Key result
A 34-layer neural network outperforms 6 board-certified cardiologists in detecting arrhythmias from single-lead wearable ECGs.
Why the study?
Does a 34-layer convolutional neural network improve arrhythmia detection from single-lead wearable monitor ECGs compared to individual board-certified cardiologists?
Population
Electrocardiograms recorded with a single-lead wearable monitor from a large dataset of unique patients
Comparison
34-layer convolutional neural network algorithm… vs 6 individual board-certified cardiologists
Design
Other
Authors
Loading...
May augment single-lead wearable arrhythmia detection beyond average cardiologist review; leaves open prospective validation and clinical integration.
Does a 34-layer convolutional neural network improve arrhythmia detection from single-lead wearable monitor ECGs compared to individual board-certified cardiologists?
A deep learning algorithm can detect a wide range of arrhythmias from single-lead ECGs with higher sensitivity and precision than average board-certified cardiologists.
Rajpurkar et al. (2017) studied Heart arrhythmias. 34-layer convolutional neural network vs. 6 individual board-certified cardiologists was evaluated on Recall (sensitivity) and precision (positive predictive value) for detecting heart arrhythmias. A 34-layer convolutional neural network exceeded the average performance of 6 board-certified cardiologists in both recall and precision for detecting arrhythmias from single-lead wearable ECGs.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: