Prediction of response to incision using the mutual information of electroencephalograms during anaesthesia.

This paper presents a new approach to predict response during isoflurane anaesthesia by using mutual information (MI) time series of electroencephalograms (EEGs) and their complexity analysis. The MI between four lead electrodes was first computed using the EEG time series. The Lempel-Ziv complexity measures, C(n)s, were extracted from the MI time series. Prediction was made by means of artificial neural network (ANN). From 98 consenting patient experiments, 98 distinct EEG recordings were collected prior to incision during isoflurane anaesthesia of different levels. During and after skin incision, each patient was observed carefully for 2 min to detect subsequent responses (purposeful movement, changes in hemodynamic parameters and respiratory pattern) and then the EEG was labelled as 0.0 for responder or as 1.0 for non-responder. Training and testing the ANN used the 'drop-one-patient' method. The prediction was tested by monitoring the response to incision and the result given by the ANN. The system was able to correctly classify purposeful response in average accuracy of 91.84% of the cases. The results showed that the method has a better performance than other methods, such as spectral edge frequency, median frequency, and bispectral analysis. This method is computationally fast and acceptable real-time clinical performance was obtained.