PDF(Pubmed)
Abstract：
UNASSIGNED: Accurately determining arrhythmia mechanism from a 12-lead electrocardiogram (ECG) of supraventricular tachycardia can be challenging. We hypothesized a convolutional neural network (CNN) can be trained to classify atrioventricular re-entrant tachycardia (AVRT) vs atrioventricular nodal re-entrant tachycardia (AVNRT) from the 12-lead ECG, when using findings from the invasive electrophysiology (EP) study as the gold standard.
UNASSIGNED: We trained a CNN on data from 124 patients undergoing EP studies with a final diagnosis of AVRT or AVNRT. A total of 4962 5-second 12-lead ECG segments were used for training. Each case was labeled AVRT or AVNRT based on the findings of the EP study. The model performance was evaluated against a hold-out test set of 31 patients and compared to an existing manual algorithm.
UNASSIGNED: The model had an accuracy of 77.4% in distinguishing between AVRT and AVNRT. The area under the receiver operating characteristic curve was 0.80. In comparison, the existing manual algorithm achieved an accuracy of 67.7% on the same test set. Saliency mapping demonstrated the network used the expected sections of the ECGs for diagnoses; these were the QRS complexes that may contain retrograde P waves.
UNASSIGNED: We describe the first neural network trained to differentiate AVRT from AVNRT. Accurate diagnosis of arrhythmia mechanism from a 12-lead ECG could aid preprocedural counseling, consent, and procedure planning. The current accuracy from our neural network is modest but may be improved with a larger training dataset.
UNASSIGNED: We trained a CNN on data from 124 patients undergoing EP studies with a final diagnosis of AVRT or AVNRT. A total of 4962 5-second 12-lead ECG segments were used for training. Each case was labeled AVRT or AVNRT based on the findings of the EP study. The model performance was evaluated against a hold-out test set of 31 patients and compared to an existing manual algorithm.
UNASSIGNED: The model had an accuracy of 77.4% in distinguishing between AVRT and AVNRT. The area under the receiver operating characteristic curve was 0.80. In comparison, the existing manual algorithm achieved an accuracy of 67.7% on the same test set. Saliency mapping demonstrated the network used the expected sections of the ECGs for diagnoses; these were the QRS complexes that may contain retrograde P waves.
UNASSIGNED: We describe the first neural network trained to differentiate AVRT from AVNRT. Accurate diagnosis of arrhythmia mechanism from a 12-lead ECG could aid preprocedural counseling, consent, and procedure planning. The current accuracy from our neural network is modest but may be improved with a larger training dataset.
摘要：
■从室上性心动过速的12导联心电图（ECG）中准确确定心律失常机制可能具有挑战性。我们假设卷积神经网络（CNN）可以通过12导联ECG对房室折返性心动过速（AVRT）和房室结折返性心动过速（AVNRT）进行分类，当使用侵入性电生理学（EP）研究的结果作为金标准时。
■我们对来自124例接受EP研究并最终诊断为AVRT或AVNRT的患者的数据进行了CNN训练。总共使用4962个5秒12导联ECG段进行训练。根据EP研究结果，每例均标记为AVRT或AVNRT。针对31名患者的保持测试集评估了模型性能，并与现有的手动算法进行了比较。
■该模型在区分AVRT和AVNRT方面的准确率为77.4%。接收器工作特性曲线下的面积为0.80。相比之下,现有的手动算法在同一测试集上达到了67.7%的准确率。显著性映射表明网络使用ECG的预期部分进行诊断；这些是可能包含逆行P波的QRS复合波。
■我们描述了第一个训练来区分AVRT和AVNRT的神经网络。12导联心电图对心律失常机制的准确诊断可以帮助术前咨询，同意,和程序规划。我们的神经网络目前的精度是适度的，但可以通过更大的训练数据集来提高。
■我们对来自124例接受EP研究并最终诊断为AVRT或AVNRT的患者的数据进行了CNN训练。总共使用4962个5秒12导联ECG段进行训练。根据EP研究结果，每例均标记为AVRT或AVNRT。针对31名患者的保持测试集评估了模型性能，并与现有的手动算法进行了比较。
■该模型在区分AVRT和AVNRT方面的准确率为77.4%。接收器工作特性曲线下的面积为0.80。相比之下,现有的手动算法在同一测试集上达到了67.7%的准确率。显著性映射表明网络使用ECG的预期部分进行诊断；这些是可能包含逆行P波的QRS复合波。
■我们描述了第一个训练来区分AVRT和AVNRT的神经网络。12导联心电图对心律失常机制的准确诊断可以帮助术前咨询，同意,和程序规划。我们的神经网络目前的精度是适度的，但可以通过更大的训练数据集来提高。
