Department of Biomedical Engineering, Yonsei University College of Health Science, Wonju, Korea.
CHANGEUI TECH Co., Ltd., Wonju, Korea.
J Korean Med Sci. 2019 Feb 15;34(7):e64. doi: 10.3346/jkms.2019.34.e64. eCollection 2019 Feb 25.
In this study, we propose a method for automatically predicting atrial fibrillation (AF) based on convolutional neural network (CNN) using a short-term normal electrocardiogram (ECG) signal.
We designed a CNN model and optimized it by dropout and normalization. One-dimensional convolution, max-pooling, and fully-connected multiple perceptron were used to analyze the short-term normal ECG. The ECG signal was preprocessed and segmented to train and evaluate the proposed CNN model. The training and test sets consisted of the two AF and one normal dataset from the MIT-BIH database.
The proposed CNN model for the automatic prediction of AF achieved a high performance with a sensitivity of 98.6%, a specificity of 98.7%, and an accuracy of 98.7%.
The results show the possibility of automatically predicting AF based on the CNN model using a short-term normal ECG signal. The proposed CNN model for the automatic prediction of AF can be a helpful tool for the early diagnosis of AF in healthcare fields.
在这项研究中，我们提出了一种基于卷积神经网络（CNN）的方法，使用短期正常心电图（ECG）信号自动预测心房颤动（AF）。
我们设计了一个 CNN 模型，并通过 dropout 和归一化对其进行了优化。一维卷积、最大池化和全连接多层感知器用于分析短期正常 ECG。对 ECG 信号进行预处理和分段，以训练和评估所提出的 CNN 模型。训练集和测试集由来自 MIT-BIH 数据库的两个 AF 和一个正常数据集组成。
所提出的用于自动预测 AF 的 CNN 模型具有较高的性能，灵敏度为 98.6%，特异性为 98.7%，准确率为 98.7%。
结果表明，基于 CNN 模型使用短期正常 ECG 信号自动预测 AF 是可行的。所提出的用于自动预测 AF 的 CNN 模型可以成为医疗保健领域中 AF 早期诊断的有用工具。
