Department of Cardiology, The Affiliated Wuxi People's Hospital of Nanjing Medical University, Wuxi, China.
Department of Cardiology, The First Affiliated Hospital of Nanjing Medical University, Nanjing, China.
J Cardiovasc Electrophysiol. 2021 Apr;32(4):1095-1102. doi: 10.1111/jce.14936. Epub 2021 Feb 15.
This study aims to develop an artificial intelligence-based method to screen patients with left ventricular ejection fraction (LVEF) of 50% or lesser using electrocardiogram (ECG) data alone.
Convolutional neural network (CNN) is a class of deep neural networks, which has been widely used in medical image recognition. We collected standard 12-lead ECG and transthoracic echocardiogram (TTE) data including the LVEF value. Then, we paired the ECG and TTE data from the same individual. For multiple ECG-TTE pairs from a single individual, only the earliest data pair was included. All the ECG-TTE pairs were randomly divided into the training, validation, or testing data set in a ratio of 9:1:1 to create or evaluate the CNN model. Finally, we assessed the screening performance by overall accuracy, sensitivity, specificity, positive predictive value, and negative predictive value.
We retrospectively enrolled a total of 26 786 ECG-TTE pairs and randomly divided them into training (n = 21 732), validation (n = 2 530), and testing data set (n = 2 530). In the testing set, the CNN algorithm showed an overall accuracy of 73.9%, sensitivity of 69.2%, specificity of 70.5%, positive predictive value of 70.1%, and negative predictive value of 69.9%.
Our results demonstrate that a well-trained CNN algorithm may be used as a low-cost and noninvasive method to identify patients with left ventricular dysfunction.
本研究旨在开发一种基于人工智能的方法，仅使用心电图（ECG）数据筛选左心室射血分数（LVEF）为 50%或更低的患者。
卷积神经网络（CNN）是一类深度学习网络，已广泛应用于医学图像识别。我们收集了标准的 12 导联心电图（ECG）和经胸超声心动图（TTE）数据，包括 LVEF 值。然后，我们将 ECG 和 TTE 数据来自同一患者进行配对。对于来自单个个体的多个 ECG-TTE 对，仅包括最早的数据对。所有 ECG-TTE 对被随机分为训练、验证或测试数据集，比例为 9:1:1，以创建或评估 CNN 模型。最后，我们通过总准确率、敏感性、特异性、阳性预测值和阴性预测值来评估筛选性能。
我们回顾性地纳入了总共 26786 对 ECG-TTE，并将其随机分为训练集（n=21732）、验证集（n=2530）和测试数据集（n=2530）。在测试集中，CNN 算法的总准确率为 73.9%，敏感性为 69.2%，特异性为 70.5%，阳性预测值为 70.1%，阴性预测值为 69.9%。
我们的研究结果表明，经过良好训练的 CNN 算法可作为一种低成本、非侵入性的方法来识别左心室功能障碍患者。
