A new QRS detection algorithm based on the Hilbert transform achieved a detection rate of 99.64%, sensitivity of 99.81%, and positive prediction of 99.83% on the MIT-BIH Arrhythmia Database.
Does a new QRS detection algorithm based on the Hilbert transform accurately detect QRS complexes in ECG records?
A new QRS detection algorithm based on the Hilbert transform demonstrates high accuracy and noise tolerance in standard ECG databases.
A robust new algorithm for QRS defection using the properties of the Hilbert transform is proposed. The method allows R waves to be differentiated from large, peaked T and P waves with a high degree of accuracy and minimizes the problems associated with baseline drift, motion artifacts and muscular noise. The performance of the algorithm was tested using the records of the MIT-BIH Arrhythmia Database. Beat by beat comparison was performed according to the recommendation of the American National Standard for ambulatory ECG analyzers (ANSI/AAMI EC38-1998). A QRS detection rate of 99.64%, a sensitivity of 99.81% and a positive prediction of 99.83% was achieved against the MIT-BIH Arrhythmia database. The noise tolerance of the new proposed QRS detector was also tested using standard records from the MIT-BIH Noise Stress Test Database. The sensitivity of the detector remains about 94% even for signal-to-noise ratios (SNR) as low as 6 dB.
Benítez et al. (Mon,) conducted a other in Arrhythmia. QRS detection algorithm based on the Hilbert transform vs. Database annotations was evaluated on QRS detection rate, sensitivity, and positive prediction. A new QRS detection algorithm based on the Hilbert transform achieved a detection rate of 99.64%, sensitivity of 99.81%, and positive prediction of 99.83% on the MIT-BIH Arrhythmia Database.