ECG signal analysis using temporary dynamic sequence alignment

This paper shows a feature extraction method for electrocardiographic signals (ECG) based on dynamic programming algorithms. Specifically, we apply local alignment technique for recognition of template in continuous ECG signal. First, we code the signal to characters in base of sign and magnitude of first derivative, then we apply local alignment algorithm to search a complex PQRST template in target continuous ECG signal. Finally, we arrange the data for direct measurement of morphological features in all PQRST segment detected. To validate these algorithms, we contrast it with conventional analysis making measurement of QT segments in MIT's data base1. We obtain processing time at least a hundred times lower than those obtained by conventional manual analysis and error rates in QT measurement below 5%. The automated massive analysis of ECG presented in this work is suitable for posprocessing methods such as datamining, classification and assisted diagnosis of cardiac pathologies.