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?
Population
37,103 paired ECG and echocardiography records of patients who underwent echocardiography
Comparison
Cardiologist interpretation with deep learning model support vs without model support
Design
Diagnostic model development and validation study with reader sub-study
Authors
Loading...
May aid cardiologist ECG interpretation for LV dysfunction; hypothesis-generating and requires prospective validation before adoption.
Cross-Sectional (n=37,103)
Does deep learning model support improve the diagnostic accuracy of cardiologists in predicting left ventricular dysfunction from ECGs?
Absolute Event Rate: 88% vs 78%
p-value: p=0.02
Deep learning model support significantly improves cardiologists' accuracy in detecting left ventricular systolic dysfunction (LVEF < 40%) from standard ECGs.
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 significantly improved the diagnostic accuracy of cardiologists in predicting left ventricular dysfunction from ECGs from 78.0% to 88.0% (P = 0.02).
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: