Key result
Few-shot deep learning improves ECG classification accuracy to ~93% over standard softmax-based neural networks.
Why the study?
The study investigated the applicability of Few-Shot Learning for ECG signal proximity-based classification across different heart disease classes.
Does a Few-Shot Learning deep convolutional neural network improve 12-lead ECG heart disease classification accuracy compared to a standard softmax-based neural network on the PTB-XL dataset?
Does a Few-Shot Learning deep convolutional neural network improve 12-lead ECG heart disease classification accuracy compared to a standard softmax-based neural network on the PTB-XL dataset?
Few-Shot Learning neural networks combined with QRS extraction and SVM (RBF kernel) improve 2- and 5-class ECG disease classification over standard softmax networks and allow continuous online performance updates on standard CPUs without retraining network weights.
Answers are grounded in this paper and cite their sources.
May enhance ECG classification efficiency; leaves open prospective clinical validation before practice change.
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.
No takes yet. Share an insight, caveat, or question.
Pałczyński et al. (2022) studied Cardiovascular diseases classified via 12-lead ECG (normal ECG, myocardial infarction, ST/T change, conduction disturbance, hypertrophy) (n=17,232). Few-Shot Learning (FSL) deep convolutional neural network for ECG QRS-complex classification vs. Softmax-based deep convolutional neural network classification was evaluated on Classification accuracy for 2 heart disease classes (healthy vs sick patients). Few-Shot Learning deep convolutional neural networks achieved higher accuracy in classifying healthy versus sick ECGs compared to softmax-based networks.
Synapse has enriched 10 related papers. Consider them for comparative context: