همایش بین المللی هوش مصنوعی

صفحه اصلی / اولین همایش بین المللی هوش مصنوعی

Early Detection of Congestive Heart Failure in Coronary Artery Disease Patients Using ECG Based Hybrid CNN-LSTM Model

نویسندگان :

Seyyed Ali Zendehbad¹ Farinaz Azari² Hadi Dehbovid³

1- Department of Biomedical Engineering Mashhad Branch, Islamic Azad University Mashhad, Iran. 2- Department of Electrical and Biomedical Engineering University College of Rouzbahan Sari, Iran 3- Department of Electrical Engineering Nour Branch, Islamic Azad University Nour, Iran.

کلمات کلیدی :

Convolutional Neural Network،Congestive Heart Failure،Electrocardiogram،Deep Learning،Long Short-Term Memory

چکیده :

The increasing prevalence of cardiovascular diseases and their associated high mortality rates necessitate the development of robust early detection methods to minimize adverse health outcomes and reduce treatment complications. Among various diagnostic tools, the Electrocardiogram (ECG) is one of the most accessible and cost-effective options. However, manual ECG interpretation is susceptible to human error and is often affected by noise and motion artifacts, making it a time-consuming and potentially unreliable process. Recent advancements in machine learning and deep learning have led to the emergence of automated models for ECG signal classification, significantly improving diagnostic accuracy and efficiency. In this study, we employed a combination of Long Short-Term Memory (LSTM) and Convolutional Neural Networks (CNN) to analyze three classes of ECG data from the PhysioNet database, comprising Congestive Heart Failure (CHF), arrhythmia, and normal sinus rhythm. The proposed hybrid model leverages the temporal sensitivity of LSTM and the spatial feature extraction capability of CNN, achieving a notable diagnostic accuracy of 87.20% for detecting coronary artery disease. The findings demonstrate that integrating LSTM and CNN is highly effective for modeling non-stationary and complex biological signals such as ECG, highlighting its potential for reliable and efficient early diagnosis of CHF.