Key result
Deep learning support boosts cardiologists' ECG diagnostic accuracy for LV dysfunction to ~88%.
Why the study?
It was hypothesized that applying a deep learning model to electrocardiograms may improve the diagnostic accuracy of cardiologists in predicting left ventricular dysfunction.
Does deep learning model support improve the diagnostic accuracy of cardiologists in predicting left ventricular dysfunction from ECGs?
Cross-Sectional (n=37,103)
Does deep learning model support improve the diagnostic accuracy of cardiologists in predicting left ventricular dysfunction from ECGs?
Deep learning model support significantly improves cardiologists' accuracy in detecting left ventricular systolic dysfunction (LVEF < 40%) from standard ECGs.
Answers are grounded in this paper and cite their sources.
May aid cardiologist ECG interpretation for LV dysfunction; hypothesis-generating and requires prospective validation before adoption.
Deep learning models can be applied to electrocardiograms (ECGs) to detect left ventricular (LV) dysfunction. We hypothesized that applying a deep learning model may improve the diagnostic accuracy of cardiologists in predicting LV dysfunction from ECGs. We acquired 37,103 paired ECG and echocardiography data records of patients who underwent echocardiography between January 2015 and December 2019. We trained a convolutional neural network to identify the data records of patients with LV dysfunction (ejection fraction < 40%) using a dataset of 23,801 ECGs. When tested on an independent set of 7,196 ECGs, we found the area under the receiver operating characteristic curve was 0.945 (95% confidence interval: 0.936-0.954). When 7 cardiologists interpreted 50 randomly selected ECGs from the test dataset of 7,196 ECGs, their accuracy for predicting LV dysfunction was 78.0% ± 6.0%. By referring to the model's output, the cardiologist accuracy improved to 88.0% ± 3.7%, which indicates that model support significantly improved the cardiologist diagnostic accuracy (P = 0.02). A sensitivity map demonstrated that the model focused on the QRS complex when detecting LV dysfunction on ECGs. We developed a deep learning model that can detect LV dysfunction on ECGs with high accuracy. Furthermore, we demonstrated that support from a deep learning model can help cardiologists to identify LV dysfunction on ECGs.
No takes yet. Share an insight, caveat, or question.
Katsushika et al. (2021) conducted a cross-sectional in Left ventricular systolic dysfunction (n=37,103). Deep learning model support vs. Cardiologist interpretation without model support was evaluated on Diagnostic accuracy for predicting left ventricular dysfunction (p=0.02). Support from a deep learning model improved the diagnostic accuracy of cardiologists in predicting left ventricular dysfunction from ECGs from 78.0% to 88.0%.
Synapse has enriched 10 related papers. Consider them for comparative context: