Key result
A novel classification approach for ECG arrhythmias using Graph Bispectrum and Deep Neural Networks effectively classified 4 different types of ECG signals.
Why the study?
Heart disease is a leading killer, and recognizing and categorizing ECG signals is crucial for early prevention of heart and cardiovascular disease.
A novel Graph Bispectrum method combined with Deep Neural Networks demonstrates effectiveness in classifying ECG arrhythmias.
Should not yet change ECG interpretation practice; leaves open validation of Graph Bispectrum DNNs in clinical cohorts.
Heart disease is leading killers of human beings. Recognizing and categorizing Electrocardiogram (ECG) signals is crucial for early heart and cardiovascular disease prevention. A novel classification approach for ECG Arrhythmias based on Graph Bispectrum (GBispec) is proposed. First, the ECG signal is converted from the time domain to the Graph domain by using Graph Fourier Transform (GFT); Then, referring to the traditional bispectrum algorithm, the GFT results of ECG are converted into GBispec; Then, extract the graph features of Graph Integral Bispectrum (GIB), and use Deep Neural Networks(DNN) to process the GIB results. 4 different types of ECG signals are classified. Experiments results show that proposed method is effective in classification.
No takes yet. Share an insight, caveat, or question.
Shiyilin et al. (2023) studied ECG Arrhythmias. Graph Bispectrum (GBispec) and Deep Neural Networks (DNN) was evaluated on Classification of 4 different types of ECG signals. A novel classification approach for ECG arrhythmias using Graph Bispectrum and Deep Neural Networks effectively classified 4 different types of ECG signals.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: