Key result
The proposed fractional wavelet-based QRS detector achieved a sensitivity of 99.76%, a positive predictivity of 99.85%, and an average error rate of 0.39% on the MIT-BIH Arrhythmia Database.
Why the study?
Detection of complex QRS is of major importance in automatic ECG processing to calculate heart rate, measure cardiac cycle intervals, and detect anomalies.
Does a Fractional Wavelet-based QRS detector improve the accuracy of QRS complex detection in ECG signals?
Does a Fractional Wavelet-based QRS detector improve the accuracy of QRS complex detection in ECG signals?
Answers are grounded in this paper and cite their sources.
A novel fractional wavelet-based algorithm demonstrates high sensitivity and positive predictivity for automated QRS detection in ECG signals.
The detection of complex QRS is of a major importance in the systems of automatic treatment of the ECG. Indeed, once the peaks R identified, the heart rate can be calculated and various times and amplitudes of the cardiac cycle can be measured and located. Anomalies can therefore be detected. This paper proposes a new method based on Fractional Wavelet Filters for accurate detection of different QRS in the ECG. This method is based on the different energy levels in Fractional Wavelet detail coefficients and it was tested using ECGs from selected records of the MIT-BIH Arrhythmia Database (MITDB). Results, in terms of error, sensitivity and the value of the positive predictivity are very satisfactory.
No takes yet. Share an insight, caveat, or question.
Houamed et al. (2020) studied Arrhythmia (ECG QRS detection) (n=48). Fractional Wavelet-based QRS Detector vs. Other QRS detection algorithms (historical/literature) was evaluated on Sensitivity of QRS detection. The proposed fractional wavelet-based QRS detector achieved a sensitivity of 99.76%, a positive predictivity of 99.85%, and an average error rate of 0.39% on the MIT-BIH Arrhythmia Database.
Synapse has enriched 10 related papers. Consider them for comparative context: