Heart Beat Parametric Modeling Based on Monte Carlo Fitting Techniques

LIBERCZUK, SERGIO; BERGAMINI, L.; ARINI P.D.

Congreso; XXI Congreso Argentino de Bioingeniería, X Jornadas de Ingeniería Clínica; 2017

Synthesis of electrocardiogram (ECG) signals is closely linked to themodeling process since precise knowledge of the parameters of the heartbeat tobe modeled is required. The knowledge of these parameters is achieved through methods ofadjusting curves between simulated beats and real beats. These traditionaloptimization methods, such as nonlinear least squares or similar, suffer fromthe drawback of falling at local minima especially when the initial conditions arenot given in an accurate fashion. In the present work, we have designed a novelmethod robust to deviations in the initial conditions based on Monte Carlotechniques derived from the ideas of the Particle Filtering. Our method allows toadjust the heart beat and to determine the parameters of a model already known in the literature that consists of the sum offive Gaussian curves. The method fits with errors very similar to thetraditional method when the initial conditions are good, but better results areobtained in terms of squared error when the initial conditions are sufficientlydegraded. Validation was carried out with real physiological and pathologicalECG records from international databases.