HYBRID CNN-LSTM MODEL FOR AUTOMATED ECG-BASEDARRHYTHMIA CLASSIFICATION

Abstract

Electrocardiogram (ECG) signals are critical for detecting cardiac arrhythmias, which are irregular heart rhythms that can lead to severe cardiovascular diseases. Traditional manual analysis of ECG signals is time-consuming and prone to human error. This research proposes a hybrid deep learning approach combining Convolutional Neural Networks (CNN) and Long Short-Term Memory (LSTM) networks for automated arrhythmia classification. The CNN layers extract spatial features from ECG waveforms, while the LSTM layers capture temporal dependencies, enabling precise detection of various arrhythmia types. The model is trained and validated on publicly available ECG datasets, such as the MIT-BIH Arrhythmia Database. Performance metrics including accuracy, sensitivity, specificity, and F1-score are evaluated. Experimental results show that the hybrid model outperforms traditional machine learning and standalone deep learning methods. This approach facilitates realtime, automated arrhythmia detection, reduces diagnostic time, and supports remote patient monitoring. The proposed system offers a scalable, robust, and energy-efficient solution for intelligent cardiac healthcare.