This paper presents a new approach for cardiac beat interpretation, based on a direct integration between a model and observed ECG signals. Physiological knowledge is represented by means of a semi-quantitative model of the cardiac electrical activity. The interpretation of cardiac beats is formalized as an optimization problem, by minimizing an error function defined between the model's output and the observations. Evolutionary algorithms (EAs) are used as the search technique in order to obtain the set of model parameters reproducing at best the observed phenomena. Examples of model adaptation to three different kinds of cardiac beats are presented. Preliminary results show the potentiality of this approach to reproduce and explain complex pathological disorders and to better localize their origin.
Publié le : 2002-11-05
Classification:
evolutionary algorithms,
cardiac modeling,
MESH: Algorithms,
MESH: Artificial Intelligence,
MESH: Computer Simulation,
MESH: Electrocardiography,
MESH: Humans,
MESH: Signal Processing, Computer-Assisted,
[SDV.IB]Life Sciences [q-bio]/Bioengineering,
[SPI.SIGNAL]Engineering Sciences [physics]/Signal and Image processing,
[MATH.MATH-DS]Mathematics [math]/Dynamical Systems [math.DS],
[MATH.MATH-ST]Mathematics [math]/Statistics [math.ST],
[INFO.INFO-MO]Computer Science [cs]/Modeling and Simulation,
[INFO.INFO-TS]Computer Science [cs]/Signal and Image Processing
@article{inserm-00134397,
author = {Hern\'andez, Alfredo and Carrault, Guy and Mora, Fernando and Bardou, Alain},
title = {Model-based interpretation of cardiac beats by evolutionary algorithms: signal and model interaction.},
journal = {HAL},
volume = {2002},
number = {0},
year = {2002},
language = {en},
url = {http://dml.mathdoc.fr/item/inserm-00134397}
}
Hernández, Alfredo; Carrault, Guy; Mora, Fernando; Bardou, Alain. Model-based interpretation of cardiac beats by evolutionary algorithms: signal and model interaction.. HAL, Tome 2002 (2002) no. 0, . http://gdmltest.u-ga.fr/item/inserm-00134397/