Key result
Novel 2D-CNN model detects STEMI from 12-lead ECG images with ~96% accuracy, outperforming transfer learning.
Why the study?
The accuracy of STEMI diagnosis by 12-lead ECG among physicians and paramedics is not sufficient, motivating development of improved detection methods.
Does a 2D-CNN model accurately detect and localize STEMI on 12-lead ECG images compared to transfer learning models?
Does a 2D-CNN model accurately detect and localize STEMI on 12-lead ECG images compared to transfer learning models?
A novel 2D-CNN model demonstrated high accuracy and interpretability for detecting and localizing STEMI on 12-lead ECG images.
Answers are grounded in this paper and cite their sources.
May support automated STEMI detection on ECG images; leaves open need for prospective clinical validation.
STEMI is the most severe type of Myocardial Infarction that causes death or disability. Previous studies among physicians and paramedics have shown that the accuracy of STEMI diagnosis by the 12-lead ECG is not sufficient. Thus, we propose a 2D-CNN model that can detect and locate the STEMI signals from 12-lead ECG images. The 2D-CNN model is trained as a binary classification with 540 ECG images (270 STEMI cases and 270 other ECG images), and it achieved 96.3% accuracy, 96.2% sensitivity, 89.4% precision, 0.926 F1-score, and 0.962 ROC-AUC scores for 537 testing images. The proposed model is compared with 10 different transfer learning models. The proposed model has the best accuracy, sensitivity, F1-score, and ROC-AUC score. Grad-CAM technique is used for localization of STEMI signals in ECG images. According to the comparisons, the proposed model is the most reliable one for localizing the STEMI signals. This localization builds trust for the model because the CNN model is not a black box anymore, we can see where the CNN model looks and decides. The result of localization can also be used for teaching inexperienced physicians and paramedics. Also, the proposed model can be helpful for the accurate diagnosis of STEMI with a quick response time for clinical practices.
No takes yet. Share an insight, caveat, or question.
Kavak et al. (2022) studied ST-Elevation Myocardial Infarction (STEMI) (n=1,137). 2D-CNN model vs. Transfer learning models was evaluated on Accuracy of STEMI detection on the testing dataset. The proposed 2D-CNN model achieved 96.3% accuracy, 96.2% sensitivity, and a 0.962 ROC-AUC score for detecting STEMI from 12-lead ECG images, outperforming 10 transfer learning models.
Synapse has enriched 10 related papers. Consider them for comparative context: