Key result
The MAPC NN successfully regulated hemodynamics against unexpected drug interactions, maintaining average errors of 6.4 ml/kg/min for cardiac output and 1.6 mmHg for mean arterial pressure.
Why the study?
Does a multiple adaptive predictive controller based on neural networks (MAPC(NN)) improve the regulation of hemodynamic variables in dogs with acute heart failure?
Does a multiple adaptive predictive controller based on neural networks (MAPC(NN)) improve the regulation of hemodynamic variables in dogs with acute heart failure?
A neural network-based multiple adaptive predictive controller can robustly regulate cardiac output and mean arterial pressure in a canine model of acute heart failure.
MAPC NN feasible for hemodynamic control in canine acute HF; hypothesis-generating for human translation.
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.
No takes yet. Share an insight, caveat, or question.
Koji Kashihara (2006) studied Acute heart failure (n=12). Multiple adaptive predictive control based on neural networks (MAPC NN) using dobutamine and sodium nitroprusside vs. Target setpoints was evaluated on Average errors between setpoints and observed responses in cardiac output (CO) and mean arterial pressure (MAP). The MAPC NN successfully regulated hemodynamics against unexpected drug interactions, maintaining average errors of 6.4 ml/kg/min for cardiac output and 1.6 mmHg for mean arterial pressure.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: