Key result
Convolutional Neural Networks (CNN) are the most widely used method for ECG classification and generally obtain higher success rates than other classification approaches.
Why the study?
Analysis of the ECG signal has been of interest for more than a decade to build models for automatic ECG classification, motivating a review of recently used classification methods.
Convolutional Neural Networks (CNN) are the most widely used and successful methods for automatic ECG signal classification compared to other machine learning approaches.
CNNs merit prioritization in ECG AI research; leaves open prospective validation before any clinical adoption.
An electrocardiogram (ECG) signal is a recording of the electrical activity generated by the heart. The analysis of the ECG signal has been interested in more than a decade to build a model to make automatic ECG classification. The main goal of this work is to study and review an overview of utilizing the classification methods that have been recently used such as Artificial Neural Network, Convolution Neural Network (CNN), discrete wavelet transform, Support Vector Machine (SVM), and K-Nearest Neighbor. Efficient comparisons are shown in the result in terms of classification methods, features extraction technique, dataset, contribution, and some other aspects. The result also shows that the CNN has been most widely used for ECG classification as it can obtain a higher success rate than the rest of the classification approaches.
No takes yet. Share an insight, caveat, or question.
Abdulla et al. (2020) conducted a review in Arrhythmia / Electrocardiogram Signal Classification. Machine learning and deep learning algorithms (ANN, CNN, DWT, SVM, KNN) was evaluated. Convolutional Neural Networks (CNN) are the most widely used method for ECG classification and generally obtain higher success rates than other classification approaches.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: