Key result
Evolvable block-based neural networks achieved high average detection accuracies of 98.1% for ventricular ectopic beats and 96.6% for supraventricular ectopic beats using the MIT-BIH database.
Population
ECG signals from the Massachusetts Institute of Technology/Beth Israel Hospital (MIT-BIH) arrhythmia database
Comparison
Evolvable block-based neural networks optimized… vs Previously reported electrocardiogram…
Authors
Loading...
Supports neural network ECG classifiers in research; leaves open prospective clinical validation.
Evolvable block-based neural networks demonstrate high accuracy in classifying ventricular and supraventricular ectopic beats from ECG signals.
Jiang et al. (2007) studied Arrhythmia. Evolvable block-based neural networks (BbNNs) vs. Previously reported ECG classification methods was evaluated on Detection accuracies of ventricular ectopic beats and supraventricular ectopic beats. Evolvable block-based neural networks achieved high average detection accuracies of 98.1% for ventricular ectopic beats and 96.6% for supraventricular ectopic beats using the MIT-BIH database.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: