Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Cardiologist-Level Arrhythmia Detection with Convolutional Neural Networks

Pranav Rajpurkar, Awni Y. Hannun, Masoumeh Haghpanahi, Codie Bourn, Andrew Y. Ng

TL;DR

The paper tackles automatic arrhythmia detection from single-lead ECGs in wearables by training a 34-layer residual CNN to map 30-second ECG segments to per-second rhythm labels across 14 classes. It leverages a large-scale, clinician-annotated dataset (≈64k records from ≈29k patients) and trains end-to-end, achieving cardiologist-level performance in both recall and precision on a medically annotated test set. The approach yields strong sequence- and set-level F1 scores and reveals realistic confusions aligned with waveform similarities. This work suggests scalable, high-accuracy ECG interpretation via wearables, with potential to augment or replace initial clinical assessments in resource-limited settings.

Abstract

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).

Cardiologist-Level Arrhythmia Detection with Convolutional Neural Networks

TL;DR

The paper tackles automatic arrhythmia detection from single-lead ECGs in wearables by training a 34-layer residual CNN to map 30-second ECG segments to per-second rhythm labels across 14 classes. It leverages a large-scale, clinician-annotated dataset (≈64k records from ≈29k patients) and trains end-to-end, achieving cardiologist-level performance in both recall and precision on a medically annotated test set. The approach yields strong sequence- and set-level F1 scores and reveals realistic confusions aligned with waveform similarities. This work suggests scalable, high-accuracy ECG interpretation via wearables, with potential to augment or replace initial clinical assessments in resource-limited settings.

Abstract

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).

Paper Structure

This paper contains 7 sections, 1 equation, 4 figures, 2 tables.

Table of Contents

  1. Introduction
  2. Model
  3. Data
  4. Results
  5. Analysis
  6. Related Work
  7. Conclusion

Figures (4)

  • Figure 1: Our trained convolutional neural network correctly detecting the sinus rhythm (SINUS) and Atrial Fibrillation (AFIB) from this ECG recorded with a single-lead wearable heart monitor.
  • Figure 2: The architecture of the network. The first and last layer are special-cased due to the pre-activation residual blocks. Overall, the network contains 33 layers of convolution followed by a fully-connected layer and a softmax.
  • Figure 3: Evaluated on the test set, the model outperforms the average cardiologist score on both the Sequence and the Set F1 metrics.
  • Figure 4: A confusion matrix for the model predictions on the test set. Many of the mistakes the model makes are not surprising. For example, confusing second degree AV Block (Type 2) with Wenckebach makes sense given the often similar expression of the two arrhythmias in the ECG record.