Detection of Myocardial Infarction Using Multi-Lead ECG and a Deep CNN Model

Le résumé fourni par la source

Myocardial infarction (MI), commonly known as heart attack, causes irreversible damage to cardiac muscle tissue, even culminating in death. Rapid and accurate identification of MI is crucial to avoid fatal outcomes. For acute diagnosis of MI, blood tests and evaluation of electrocardiographic (ECG) signals are used. However, a certain time lag is necessary for blood enzyme levels to show a significant increase after the attack, resulting in a delay in diagnosis. Therefore, manual ECG interpretation, although vital, is susceptible to variations among experienced observers.It is in this context that diagnostic assistance using computational systems presents itself as a valuable tool for the automatic detection of MI in ECG signals. In this study, we propose the implementation of a deep learning model with an end-to-end structure, applied to standard 12-lead ECG signals for MI diagnosis. To achieve this, convolutional neural network (CNN), a widely recognized technique in this area, is employed.The CNN model developed in this study, utilizing the specified architecture, achieved remarkable accuracy and sensitivity, surpassing 99.00% in diagnosing myocardial infarction (MI) across all ECG leads. This suggests that the proposed model holds substantial promise for high-performance MI detection, making it suitable for integration into portable medical devices and use in intensive care settings.

Ce résumé expose les affirmations des auteurs. BNTIC ne l’interprète pas comme une validation indépendante des résultats.