ECG-SMART-NET: A Deep Learning Architecture for Precise ECG Diagnosis of Occlusion Myocardial Infarction

2024-05-08

IEEE transactions on bio-medical engineering

AI Summary

Obstructive myocardial infarction (OMI) is frequently missed on 12-lead electrocardiograms (ECGs), with visual detection rates as low as ~33%, leading to high mortality. To address this clinical challenge, we propose a clinically inspired temporal-spatial decoupled convolutional deep learning model: temporal features are extracted via 1×k convolutions applied independently to each lead, followed by 12×1 spatial convolutions to capture inter-lead covariation; the architecture integrates residual connections based on ResNet-18. This design overcomes the limitation of conventional CNNs that jointly model temporal and spatial dimensions. Evaluated on a large multicenter real-world clinical dataset comprising 10,393 ECGs, our model achieves an AUC of 0.953—significantly outperforming standard ResNet-18 and state-of-the-art methods including random forests—demonstrating substantial improvements in both accuracy and robustness for automated OMI detection.

Technology Category

• Computer Vision: Multi-modal Vision
• Machine Learning: Multimodal Learning
• Data Mining & Knowledge Management: Mining of Spatial, Temporal or Spatio-Temporal Data

Application Category

• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs
• Responsible Web: Machine-in-the-loop, human agency and autonomy
• User Modeling, Personalization and Recommendation: Explainable and interpretable methods for personalization

Abstract

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.

Problem

• Develop deep learning for precise ECG OMI diagnosis
• Improve detection of visually elusive occlusion myocardial infarction
• Enhance temporal and spatial feature capture in ECGs

Innovation

• Deep learning for ECG diagnosis
• Modified ResNet-18 with temporal layers
• Spatial convolutional layer post residual blocks