A Hybrid Reinforcement and Deep Learning Framework for ECG and PCG Based Cardiovascular Signal Classification

Abstract

This study presents an innovative approach that combines Deep Reinforcement Learning with machine learning techniques to classify cardiovascular disease conditions using ECG and PCG signals from the EPNOGRAM dataset. The core aim is to boost classification accuracy by leveraging Deep Reinforcement Learning(DRL) for enhanced feature extraction, which is then fed into conventional models like CNN, RNN, LSTM, BiLSTM, and hybrid architectures such as CNN-RNN and LSTM &BiLSTM. Experimental results reveal notable performance gains when Deep Reinforcement Learning(DRL) is integrated. Specifically, the CNN-RNN hybrid achieved 90% accuracy, 89% precision, 88% recall, 88% F1-score, and a 92% AUC-ROC. The LSTM-BiLSTM hybrid outperformed with 92% accuracy, 91% precision, 90% recall, and 90% F1-score, and a 94% AUC. These findings highlight the effectiveness of merging Deep Reinforcement Learning(DRL) with supervised models, particularly in addressing the complexity of cardiopulmonary signal classification, and demonstrate the superior performance of hybrid models over standard classifiers in both accuracy and interpretability.