Key result
The computer-aided diagnostic system using a cubic support vector machine (C-SVM) achieved an overall accuracy of 98.4% for classifying arrhythmia, atrial fibrillation, and normal sinus rhythm.
Answers are grounded in this paper and cite their sources.
A computer-aided diagnostic system using a cubic support vector machine classifier can accurately detect arrhythmia and atrial fibrillation from ECG signals.
This article proposes a computer-aided diagnostic system for feature-based selection classification (CAD-FSC) to detect arrhythmia, atrial fibrillation and normal sinus rhythm. The CAD-FSC methodology encompasses of ECG signal processing phases: ECG pre-processing, R-peak detection, feature extraction, feature selection and ECG classification. Digital filters are used to pre-process the ECG signal and the R-peak is detected by using the Pan-Tompkin’s algorithm. The heart rate variability (HRV) features are extracted in time and frequency domains. Among them, the prominent features are selected with analysis of variance (ANOVA) using Statistical Package for the Social Sciences (SPSS) tool. Cubic support vector machine (C-SVM), coarse Gaussian support vector machine (CG-SVM), cubic k-nearest neighbor (C-kNN) and weighted k-nearest neighbor (W-kNN) classifiers are utilized to validate the CAD-FSC system for three-stage classification. The C-SVM outperforms all other classifiers by giving higher overall accuracy of 98.4% after feature selection of time domain and frequency domain.
No takes yet. Share an insight, caveat, or question.
Tripath et al. (2020) studied Arrhythmia, atrial fibrillation, and normal sinus rhythm. Computer-aided diagnostic system for feature-based selection classification (CAD-FSC) using C-SVM vs. CG-SVM, C-kNN, and W-kNN classifiers was evaluated on Overall classification accuracy. The computer-aided diagnostic system using a cubic support vector machine (C-SVM) achieved an overall accuracy of 98.4% for classifying arrhythmia, atrial fibrillation, and normal sinus rhythm.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: