January 29, 2022Neural Computing and Applications69 citationsOpen Access

Automated ECG multi-class classification system based on combining deep learning features with HRV and ECG measures

AEAhmed S. EltrassAlexandria University MTMazhar B. TayelAlexandria University AAAbeer I. AmmarAlexandria University

Structured PICO

Does a hybrid deep learning system combining ECG and HRV features improve the classification accuracy of congestive heart failure, arrhythmia, and normal sinus rhythm?

Population

Real ECG data from well-known databases representing congestive heart failure, arrhythmia, and normal sinus rhythm (NSR).

Intervention

Hybrid deep neural network (AlexNet) combined with linear and nonlinear features extracted from ECG and HRV using chaos theory, fragmentation analysis, and constant-Q non-stationary Gabor transform.

Comparator

Other recent state-of-the-art ECG classification systems.

Outcome

Classification accuracy, specificity, sensitivity, and computational time.surrogate

A novel hybrid deep learning and feature extraction system achieves high accuracy (98.75%) in classifying ECGs into congestive heart failure, arrhythmia, and normal sinus rhythm, potentially assisting real-time clinical diagnosis.

Abstract

Abstract Electrocardiogram (ECG) serves as the gold standard for noninvasive diagnosis of several types of heart disorders. In this study, a novel hybrid approach of deep neural network combined with linear and nonlinear features extracted from ECG and heart rate variability (HRV) is proposed for ECG multi-class classification. The proposed system enhances the ECG diagnosis performance by combining optimized deep learning features with an effective aggregation of ECG features and HRV measures using chaos theory and fragmentation analysis. The constant-Q non-stationary Gabor transform technique is employed to convert the 1-D ECG signal into 2-D image which is sent to a pre-trained convolutional neural network structure, called AlexNet. The pair-wise feature proximity algorithm is employed to select the optimal features from the AlexNet output feature vector to be concatenated with the ECG and HRV measures. The concatenated features are sent to different types of classifiers to distinguish three distinct subjects, namely congestive heart failure, arrhythmia, and normal sinus rhythm (NSR). The results reveal that the linear discriminant analysis classifier has the highest accuracy compared to the other classifiers. The proposed system is investigated with real ECG data taken from well-known databases, and the experimental results show that the proposed diagnosis system outperforms other recent state-of-the-art systems in terms of accuracy 98.75%, specificity 99.00%, sensitivity of 98.18%, and computational time 0.15 s. This demonstrates that the proposed system can be used to assist cardiologists in enhancing the accuracy of ECG diagnosis in real-time clinical setting.

Ask AI

Helpful

Bookmark

View Full Paper