Hierarchical fuzzy modelling for monitoring depth of anaesthesia

Abstract

A hierarchical structure, based on fuzzy modelling, which can monitor depth of anaesthesia (DOA) from many clinical signs in the operating theatre, is described. The first level uses numerical clinical signs, such as systolic arterial pressure (SAP) and heart rate (HR), via a rule-base from anaesthetists' experience or a self-organizing learning algorithm to interpret primary depth of anaesthesia (PDOA). The second level is focused on non-numerical clinical signs, such as sweating (SW), lacrimation (LA) and pupil response (PR), which can be merged with the first level of PDOA to decide DOA with more confidence. Furthermore, linguistic rules and a simple fuzzy modelling concept have been used to model a patient during induction and maintenance stages. Not only can this model simulate new ideas and monitoring methods, but it can also be used clinically on-line to give an estimate of the adequacy of DOA. Successful results have given confidence to perform on-line clinical trials in the operating theatre. Two configurations of fuzzy modelling to determine the rule-base are described in this paper. Firstly, a self-organizing fuzzy modelling approach has the ability to generate rules on-line from input and output data. Secondly, if there is no direct measurement for the system output or it is very difficult to interpret, a self-organizing learning system which can learn rules from off-line input and output data can be utilized for modelling such systems.