异常。早期和准确的诊断将允许早期治疗和干预，以预防心血管疾病的严重并发症。我们的目标是开发一种算法，该算法可以自动从 12 导联心电图数据库中识别 27 种心电图异常。
首先，我们提出了一系列预处理方法，并将其应用于各种数据源，以减轻数据分歧的问题。其次，我们集成了两个 SE_ResNet 模型和一个基于规则的模型，以提高各种心电图异常分类的性能。第三，我们引入了符号丢失（Sign Loss）来解决类不平衡的问题，从而提高模型的泛化能力。
在 PhysioNet/Computing in Cardiology Challenge（2020）中，我们的方法在挑战验证中获得了 0.682 的得分，在完整测试中获得了 0.514 的得分，在官方排名中名列第四十名中的第三名。
我们提出了一种准确且稳健的预测框架，该框架结合了深度学习网络和临床知识，能够自动分类多种心电图异常。我们的框架能够从多导联心电图信号中识别 27 种心电图异常，无论数据源存在差异还是数据标签不平衡。我们在五个数据集上进行了训练，并在来自不同国家的六个数据集上进行了验证。出色的表现证明了我们提出的框架的有效性。
