Key result
The proposed algorithm combining K-Nearest Neighbor and Particle Swarm Optimization achieved an average detection accuracy of 99.43%, sensitivity of 99.69%, and positive predictivity of 99.72%.
Population
48 ECG records from the MIT-BIH arrhythmia database (MITDB)
Comparison
A real-time algorithm combining K-Nearest… vs Extant algorithms reported in literature
Design
Other
Authors
Loading...
May enhance automated QRS detection; leaves open validation in diverse clinical ECG datasets.
A novel algorithm combining KNN and PSO achieves >99% accuracy, sensitivity, and positive predictivity for QRS detection in ECG signals.
He et al. (2017) studied Arrhythmia (ECG signal processing) (n=48). K-Nearest Neighbor and Particle Swarm Optimization based QRS detection algorithm vs. Extant QRS detection algorithms was evaluated on Detection accuracy. The proposed algorithm combining K-Nearest Neighbor and Particle Swarm Optimization achieved an average detection accuracy of 99.43%, sensitivity of 99.69%, and positive predictivity of 99.72%.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: