The heart disease detection and classification using the cost-effective tool electrocardiogram (ECG) becomes interesting research considering smart healthcare applications. Automation, accuracy, and robustness are vital demands for an ECG-based heart disease prediction system. Deep learning brings automation to the applications like Computer-Aided Diagnosis (CAD) systems with accuracy improvement compromising robustness. We propose the novel ECG-based heart disease prediction system using the hybrid mechanism to satisfy the automation, accuracy, and robustness requirements. We design the model via the steps of pre-processing, hybrid features formation, and classification. The ECG pre-processing is aiming at suppressing the baseline and powerline interference without loss of heartbeats. We propose a hybrid mechanism that consists of handcrafted and automatic Convolutional Neural Network (CNN) lightweight features for efficient classification. The hybrid feature vector is fed to the deep learning classifier Long Term Short Memory (LSTM) sequentially to predict the disease. The simulation results show that the proposed model reduces the diagnosis errors and time compare to state-of-art methods.
Automatic Heart Disease Classification Using Ensemble Features Extraction Mechanism from ECG Signals
