Key result
An artificial neural network-based adaptive matched filtering algorithm achieved a 99.5% QRS detection rate on a very noisy ECG record, outperforming linear adaptive and bandpass filtering methods.
Why the study?
Does an ANN-based adaptive matched filtering algorithm improve QRS detection rate in noisy ECG signals compared to linear or bandpass filtering?
Does an ANN-based adaptive matched filtering algorithm improve QRS detection rate in noisy ECG signals compared to linear or bandpass filtering?
Absolute Event Rate: 99.5% vs 97.5%
An ANN-based adaptive matched filtering algorithm effectively removes nonlinear noise from ECG signals, improving QRS detection rates in noisy records.
Authors
No takes yet. Share an insight, caveat, or question.
May aid QRS detection in noisy ECGs; leaves open validation in prospective clinical datasets.
Xue et al. (1992) studied Arrhythmia (QRS detection). Adaptive matched filtering algorithm based upon an artificial neural network (ANN) vs. Linear adaptive whitening filter and bandpass filtering method was evaluated on QRS detection rate. An artificial neural network-based adaptive matched filtering algorithm achieved a 99.5% QRS detection rate on a very noisy ECG record, outperforming linear adaptive and bandpass filtering methods.
Synapse has enriched 3 closely related papers on similar clinical questions. Consider them for comparative context: