A novel hybrid CNN-transformer model using stockwell transform achieved an arrhythmia classification accuracy of 97.8% on the Icentia11k dataset and 99.58% on the MIT-BIH dataset.
A novel hybrid CNN-transformer model accurately classifies arrhythmias from ECG signals without requiring R-peak detection, achieving >97% accuracy on standard datasets.
This study presents a novel hybrid deep learning model for arrhythmia classification from electrocardiogram signals, utilizing the stockwell transform for feature extraction. As ECG signals are time-series data, they are transformed into the frequency domain to extract relevant features. Subsequently, a CNN is employed to capture local patterns, while a transformer architecture learns long-term dependencies. Unlike traditional CNN-based models that require R-peak detection, the proposed model operates without it and demonstrates superior accuracy and efficiency. The findings contribute to enhancing the accuracy of ECG-based arrhythmia diagnosis and are applicable to real-time monitoring systems. Specifically, the model achieves an accuracy of 97.8% on the Icentia11k dataset using four arrhythmia classes and 99.58% on the MIT-BIH dataset using five arrhythmia classes.
Kim et al. (2025) studied Arrhythmia. Hybrid CNN-transformer model using stockwell transform vs. Traditional CNN-based models requiring R-peak detection was evaluated on Accuracy of arrhythmia classification. A novel hybrid CNN-transformer model using stockwell transform achieved an arrhythmia classification accuracy of 97.8% on the Icentia11k dataset and 99.58% on the MIT-BIH dataset.