Detection of QRS Complexes in 12-lead ECG using Adaptive Quantized Threshold

The QRS complex is the most prominent wave component within the electrocardiogram. It reflects the electrical activity of heart during the ventricular contraction and the time of its occurrence. Its morphology provides information about the current state of the heart. The identification of QRS-complexes forms the basis for almost all automated ECG analysis algorithms. The presented algorithm employs a modified definition of slope, of ECG signal, as the feature for detection of QRS. A sequence of transformations of the filtered and baseline drift corrected ECG signal is used for extraction of a new modified slope-feature. Two feature-components are combined to derive the final QRSfeature signal. Multiple quantized amplitude thresholds are employed for distinguishing QRS-complexes from non-QRS regions of the ECG waveform. An adequate amplitude threshold is automatically selected by the presented algorithm and is utilized for delineating the QRS-complexes. A QRS detection rate of 98.56% with false positive and false negative percentage of 0.82% and 1.44% has been reported.