Key result
A multilevel wavelet entropy method combined with a quadratic support vector machine classifier achieved 94.9% accuracy in distinguishing premature ventricular contractions from normal ECG signals.
Why the study?
Methods to automatically distinguish premature ventricular contractions from normal ECG signals using fewer features were needed.
A multilevel wavelet entropy method combined with a quadratic support vector machine classifier achieved 94.9% accuracy in distinguishing premature ventricular contractions from normal ECG signals using only five features.
One of the abnormalities in the heart that can be assessed from an ECG signal is premature ventricle contraction (PVC). PVC is a form of arrhythmia in the form of irregularity in beat ECG signals. In this study, a multilevel wavelet entropy method was developed to distinguish PVC and normal ECG signals automatically. Data was taken from the MIT-BIH arrhythmia database with the process carried out is normalization, median filtering, beat-parsing, MWE calculation and classification using SVM. The results of the experiment showed that MWE level 5 with DB2 as mother wavelet and Quadratic SVM as classifier resulted in the highest accuracy of 94.9%. MWE level 5 means only five features needed for classification. The number of features is very little compared to previous research with a quite high accuracy.
No takes yet. Share an insight, caveat, or question.
Rizal et al. (2018) studied Premature Ventricular Contraction (n=8,984). Multilevel Wavelet Entropy (MWE) and Support Vector Machine (SVM) was evaluated on Classification accuracy. A multilevel wavelet entropy method combined with a quadratic support vector machine classifier achieved 94.9% accuracy in distinguishing premature ventricular contractions from normal ECG signals.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: