We develop an algorithm which exceeds the performance of board certified cardiologists in detecting a wide range of heart arrhythmias from electrocardiograms recorded with a single-lead wearable monitor. We build a dataset with more than 500 times the number of unique patients than previously studied corpora. On this dataset, we train a 34-layer convolutional neural network which maps a sequence of ECG samples to a sequence of rhythm classes. Committees of board-certified cardiologists annotate a gold standard test set on which we compare the performance of our model to that of 6 other individual cardiologists. We exceed the average cardiologist performance in both recall (sensitivity) and precision (positive predictive value).
@article{arxiv.1707.01836,
title = {Cardiologist-Level Arrhythmia Detection with Convolutional Neural Networks},
author = {Pranav Rajpurkar and Awni Y. Hannun and Masoumeh Haghpanahi and Codie Bourn and Andrew Y. Ng},
journal= {arXiv preprint arXiv:1707.01836},
year = {2017}
}