Key result
A convolutional neural network using short-time Fourier transform detected multiple arrhythmias with an accuracy of 96.65%, average sensitivity of 96.47%, and an AUC of 0.9987.
Why the study?
With the development of dynamic ECG monitoring, an effective and simple algorithm is needed to handle large quantities of ECG data for detecting arrhythmias.
Does a novel algorithm based on time-frequency analysis and convolutional neural networks accurately detect multiple arrhythmias from short-time single-lead ECG signals?
Does a novel algorithm based on time-frequency analysis and convolutional neural networks accurately detect multiple arrhythmias from short-time single-lead ECG signals?
A novel deep learning algorithm utilizing short-time Fourier transform and convolutional neural networks demonstrated high accuracy (96.65%) for detecting 12 classes of arrhythmias from 10-second single-lead ECGs.
Answers are grounded in this paper and cite their sources.
Time-frequency CNN enables efficient multi-arrhythmia detection from short ECG; leaves open prospective validation before clinical use.
Electrocardiogram (ECG) is an efficient and commonly used tool for detecting arrhythmias. With the development of dynamic ECG monitoring, an effective and simple algorithm is needed to deal with large quantities of ECG data. In this study, we proposed a method to detect multiple arrhythmias based on time-frequency analysis and convolutional neural networks. For a short-time (10 s) single-lead ECG signal, the time-frequency distribution matrix of the signal was first obtained using a time-frequency transform method, and then a convolutional neural network was used to discriminate the rhythm of the signal. ECG data in multiple databases were used and were divided into 12 classes. Finally, the performance of three kinds of time-frequency transform methods are evaluated, including short-time Fourier transform (STFT), continuous wavelet transform (CWT), and pseudo Wigner-Ville distribution (PWVD). The best result was obtained by STFT, with an accuracy of 96.65%, an average sensitivity of 96.47%, an average specificity of 99.68%, and an average F1 score of 96.27%, respectively. Especially, the area under curve (AUC) value is 0.9987. The proposed method in this work may be efficient and valuable to detect multiple arrhythmias for dynamic ECG monitoring.
No takes yet. Share an insight, caveat, or question.
Wu et al. (2019) studied Arrhythmias. Time-frequency analysis and convolutional neural networks vs. Continuous wavelet transform (CWT) and pseudo Wigner-Ville distribution (PWVD) was evaluated on Arrhythmia detection accuracy. A convolutional neural network using short-time Fourier transform detected multiple arrhythmias with an accuracy of 96.65%, average sensitivity of 96.47%, and an AUC of 0.9987.
Synapse has enriched 10 related papers. Consider them for comparative context: