Artificial neural networks used with bispectral analysis for intra-operative EEG monitoring

The brain is the target organ of anesthesia yet the electroencephalogram (EEG) is not routinely monitored during anesthetic procedures. This is partly due to the difficulty of interpreting complex changes in the EEG waveform with respect to anesthetic conditions. Most attempts at developing EEG derived variables and display techniques have been based on spectral analysis. Bispectral analysis is a signal processing technique capable of detecting phase-coupling within a signal (which is lost using conventional power spectral analysis). Artificial neural networks (ANN) which excel at pattern classification were used in this study to interpret results of bispectral analysis. Six human subjects were studied at three anesthetic levels (light, nominal, and deep anesthesia). ANNs offer an efficient approach for extracting and using the additional signal information provided by bispectral analysis