Temporal classification of patient anaesthetic states

The goal of this study is to explore the ability of temporal neural network models to classification of patient anaesthetic states. Application of standard multilayer perceptron networks to recognise the states of anaesthesia 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. An extension of the conventional multilayered feedforward networks to have memory for past values is undertaken to address the issue.