Key result
A novel neural network-based algorithm using hybrid morphological and dynamic ECG features achieved an average arrhythmia classification accuracy of 99.75% and 99.84%.
Population
ECG signals from the MIT-BIH arrhythmia database and MIT-BIH supraventricular arrhythmia database
Design
Other
Authors
Loading...
Supports AI-ECG arrhythmia detection research; leaves open prospective clinical validation before practice adoption.
A novel hybrid feature extraction method using discrete wavelet transform and RR interval dynamics fed into a neural network achieved >99% accuracy in classifying arrhythmias from standard ECG databases.
Anwar et al. (2018) studied Arrhythmia (n=35,875). Arrhythmia classification algorithm using hybrid features and neural network was evaluated on Average accuracy for class- and subject-oriented scheme. A novel neural network-based algorithm using hybrid morphological and dynamic ECG features achieved an average arrhythmia classification accuracy of 99.75% and 99.84%.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: