Automatic Regulation of Hemodynamic Variables in Acute Heart Failure by a Multiple Adaptive Predictive Controller Based on Neural NetworksReportar como inadecuado




Automatic Regulation of Hemodynamic Variables in Acute Heart Failure by a Multiple Adaptive Predictive Controller Based on Neural Networks - Descarga este documento en PDF. Documentación en PDF para descargar gratis. Disponible también para leer online.

Annals of Biomedical Engineering

, Volume 34, Issue 12, pp 1846–1869

First Online: 18 October 2006Received: 16 August 2005Accepted: 29 August 2006

Abstract

Automated drug-delivery systems that can tolerate various responses to therapeutic agents have been required to control hemodynamic variables with heart failure. This study is intended to evaluate the control performance of a multiple adaptive predictive control based on neural networks MAPCNN to regulate the unexpected responses to therapeutic agents of cardiac output CO and mean arterial pressure MAP in cases of heart failure. The NN components in the MAPCNN learned nonlinear responses of CO and MAP determined by hemodynamics of dogs with heart failure. The MAPCNN performed ideal control against unexpected 1 drug interactions, 2 acute disturbances, and 3 time-variant responses of hemodynamics average errors between setpoints +35 ml kg min in CO and ±0 mmHg in MAP and observed responses; 6.4, 3.7, and 4.2 ml kg min in CO and 1.6, 1.4, and 2.7 mmHg 10.5, 20.8, and 15.3 mmHg without a vasodilator in MAP during 120-min closed-loop control. The MAPCNN could also regulate the hemodynamics in actual heart failure of a dog. Robust regulation of hemodynamics by the MAPCNN was attributable to the ability of on-line adaptation to adopt various responses and predictive control using the NN. Results demonstrate the feasibility of applying the MAPCNN using a simple NN to clinical situations.

KeywordsCardiac output Mean arterial pressure Therapeutic agents An automated drug infusion system  Download fulltext PDF



Autor: Koji Kashihara

Fuente: https://link.springer.com/







Documentos relacionados