Key result
Multi-Class Support Vector Machine (MSVM) using Crammers method was highly effective for classifying Normal, Right Bundle Branch Block, and Premature Ventricular Contraction ECG beats.
Population
ECG signals containing three types of beats: Normal, Right Bundle Branch Block, and Premature Ventricular…
Comparison
Artificial Neural Network classifiers… vs K-Nearest Neighbor and Naive Bayes Classifier
Authors
Loading...
ANN-based ECG classification appears feasible; leaves open validation before clinical use.
Multi-Class Support Vector Machine (MSVM) classifiers can effectively and reliably classify normal and abnormal ECG beats for diagnostic decision support.
Sultana et al. (2016) studied Cardiac arrhythmia. Artificial Neural Network classifiers (KNN, NBC, MSVM) was evaluated on ECG beat classification performance (Sensitivity, Specificity, Precision, Bit Error Rate, Accuracy). Multi-Class Support Vector Machine (MSVM) using Crammers method was highly effective for classifying Normal, Right Bundle Branch Block, and Premature Ventricular Contraction ECG beats.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: