Key result
An arrhythmia detection algorithm based on a Convolutional Neural Network and Squeeze-and-Excitation module achieved an overall classification accuracy of 99.53% on the MIT-BIH database.
Why the study?
ECG is significant for clinical diagnosis of arrhythmias, but further improvement in ECG signal classification performance was needed.
Does an SE-CNN algorithm improve the classification accuracy of arrhythmias from ECG signals?
Does an SE-CNN algorithm improve the classification accuracy of arrhythmias from ECG signals?
An SE-CNN algorithm achieved 99.53% accuracy in classifying eight heart rhythm classes from the MIT-BIH database, demonstrating potential for automated ECG interpretation.
High benchmark accuracy supports further model refinement; leaves open clinical utility in real-world ECG interpretation.
Cardiovascular disease is a serious threat to human health. Electrocardiogram (ECG) is of great significance in clinical diagnosis and follow-up treatment of arrhythmias. To further improve ECG signal classification performance, an arrhythmia detection algorithm based on Convolutional Neural Network (CNN) and channel attention mechanism was proposed. Firstly, one-dimensional ECG signals were converted to two-dimensional grayscale images as input data, which no longer required noise filtering and retained the original data information to the greatest extent. In addition, minority classes data could be enlarged by a special data enhancement method to solve the problem of data imbalance. The Squeeze-and-Excitation (SE) module was inserted to the model to focus on more important information. By training on eight heart rhythm classes from the MIT-BIH arrhythmia database, an overall accuracy of 99.53% was achieved on the SE-CNN algorithm. The experimental results show that the classification accuracy of arrhythmia is improved, while the detection efficiency ensured, which has practical application value and can help doctors to diagnose diseases quickly and accurately in clinical work.
No takes yet. Share an insight, caveat, or question.
Zheng et al. (2022) studied Arrhythmias. SE-CNN algorithm was evaluated on Overall accuracy. An arrhythmia detection algorithm based on a Convolutional Neural Network and Squeeze-and-Excitation module achieved an overall classification accuracy of 99.53% on the MIT-BIH database.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: