Dynamic monitoring and control of patient anaesthetic levels

The aim of the study is to examine the ability of dynamic neural network models to control the anaesthetic level of a patient. Application of standard multilayer perceptron networks to identify the anaesthesic states of patients already has produced impressive results. Encouraged by these results, we attempt to address the question of how such models can be expanded to capture some critical aspects of the dynamic nature of anaesthesia. Data obtained under different levels of anaesthesia have been modelled for the purpose. It has been shown that inferential parameters can be used to monitor and control the anaesthesic levels.