Pattern defined heuristic rules and directional histogram based online ECG parameter extraction

A simple histogram based approach is employed here for detection of QRS and base line of ECG signals. On the other hand, pattern defined heuristic rules are used for exposure of different patterns of ECG waves and extraction of few important time-plane features, which are clinically significant for ECG interpretation and classification. A very simple and novel idea of computation of directional histogram in both horizontal and vertical direction is employed here for detection of baseline and QRS complexes, respectively, from ECG images plotted on computer screen. Directional histogram is basically the measure of orientation of the object points in a few quantized directions. The vertical histograms are generated by computation of vertical orientation of object points whereas horizontal histograms are computed after judging the horizontal directionality of the object points. The base line is determined at the maximum of the horizontal histogram whereas QRS or R-peaks are determined from the local maxima of the maximum area zone of vertical histograms. A good degree of accuracy is achieved for both the cases (99.5% for QRS and 92% for base line). This method is advantageous for online analysis because both QRS and base lines can be determined directly from ECG data on computer screen without computation of complex mathematical models even when ECGs get tilted due to respiration and in the presence of power line oscillation. After detection of R points and base points, an efficient pattern based heuristic algorithm is developed using priory knowledge of the shape of ECG wave for detection of P, Q, R, S and T waves and their various features, which are helpful for ECG elucidation and classification.