The proposed premature ventricular contraction detection system using tunable Q-factor wavelet transform and K-Nearest Neighbor classifier achieved an accuracy of 97.81% and sensitivity of 98.23%.
Does a detection system based on tunable Q-factor wavelet transform and KNN classifier improve the accuracy and sensitivity of identifying premature ventricular contractions in ECG records?
A novel algorithm using tunable Q-factor wavelet transform and a KNN classifier demonstrates high accuracy and sensitivity for automated detection of premature ventricular contractions, which could assist in screening patients with coronary artery disease.
BACKGROUND: The Electrocardiogram (ECG) is an important measure for diagnosing the presence or absence of heart arrhythmias. Premature ventricular contractions (PVC) is a relatively large arrhythmia occurring outside the normal tract and being triggered outside the Sino atrial (SA) node of heart. OBJECTIVE: This study has focused on tunable Q-factor wavelet transform (TQWT) algorithm and statistical methods to detect PVC. MATERIAL AND METHODS: In this analytical and statistical study, 22 ECGs records were selected from the MIT/BIH arrhythmia database. In the first stage the noise of signal remove and then five sub-bands create by TQWT. In the second stage nine features (minimum, maximum, root mean square, mean, interquartile range, standard deviation (SD), skewness, and variance) extracted of ECG and then the best features selected by using analysis of variance (ANOVA) test. Finally, the system is evaluated by using the learning machines of support vector machine (SVM), the K-Nearest Neighbor (KNN), and artificial neural network (ANN). RESULTS: The best results were verified with KNN learning machine the sensitivity Se= 98.23% and accuracy Ac= 97.81%. CONCLUSION: A comparative analysis with the related existing methods shows the method proposed in this study is higher than the other method for classification PVC and can help physicians to classify normal and PVC heart signals in the screening of the patients with coronary artery diseases (CADs).
Mohamad Hadi Mazidi (Sat,) conducted a other in Premature Ventricular Contraction (PVC) (n=22). Tunable Q-factor wavelet transform (TQWT) with K-Nearest Neighbor (KNN) classifier vs. Support Vector Machine (SVM) and Artificial Neural Network (ANN) was evaluated on Accuracy and Sensitivity of PVC detection. The proposed premature ventricular contraction detection system using tunable Q-factor wavelet transform and K-Nearest Neighbor classifier achieved an accuracy of 97.81% and sensitivity of 98.23%.