ECG-WMA-Net detected cardiac wall motion abnormalities from 12-lead ECGs with an AUROC of 0.781, significantly outperforming expert physician interpretation and quantitative Q-wave indices.
Observational (n=37,548)
Yes
Does a deep neural network (ECG-WMA-Net) improve the detection of cardiac wall motion abnormalities from ECGs compared to expert interpretation and Q-wave indices?
A deep learning model applied to standard ECGs can detect echocardiographic wall motion abnormalities more accurately than expert interpretation or traditional Q-wave criteria.
Effect estimate: AUROC 0.781 (95% CI 0.762-0.799)
Absolute Event Rate: 0.781% vs 0.571%
p-value: p=<0.0001
Cardiac wall motion abnormalities (WMA) are strong predictors of mortality, but current screening methods using Q waves from electrocardiograms (ECGs) have limited accuracy and vary across racial and ethnic groups. This study aimed to identify novel ECG features using deep learning to enhance WMA detection, referencing echocardiography as the gold standard. We collected ECG and echocardiogram data from 35,210 patients in California and labeled WMA using unstructured language parsing of echocardiographic reports. A deep neural network (ECG-WMA-Net) was trained and outperformed both expert ECG interpretation and Q-wave indices, achieving an AUROC of 0.781 (CI: 0.762-0.799). The model was externally validated in a diverse cohort from Georgia (n = 2338), with an AUC of 0.723 (CI: 0.685-0.757). Explainability analysis revealed significant contributions from QRS and T-wave regions. This deep learning approach improves WMA screening accuracy, potentially addressing physiological differences not captured by standard ECG-based methods.
Rogers et al. (Sat,) conducted a observational in Cardiac wall motion abnormalities (n=37,548). ECG-WMA-Net (deep neural network) vs. Qualitative expert ECG interpretation and quantitative ECG indices was evaluated on Detection of cardiac wall motion abnormalities (AUROC) (AUROC 0.781, 95% CI 0.762-0.799, p=<0.0001). ECG-WMA-Net detected cardiac wall motion abnormalities from 12-lead ECGs with an AUROC of 0.781, significantly outperforming expert physician interpretation and quantitative Q-wave indices.