Deep Learning-Based Identification of Echocardiographic Abnormalities From Electrocardiograms

Heart failure should be diagnosed as early as possible. Although deep learning models can predict one or more echocardiographic findings from electrocardiograms (ECGs), such analyses are not comprehensive.

This study aimed to develop a deep learning model for comprehensive prediction of echocardiographic findings from ECGs.

We obtained 229,439 paired ECG and echocardiography data sets from 8 centers. Six centers contributed to model development and 2 to external validation. We identified 12 echocardiographic findings related to left-sided cardiac abnormalities, valvular heart diseases, and right-sided cardiac abnormalities. These findings were predicted using convolutional neural networks, and a composite label was analyzed using logistic regression. A positive composite label indicated positivity in any of the 12 findings.

For the composite findings label, the area under the receiver-operating characteristic curve was 0.80 (95% CI: 0.80-0.81) on hold-out validation and 0.78 (95% CI: 0.78-0.79) on external validation. The composite findings label applying logistic regression had an area under the receiver-operating characteristic curve of 0.80 (95% CI: 0.80-0.81) with accuracy of 73.8% (95% CI: 73.2-74.4), sensitivity of 81.1% (95% CI: 80.5-81.8), and specificity of 60.7% (95% CI: 59.6-61.8).

We have developed convolutional neural network models that predict a wide range of echocardiographic findings, including left-sided cardiac abnormalities, valvular heart diseases, and right-sided cardiac abnormalities from ECGs and created a model to predict a composite findings label by logistic regression analysis. This model has potential to serve as an adjunct for early diagnosis and treatment of previously undetected cardiac disease.