Key result
ECG-SMART-NET outperforms standard random forest in detecting OMI with ~0.95 AUC.
Why the study?
Two thirds of occlusion myocardial infarction cases are difficult to visually identify from a 12-lead ECG, and previous works on ECG detection of OMI are scarce.
Does the ECG-SMART-NET deep learning architecture improve the diagnostic identification of occlusion myocardial infarction on 12-lead ECGs compared to standard ResNet-18 models and state-of-the-art random forests in patients with chest pain?
Observational (n=7,397)
Yes
Does the ECG-SMART-NET deep learning architecture improve the diagnostic identification of occlusion myocardial infarction on 12-lead ECGs compared to standard ResNet-18 models and state-of-the-art random forests in patients with chest pain?
ECG-SMART-NET, a clinically informed deep learning architecture that assesses temporal then spatial ECG features, achieved superior diagnostic accuracy for detecting occlusion myocardial infarction compared to standard convolutional neural networks and state-of-the-art random forest models.
OBJECTIVE: In this paper we develop and evaluate ECG-SMART-NET for occlusion myocardial infarction (OMI) identification. OMI is a severe form of heart attack characterized by complete blockage of one or more coronary arteries requiring immediate referral for cardiac catheterization to restore blood flow to the heart. Two thirds of OMI cases are difficult to visually identify from a 12-lead electrocardiogram (ECG) and can be potentially fatal if not identified quickly. Previous works on this topic are scarce, and current state-of-the-art evidence suggests both feature-based random forests and convolutional neural networks (CNNs) are promising approaches to improve ECG detection of OMI. METHODS: While the ResNet architecture has been adapted for use with ECG recordings, it is not ideally suited to capture informative temporal features within each lead and the spatial concordance or discordance across leads. We propose a clinically informed modification of the ResNet-18 architecture. The model first learns temporal features through temporal convolutional layers with 1xk kernels followed by a spatial convolutional layer, after the residual blocks, with 12x1 kernels to learn spatial features. RESULTS: ECG-SMART-NET was benchmarked against the original ResNet-18 and other state-of-the-art models on a multisite real-word clinical dataset that consists of 10, 393 ECGs from 7, 397 unique patients (rate of OMI = 7.2%). ECG-SMART-NET outperformed other models in the classification of OMI with a test AUC of 0.953 [0.921, 0.978]. CONCLUSION AND SIGNIFICANCE: ECG-SMART-NET can outperform the state-of-the-art random forest for OMI prediction and is better suited for this task than the original ResNet-18 architecture.
No takes yet. Share an insight, caveat, or question.
Riek et al. (2025) conducted an observational in Occlusion Myocardial Infarction (n=7,397). ECG-SMART-NET vs. Random Forest was evaluated on Area under the receiver operating characteristics curve (AUC) for classifying Occlusion Myocardial Infarction on the test set (AUC 0.953, 95% CI 0.921-0.978). ECG-SMART-NET outperformed the state-of-the-art random forest model in the classification of occlusion myocardial infarction, achieving a test AUC of 0.953.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: