Accommodation of time delay variations in automatic infusion of sodium nitroprusside

Automatic regulation of hemodynamic variables in acute heart failure by a multiple adaptive predictive controller based on neural networks

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 (MAPC_NN) 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 MAPC_NN learned nonlinear responses of CO and MAP determined by hemodynamics of dogs with heart failure. The MAPC_NN 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⁻¹ min⁻¹ in CO and ±0 mmHg in MAP) and observed responses; 6.4, 3.7, and 4.2 ml kg⁻¹ min⁻¹ 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 MAPC_NN could also regulate the hemodynamics in actual heart failure of a dog. Robust regulation of hemodynamics by the MAPC_NN 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 MAPC_NN using a simple NN to clinical situations.

Adaptive control of arterial blood pressure with a learning controller based on multilayer neural networks

We discuss a two-model multilayer neural network controller for adaptive control of mean arterial blood pressure (MABP) using sodium nitroprusside. A model with an autoregressive moving average (ARMA), representing the dynamics of the system, and a modified back-propagation training algorithm are used to design the control system to meet specified objectives of design (settling time and undershoot/overshoot) and clinical constraints. The controller is associated with a weighting-determinant unit (WDU) to determine and update the output weighting factor of the parallel two-model neural network for adequate control action and a control-signal modification unit (CMU) to comply with clinical constraints and to suppress the effect of adverse noise and to improve the WDU performance. Extensive computer simulations indicate satisfactory performance and robustness of the proposed controller in the presence of much noise, over the full range of plant parameters, uncertainties, and large variations of parameters.