Key result
A Multilayer Perceptron Neural Network using WQRS, TQ, pb1, and pb2 features classified normal sinus rhythm, atrial premature complexes, and ventricular premature complexes with 99.89% accuracy.
Why the study?
Arrhythmias are the most common disturbances in heart disease, and automatic detection of APC and PVC was sought to provide clinical convenience.
An artificial neural network model using specific ECG features (WQRS, TQ, pb1, pb2) can automatically classify normal sinus rhythm, atrial premature complexes, and ventricular premature complexes with over 99% accuracy.
No takes yet. Share an insight, caveat, or question.
Akin et al. (2020) studied Cardiac arrhythmias (APC and PVC) (n=900). Multilayer Perceptron Neural Network (MLPNN) vs. Other artificial neural network structures (RBFNN, GRNN, Decision Tree) was evaluated on Accuracy of arrhythmia classification (NSR, APC, PVC). A Multilayer Perceptron Neural Network using WQRS, TQ, pb1, and pb2 features classified normal sinus rhythm, atrial premature complexes, and ventricular premature complexes with 99.89% accuracy.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: