Key result
ECG preprocessing with noise reduction and pulse segmentation boosts CNN-based STEMI detection AUC to ~0.94.
Why the study?
Prompt diagnosis of STEMI is crucial within the golden time, but accuracy of STEMI diagnosis by ECG among physicians and paramedics is not sufficient.
Does a preprocessing technique improve the diagnostic performance of a CNN-based algorithm for detecting STEMI on 12-lead ECG?
Does a preprocessing technique improve the diagnostic performance of a CNN-based algorithm for detecting STEMI on 12-lead ECG?
Applying noise reduction and pulse segmentation preprocessing significantly enhances the accuracy of CNN-based STEMI detection on 12-lead ECGs.
Answers are grounded in this paper and cite their sources.
May enhance CNN-based STEMI detection on ECGs; hypothesis-generating and requires prospective validation before clinical use.
ST elevation myocardial infarction (STEMI) is an acute life-threatening disease. It shows a high mortality risk when a patient is not timely treated within the golden time, prompt diagnosis with limited information such as electrocardiogram (ECG) is crucial. However, previous studies among physicians and paramedics have shown that the accuracy of STEMI diagnosis by the ECG is not sufficient. Thus, we propose a detecting algorithm based on a convolutional neural network (CNN) for detecting the STEMI on 12-lead ECG in order to support physicians, especially in an emergency room. We mostly focus on enhancing the detecting performance using a preprocessing technique. First, we reduce the noise of ECG using a notch filter and high-pass filter. We also segment pulses from ECG to focus on the ST segment. We use 96 normal and 179 STEMI records provided by Seoul National University Bundang Hospital (SNUBH) for the experiment. The sensitivity, specificity, and area under the curve (AUC) of the receiver operating characteristic (ROC) curve are increased from 0.685, 0.350, and 0.526 to 0.932, 0.896, and 0.943, respectively, depending on the preprocessing technique. As our result shows, the proposed method is effective to enhance STEIM detecting performance. Also, the proposed algorithm would be expected to help timely and the accurate diagnosis of STEMI in clinical practices.
No takes yet. Share an insight, caveat, or question.
Park et al. (2019) studied ST elevation myocardial infarction (STEMI) (n=275). Preprocessing technique (noise reduction and pulse segmentation) prior to CNN vs. Raw ECG data without preprocessing was evaluated on Area under the ROC curve (AUC) for STEMI detection. Applying noise reduction and pulse segmentation preprocessing techniques to 12-lead ECGs increased the sensitivity, specificity, and AUC of a CNN-based STEMI detection model from 0.685, 0.350, and 0.526 to 0.932, 0.896, and 0.943, respectively.
Synapse has enriched 10 related papers. Consider them for comparative context: