Computerized electrocardiogram (ECG) interpretation plays a critical role in the clinical ECG workflow1. Widely available digital ECG data and the algorithmic paradigm of deep learning2 present an opportunity to substantially improve the accuracy and scalability of automated ECG analysis. However, a comprehensive evaluation of an end-to-end deep learning approach for ECG analysis across a wide variety of diagnostic classes has not been previously reported. Here, we develop a deep neural network (DNN) to classify 12 rhythm classes using 91,232 single-lead ECGs from 53,549 patients who used a single-lead ambulatory ECG monitoring device. When validated against an independent test dataset annotated by a consensus committee of board-certified practicing cardiologists, the DNN achieved an average area under the receiver operating characteristic curve (ROC) of 0.97. The average F1 score, which is the harmonic mean of the positive predictive value and sensitivity, for the DNN (0.837) exceeded that of average cardiologists (0.780). With specificity fixed at the average specificity achieved by cardiologists, the sensitivity of the DNN exceeded the average cardiologist sensitivity for all rhythm classes. These findings demonstrate that an end-to-end deep learning approach can classify a broad range of distinct arrhythmias from single-lead ECGs with high diagnostic performance similar to that of cardiologists. If confirmed in clinical settings, this approach could reduce the rate of misdiagnosed computerized ECG interpretations and improve the efficiency of expert human ECG interpretation by accurately triaging or prioritizing the most urgent conditions.

Rent or Buy article

Get time limited or full article access on ReadCube.


All prices are NET prices.

The test dataset used to support the findings of this study is publicly available at without restriction. Restrictions apply to the availability of the training dataset, which was used under license from iRhythm Technologies, Inc. for the current study. iRhythm Technologies, Inc. will consider requests to access the training data on an individual basis. Any data use will be restricted to noncommercial research purposes, and the data will only be made available on execution of appropriate data use agreements.

iRhythm Technologies, Inc. provided financial support for the data annotation in this work. M.H. and C.B. are employees of iRhythm Technologies, Inc. A.Y.H. was funded by an NVIDIA fellowship. G.H.T. received support from the National Institutes of Health (K23 HL135274). The only financial support provided by iRhythm Technologies, Inc. for this study was for the data annotation. Data analysis and interpretation was performed independently from the sponsor. The corresponding author had full access to all the data in the study and had final responsibility for the decision to submit for publication.

  • Nature Medicine (2019)