An Efficient and Automatic ECG Arrhythmia Diagnosis System using DWT and HOS Features and Entropy- Based Feature...

Area of Science:

• Cardiology
• Biomedical Engineering
• Signal Processing

Background:

• Early detection of heart disease is crucial for reducing cardiac patient mortality.
• Subtle changes in electrocardiogram (ECG) signals indicating abnormalities are difficult to detect visually.
• Computer-aided diagnosis (CAD) systems offer a promising approach to enhance diagnostic accuracy.

Purpose of the Study:

• To propose an efficient computer-aided diagnosis (CAD) approach for ECG arrhythmia detection.
• To improve the accuracy and reliability of identifying different classes of heartbeats.
• To reduce the fatality rate among cardiac patients through advanced diagnostic tools.

Main Methods:

• Feature extraction using Discrete Wavelet Transform (DWT) and Higher-Order Statistics (HOS).
• Feature selection employing entropy-based methods.
• Classification of five heartbeat categories using Neural Networks (NN) and Support Vector Machines (SVM).

Main Results:

• The proposed system achieved high classification accuracy for arrhythmia classes.
• Neural Network (NN) classification accuracy reached 99.83%.
• Support Vector Machine (SVM) classification accuracy reached 99.03%.

Conclusions:

• The developed CAD system demonstrates superior performance in ECG arrhythmia diagnosis compared to existing methods.
• The combination of DWT, HOS, and entropy-based feature selection proves effective for accurate heart abnormality detection.
• This approach holds significant potential for clinical application in cardiac patient management.