INVESTIGADORES
BANDONI Jose Alberto
artículos
Título:
Optimal Drug Infusion Profiles using a Particle Swarm Optimization Algo
Autor/es:
M. MONTAIN; A. BLANCO; J. A. BANDONI
Revista:
COMPUTERS AND CHEMICAL ENGINEERING
Editorial:
PERGAMON-ELSEVIER SCIENCE LTD
Referencias:
Lugar: Amsterdam; Año: 2015 vol. 82 p. 13 - 24
ISSN:
0098-1354
Resumen:
tThe dynamic optimization of the administration of therapeutic drugs in simulated patients is proposed.The approach is based on a non-linear discontinuous cardiorespiratory model, which has been conceivedto simulate the effect of inotropic and vasoactive drugs as well as anesthetic agents. A stochastic technique(Particle Swarm Optimization), within the context of the control vector parameterization approach, isadopted to identify the infusion profiles of various drugs in order to track, as close as possible, the set-points on several variables of medical interest. Two different medical procedures are investigated in orderto test the efficiency and robustness of the algorithm: a congestive heart failure and the unclamping of anaortic vessel. Due to the conflicting nature of the different objectives, compromise solutions are obtainedin all cases.The dynamic optimization of the administration of therapeutic drugs in simulated patients is proposed.The approach is based on a non-linear discontinuous cardiorespiratory model, which has been conceivedto simulate the effect of inotropic and vasoactive drugs as well as anesthetic agents. A stochastic technique(Particle Swarm Optimization), within the context of the control vector parameterization approach, isadopted to identify the infusion profiles of various drugs in order to track, as close as possible, the set-points on several variables of medical interest. Two different medical procedures are investigated in orderto test the efficiency and robustness of the algorithm: a congestive heart failure and the unclamping of anaortic vessel. Due to the conflicting nature of the different objectives, compromise solutions are obtainedin all cases.