Development of adaptive QRS detection rules based on center differentiation method for clinical application

Publication Type:
Conference Proceeding
ISCAS 2012 - 2012 IEEE International Symposium on Circuits and Systems, 2012, pp. 2071 - 2074
Issue Date:
Filename Description Size
06271690.pdfPublished version748.75 kB
Adobe PDF
Full metadata record
Interpretation of cardiac rhythms is highly dependent on accurate detection of atrial activity. The robustness is an important requirement for clinical usage. This study presents an adaptive QRS detection method for real-time clinical ECG signals. In this method, center differentiation is applied as a whitening filer, and a composite function enhances the high frequency QRS energy. To robustly detect clinical data, a novel threshold selection method based on statistics is proposed. Moreover, this study provides a benchmarking clinical dataset acquired from cardiac patients. Our extensive experimental results using the MIT-BIH arrhythmia database show that our technique can detect beats with 99.67% accuracy, and the sensitivity is 99.83%. With the exceptional QRS detection result, further testing of the proposed method with clinical data shows the accuracy for atrial and ventricular arrhythmias is 82.9% and 90.2%, respectively. © 2012 IEEE.
Please use this identifier to cite or link to this item: