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.