Automatic closed-loop control of mivacurium infusions applying neural networks

Recently introduced short-acting blocking agents like mivacurium provide benefits for the clinical routine due to a small onset time and half life. So for an automatic closed-loop control of the neuromuscular blockade a fast and highly adaptable control unit is needed. Its development should not imply costly investigations for determining a pharmacological model. The fulfilling of these requirements yields a self-adapting model-based predictive control system applying artificial neural networks. In a clinical study mivacurium was administered to 35 patients (ASA I-III). The performance of the novel system (mean of the T/sub 1/-error: -0.32/spl plusmn/1.7) compares favourably with closed-loop controllers demonstrated in the past. These promising results and the easy adaption to other blocking agents encourage to apply this technology even for delivering hypnotic drugs.