Optimizing Myocardial Infarction Detection: A Hybrid CNN-GRU Deep Learning Approach

Read the full article See related articles

Listed in

This article is not in any list yet, why not save it to one of your lists.
Log in to save this article

Abstract

Background Myocardial infarction (MI) is a life-threatening condition characterized by the abrupt interruption of blood supply to the heart, often due to thrombosis. Diagnosing MI can be challenging, and delayed or incorrect diagnosis is a significant problem that healthcare providers face regularly. The primary and crucial method for detecting MI is electrocardiogram (ECG). This study aimed to optimize MI detection by developing a hybrid CNN-GRU Deep Learning model (DLM) based on ECG as a diagnostic support tool. Methods This retrospective diagnostic study included a total of 56354 ECGs, comprising 41871 from patients diagnosed with (MI) and 14474 from healthy patients. The CNN-GRU model was trained on 85% of these ECGs and validated on the remaining 15%. The CNN-GRU model was executed on the pre-processed data using the Pan-Tompkins algorithm obtained from the PhysioNet website (PTB). Multiple studies have focused on the precise classification of heartbeats and many deep neural networks have been proposed to enhance accuracy and simplify the model further. We examined a new model for classifying ECG heartbeats and found that it can compete with advanced models. The performance of the DLM was evaluated using the area under the receiver operating characteristic curve (AUC), sensitivity, specificity, Macro Average, and Weighted Average. Results The area under the receiver operating characteristic curve (AUC) of the CNN-GRU model for MI detection was close to one. Furthermore, the CNN-GRU model independently demonstrated sufficient diagnostic capacity for MI using 15 leads (ACC = 99.43%; sensitivity = 99.71%; specificity = 98.59%; the macro-averaged precision, and F1-score were 99.15%, and 99.24%, indicating the excellent performance of the model on both classes; The weighted average of precision, and F1-score was also 99.42%, confirming the overall high performance of the model). In addition, the performance of the model when using lead II was equal (ACC = 99.73%, sensitivity = 99.75%, specificity = 99.66%; the macro-averaged precision, and F1-score were 99.71%, and 99.65%, The weighted average of precision, and F1-score was also 99.73%,). Based on the reported results, the CNN-GRU model using lead II was the best model. Conclusions The suggested model can function as a prompt, impartial, and precise diagnostic decision support tool to aid emergency medical system networks and frontline clinicians in identifying myocardial infarction, thus facilitating the initiation of reperfusion therapy.

Article activity feed