Hidden Markov Tree Model Applied to ECG Delineation

Abstract

A new electrocardiogram (ECG) delineation method is proposed, which uses a hidden Markov tree model. The aim of this approach is, on the one hand, to use wavelet coefficients to characterize the different ECG waves, and, on the other hand, to link these coefficients by a tree structure enabling wave change to be detected. By associating this method with a fusion method between scales based on the concept of context, good results are obtained on a special database created for the risk analysis of atrial fibrillation, particularly in P-wave delineation.