A deep neural network learning algorithm outperforms a conventional for algorithm for emergency department electrocardiogram interpretation

摘要

Background: Cardiologs has developed the first electrocardiogram (ECG) algorithm that uses a deep neural network (DNN) for full 12-lead ECG analysis, including rhythm, QRS and ST-T-U waves. We compared the accuracy of the first version of Cardiologs (R) DNN algorithm to the Mortara/Veritas (R) conventional algorithm in emergency department (ED) ECG5.