State Key Laboratory of Mathematical Engineering and Advanced Computing, Zhengzhou Science and Technology Institute, Zhengzhou 450003, China.
Cooperative Innovation Center of Internet Healthcare, Zhengzhou University, Zhengzhou 450001, China.
J Healthc Eng. 2020 May 18;2020:7526825. doi: 10.1155/2020/7526825. eCollection 2020.
Atrial fibrillation is the most common arrhythmia and is associated with high morbidity and mortality from stroke, heart failure, myocardial infarction, and cerebral thrombosis. Effective and rapid detection of atrial fibrillation is critical to reducing morbidity and mortality in patients. Screening atrial fibrillation quickly and efficiently remains a challenging task. In this paper, we propose SS-SWT and SI-CNN: an atrial fibrillation detection framework for the time-frequency ECG signal. First, specific-scale stationary wavelet transform (SS-SWT) is used to decompose a 5-s ECG signal into 8 scales. We select specific scales of coefficients as valid time-frequency features and abandon the other coefficients. The selected coefficients are fed to the scale-independent convolutional neural network (SI-CNN) as a two-dimensional (2D) matrix. In SI-CNN, a convolution kernel specifically for the time-frequency characteristics of ECG signals is designed. During the convolution process, the independence between each scale of coefficient is preserved, and the time domain and the frequency domain characteristics of the ECG signal are effectively extracted, and finally the atrial fibrillation signal is quickly and accurately identified. In this study, experiments are performed using the MIT-BIH AFDB data in 5-s data segments. We achieve 99.03% sensitivity, 99.35% specificity, and 99.23% overall accuracy. The SS-SWT and SI-CNN we propose simplify the feature extraction step, effectively extracts the features of ECG, and reduces the feature redundancy that may be caused by wavelet transform. The results shows that the method can effectively detect atrial fibrillation signals and has potential in clinical application.
心房颤动是最常见的心律失常，与中风、心力衰竭、心肌梗死和脑血栓形成导致的高发病率和死亡率有关。快速有效地检测心房颤动对于降低患者的发病率和死亡率至关重要。快速有效地筛选心房颤动仍然是一项具有挑战性的任务。在本文中，我们提出了 SS-SWT 和 SI-CNN：一种用于时频 ECG 信号的心房颤动检测框架。首先，使用特定尺度的平稳小波变换（SS-SWT）将 5 秒 ECG 信号分解为 8 个尺度。我们选择特定尺度的系数作为有效时频特征，并舍弃其他系数。选择的系数作为二维（2D）矩阵输入到尺度独立卷积神经网络（SI-CNN）中。在 SI-CNN 中，设计了一个专门针对 ECG 信号时频特征的卷积核。在卷积过程中，保留了每个系数尺度之间的独立性，有效地提取了 ECG 信号的时域和频域特征，并最终快速准确地识别心房颤动信号。在这项研究中，我们使用 MIT-BIH AFDB 数据在 5 秒数据段中进行了实验。我们实现了 99.03%的灵敏度、99.35%的特异性和 99.23%的整体准确性。我们提出的 SS-SWT 和 SI-CNN 简化了特征提取步骤，有效地提取了 ECG 的特征，并减少了可能由小波变换引起的特征冗余。结果表明，该方法可以有效地检测心房颤动信号，在临床应用中具有潜力。
