Abstract
The electrocardiogram (ECG) is considered a fundamental of cardiology. The ECG consists of P, QRS, and T waves. Information provided from the signal based on the intervals and amplitudes of these waves is associated with various heart diseases. The first step in isolating the features of an ECG begins with the accurate detection of the R-peaks in the QRS complex. The database was based on the PTB-XL database, and the signals from Lead I–XII were analyzed. This research focuses on determining the Few-Shot Learning (FSL) applicability for ECG signal proximity-based classification. The study was conducted by training Deep Convolutional Neural Networks to recognize 2, 5, and 20 different heart disease classes. The results of the FSL network were compared with the evaluation score of the neural network performing softmax-based classification. The neural network proposed for this task interprets a set of QRS complexes extracted from ECG signals. The FSL network proved to have higher accuracy in classifying healthy/sick patients ranging from 93.2% to 89.2% than the softmax-based classification network, which achieved 90.5–89.2% accuracy. The proposed network also achieved better results in classifying five different disease classes than softmax-based counterparts with an accuracy of 80.2–77.9% as opposed to 77.1% to 75.1%. In addition, the method of R-peaks labeling and QRS complexes extraction has been implemented. This procedure converts a 12-lead signal into a set of R waves by using the detection algorithms and the k-mean algorithm.
Highlights
Machine learning, especially Deep Learning (DL) approaches, has been of interest in academia and industry
Classification using DL methods [4] have several practical applications in various areas of medicine, such as the diagnosis of diseases based on physiological parameters [5], the classification of cardiac arrhythmias based on ECG signals [6,7], and the recognition of human activity [8]
The methodology used in the paper was as follows (Figure 2): The PTB-XL dataset containing the labeled 10-second raw-signal ECG was used for the research
Summary
Especially Deep Learning (DL) approaches, has been of interest in academia and industry. This has resulted in numerous changes in the approach to automatic detection or classification processes. Classification using DL methods [4] have several practical applications in various areas of medicine, such as the diagnosis of diseases based on physiological parameters [5], the classification of cardiac arrhythmias based on ECG signals [6,7], and the recognition of human activity [8]. Various ECG classification schemes based on DL were used to detect heart diseases [9,10,11,12], for example, using Long Short-Term Memory networks [13] and onedimensional Convolution Neural Networks [14,15,16]. DL methods have been used to classify pathological conditions of the heart, such as arrhythmia, atrial fibrillation, ventricular fibrillation, and others
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
