Key result
A deep learning model using ResNet18 for feature extraction and an optimized SVM for classification achieved 98.70% accuracy in detecting 16 types of cardiac arrhythmias from ECG beats.
Why the study?
Detecting ECG abnormalities plays a key role in monitoring, and deep neural networks trained on large datasets can detect cardiac arrhythmia to aid early treatment.
Absolute Event Rate: 98.7% vs 98.06%
A novel deep learning approach using ResNet18 for feature extraction and an optimized SVM classifier accurately detects and classifies 16 types of cardiac arrhythmias from ECG signals.
Proposed DL model for ECG arrhythmia detection is hypothesis-generating; leaves open clinical utility pending prospective validation.
Deep learning (DL) has become a topic of study in various applications, including healthcare. Detection of abnormalities in an electrocardiogram (ECG) plays a significant role in patient monitoring. It is noted that a deep neural network when trained on huge data, can easily detect cardiac arrhythmia. This may help cardiologists to start treatment as early as possible. This paper proposes a new deep learning model adapting the concept of transfer learning to extract deep-CNN features and facilitates automated classification of electrocardiogram (ECG) into sixteen types of ECG beats using an optimized support vector machine (SVM). The proposed strategy begins with gathering ECG datasets, removal of noise from ECG signals, and extracting beats from denoised ECG signals. Feature extraction is done using ResNet18 via concept of transfer learning. These extracted features are classified using optimized SVM. These methods are evaluated and tested on the MIT-BIH arrhythmia database. Our proposed model is effective compared to all State of Art Techniques with an accuracy of 98.70%.
No takes yet. Share an insight, caveat, or question.
Mohebbanaaz et al. (2021) studied Cardiac arrhythmia (n=45,943). ResNet18 with optimized SVM vs. Standard SVM and other state-of-the-art models was evaluated on Classification accuracy of 16 types of ECG beats. A deep learning model using ResNet18 for feature extraction and an optimized SVM for classification achieved 98.70% accuracy in detecting 16 types of cardiac arrhythmias from ECG beats.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: