Salinas-Martínez Ricardo, de Bie Johannes, Marzocchi Nicoletta, Sandberg Frida
Mortara Instrument Europe s.r.l., Bologna, Italy.
Department of Biomedical Engineering, Lund University, Lund, Sweden.
Front Physiol. 2021 Aug 25;12:673819. doi: 10.3389/fphys.2021.673819. eCollection 2021.
Brief episodes of atrial fibrillation (AF) may evolve into longer AF episodes increasing the chances of thrombus formation, stroke, and death. Classical methods for AF detection investigate rhythm irregularity or P-wave absence in the ECG, while deep learning approaches profit from the availability of annotated ECG databases to learn discriminatory features linked to different diagnosis. However, some deep learning approaches do not provide analysis of the features used for classification. This paper introduces a convolutional neural network (CNN) approach for automatic detection of brief AF episodes based on electrocardiomatrix-images (ECM-images) aiming to link deep learning to features with clinical meaning. The CNN is trained using two databases: the Long-Term Atrial Fibrillation and the MIT-BIH Normal Sinus Rhythm, and tested on three databases: the MIT-BIH Atrial Fibrillation, the MIT-BIH Arrhythmia, and the Monzino-AF. Detection of AF is done using a sliding window of 10 beats plus 3 s. Performance is quantified using both standard classification metrics and the EC57 standard for arrhythmia detection. Layer-wise relevance propagation analysis was applied to link the decisions made by the CNN to clinical characteristics in the ECG. For all three testing databases, episode sensitivity was greater than 80.22, 89.66, and 97.45% for AF episodes shorter than 15, 30 s, and for all episodes, respectively. Rhythm and morphological characteristics of the electrocardiogram can be learned by a CNN from ECM-images for the detection of brief episodes of AF.
短暂性心房颤动（AF）发作可能会演变为更长时间的AF发作，从而增加血栓形成、中风和死亡的几率。传统的AF检测方法是研究心电图（ECG）中的节律不规则或P波缺失，而深度学习方法则受益于带注释的ECG数据库，以学习与不同诊断相关的判别特征。然而，一些深度学习方法并未对用于分类的特征进行分析。本文介绍了一种基于心电图矩阵图像（ECM图像）自动检测短暂AF发作的卷积神经网络（CNN）方法，旨在将深度学习与具有临床意义的特征联系起来。该CNN使用两个数据库进行训练：长期心房颤动数据库和麻省理工学院-比哈尔（MIT-BIH）正常窦性心律数据库，并在三个数据库上进行测试：麻省理工学院-比哈尔心房颤动数据库、麻省理工学院-比哈尔心律失常数据库和蒙齐诺-AF数据库。使用10个心搏加3秒的滑动窗口进行AF检测。使用标准分类指标和心律失常检测的EC57标准对性能进行量化。应用逐层相关性传播分析将CNN做出的决策与ECG中的临床特征联系起来。对于所有三个测试数据库，对于短于15秒、30秒的AF发作以及所有发作，发作敏感性分别大于80.22%、89.66%和97.45%。CNN可以从ECM图像中学习心电图的节律和形态特征，以检测短暂性AF发作。
