Hidden Markov model in wavelet analysis of myocardial ischemia in rabbit

Deals with analysis of myocardial ischemia caused by left anterior coronary artery occlusion. A system based on hidden Markov models has been designed. The vectorcardiograms recorded before and during the episode of local ischemia were preprocessed by wavelet transform to reveal short-time events during ventricular depolarization. To verify the models, 11 Langendorf-perfused rabbit hearts have been used. The presented results show that models can detect early ischemia in one of three orthogonal electrocardiograms in more than 90% of cases.