Study of the Few-Shot Learning for ECG Classification Based on the PTB-XL Dataset

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.

ECG Classification Using Orthogonal Matching Pursuit and Machine Learning

“…The values of the ACC classification metric for grades 2 and 5 remain higher than the tests in the work [23,24], regardless of the approach used. In the case of the work [25], they remain lower. The obtained Accuracy results for the classification of two and five classes achieved an Accuracy of 0.9023 and 0.7766, respectively.…”

“…The authors often emphasized that data from single, small, or relatively homogeneous datasets, further limited by the small number of patients and rhythm, prevented the creation of reliable algorithms in Machine Learning models. To some extent, the PTB-XL database [21,22], for which multi-class classification work is already known [23][24][25], has become a solution to the problem of data inaccessibility.…”

Lightweight Multireceptive Field CNN for 12-Lead ECG Signal Classification

“…Based on the previous works of the literature on the PTB-XL dataset classification, we have tested our model under two scenarios. The first scenario is that classes with a sample number of less than 20 are removed from the dataset as is done in [ 45 – 47 ]. The second scenario is working on the whole dataset without removing any classes.…”

“…We have compared the performance of the proposed model under both scenarios with the existing model. Under the first case, the proposed model has a significant performance improvement compared to the architecture in [ 45 – 47 ] as portrayed in Tables 6 – 8 . The performance gain in evaluation metrics (accuracy, precision, recall, F 1 score, and AUC) is significant, and the proposed model has fewer parameter numbers.…”

“…They also claim that adding QRX complexes features extracted from the signal substantially enhances performance in the study they carried out in paper [ 46 ]. The authors in [ 47 ] proposed a neural network trained for conducting Few-Shot Learning (FSL) classification and proved that FSL-based classification is more accurate than the softmax-based classification. The authors in [ 48 ] tried to address the challenges of cross-institutional algorithm evaluation using transfer learning and frequency domain CNN.…”