Key result
A branch-reduced convolutional neural network detects AMI from single-lead ECGs with ~95% accuracy.
Why the study?
Myocardial infarction is life-threatening and requires accurate and rapid detection.
Does a branch-reduced convolutional neural network accurately detect and locate acute myocardial infarction using single-lead ECG signals?
Does a branch-reduced convolutional neural network accurately detect and locate acute myocardial infarction using single-lead ECG signals?
A compact branch-reduced convolutional neural network can accurately detect and localize acute myocardial infarction from single-lead ECGs, potentially enabling implementation on low-power handheld devices.
Answers are grounded in this paper and cite their sources.
Supports point-of-care AMI detection on low-power devices; extends compact CNN validation for single-lead ECG analysis.
Myocardial infarction can be life-threatening and needs to be detected accurately and quickly. In this paper, a branch-reduced network (BRN) is developed to detect and locate acute myocardial infarction (AMI) using single-lead electrocardiogram (ECG) signals and one-dimensional convolutional neural network. A grouping method for single-lead ECG signals is introduced to reduce the neural network size. A periodic feature-embedded convolutional block attention module is proposed to capture periodic features in the input ECG signals and improve AMI detection performance. The proposed model has achieved AMI detection sensitivity, specificity, and accuracy of 95.82%, 93.38%, and 95.16%, respectively. The AMI localization accuracy is 84.26%. The proposed model is of 28,863 trainable parameters, which is two orders of magnitude smaller than the number of trainable parameters in the related works. The compact network structure makes it possible to implement the proposed model on low-power handheld devices for emergency rooms, remote areas and developing countries.
No takes yet. Share an insight, caveat, or question.
Shen et al. (2025) studied Acute myocardial infarction. Branch-reduced network (BRN) using single-lead ECG was evaluated on AMI detection accuracy. A branch-reduced convolutional neural network using single-lead ECG signals achieved AMI detection sensitivity of 95.82%, specificity of 93.38%, and accuracy of 95.16% with 28,863 parameters.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: