Depth of anaesthesia assessment with generative polyspectral models

The application of anaesthetic agents is known to have significant effects on the EEG waveform. Information extraction now routinely goes beyond second order spectral analysis, as obtained via power spectral methods, and uses higher order spectral methods. In this paper we present a model which generalises the autoregressive class of polyspectral models by having a semi-parametric description of the residual probability density. We estimate the model in the variational Bayesian framework and extract higher order spectral features. Testing their importance for depth of anaesthesia classification is done on three different EEG data sets collected under exposure to different agents. The results show that significant improvements can be made over standard methods of estimating higher order spectra. The results also indicate that in two out of three anaesthetic agents, better classification can be achieved with higher order spectral features.

[1]  P. Myles,et al.  Patient satisfaction after anaesthesia and surgery: results of a prospective survey of 10,811 patients. , 2000, British journal of anaesthesia.

[2]  E Kochs,et al.  Does bispectral analysis add anything but complexity? BIS sub-components may be superior to BIS for detection of awareness. , 2004, British journal of anaesthesia.

[3]  I. Rampil.  A Primer for EEG Signal Processing in Anesthesia , 1998, Anesthesiology.

[4]  D. Maynard,et al.  The cerebral function analysing monitor Initial clinical experience, application and further development , 1983, Anaesthesia.

[5]  Makoto Ozaki,et al.  A502 Ketamine Causes a Paradoxical Increase in the Bispectral Index , 1997 .

[6]  Derek A. Linkens,et al.  Recognition of patient anaesthetic levels: neural network systems, principal components analysis, and canonical discriminant variates , 1997, Artif. Intell. Medicine.

[7]  Robert K. Stoelting,et al.  Handbook of Pharmacology and Physiology in Anesthetic Practice , 1995 .

[8]  William D. Penny,et al.  Variational Bayes for Generalized , 2002 .

[9]  Bruno O. Shubert,et al.  Random variables and stochastic processes , 1979 .

[10]  K. Kuizenga,et al.  Biphasic EEG changes in relation to loss of consciousness during induction with thiopental, propofol, etomidate, midazolam or sevoflurane. , 2001, British journal of anaesthesia.

[11]  Yoshua Bengio,et al.  Pattern Recognition and Neural Networks , 1995 .

[12]  S.M. Kay,et al.  Spectrum analysis—A modern perspective , 1981, Proceedings of the IEEE.

[13]  M. West.  Outlier Models and Prior Distributions in Bayesian Linear Regression , 1984 .

[14]  S. Roberts,et al.  EEG signal processing in anaesthesia. Use of a neural network technique for monitoring depth of anaesthesia. , 2002, British journal of anaesthesia.

[15]  A. Yli-Hankala,et al.  Description of the Entropy™ algorithm as applied in the Datex‐Ohmeda S/5™ Entropy Module , 2004, Acta anaesthesiologica Scandinavica.

[16]  C Thornton,et al.  Evoked responses in anaesthesia. , 1998, British journal of anaesthesia.

[17]  J. Jakobsson,et al.  Nitrous oxide does not alter bispectral index: study with nitrous oxide as sole agent and as an adjunct to i.v. anaesthesia. , 1999, British journal of anaesthesia.

[18]  William D. Penny,et al.  Variational Bayes for generalized autoregressive models , 2002, IEEE Trans. Signal Process..

[19]  Tommi S. Jaakkola,et al.  Tutorial on variational approximation methods , 2000 .

[20]  D A Linkens,et al.  Neural networks and nonlinear regression modelling and control of depth of anaesthesia for spontaneously breathing and ventilated patients. , 1993, Computer methods and programs in biomedicine.

[21]  B. Ripley,et al.  Robust Statistics , 2018, Wiley Series in Probability and Statistics.

[22]  J. Davenport.  Editor , 1960 .

[23]  Andrew R. Webb,et al.  Statistical Pattern Recognition , 1999 .

[24]  J. Hall,et al.  Bispectral index: comparison of two montages. , 1998, British journal of anaesthesia.

[25]  D. Tempe,et al.  Is there any alternative to the Bispectral Index Monitor? , 2004, British journal of anaesthesia.

[26]  Chiharu Negishi,et al.  Bispectral EEG Index during Nitrous Oxide Administration , 1998, Anesthesiology.

[27]  Lionel Tarassenko,et al.  Use of parametric modelling and statistical pattern recognition in detection of awareness during general anaesthesia , 1998 .

[28]  Hugo Vereecke,et al.  Spectral Entropy as an Electroencephalographic Measure of Anesthetic Drug Effect: A Comparison with Bispectral Index and Processed Midlatency Auditory Evoked Response , 2004, Anesthesiology.

[29]  Foster J. Provost,et al.  Confidence Bands for Roc Curves , 2004, ROCAI.

[30]  J. F. Scott.  Distribution Theory , 1973, Nature.

[31]  Chrysostomos L. Nikias,et al.  Bispectrum estimation: A parametric approach , 1985, IEEE Trans. Acoust. Speech Signal Process..

[32]  Stephen J. Roberts,et al.  EEG-based assessment of anaesthetic depth using neural networks , 1996 .

[33]  John G. Proakis,et al.  Probability, random variables and stochastic processes , 1985, IEEE Trans. Acoust. Speech Signal Process..

[34]  K. Leslie,et al.  For Personal Use. Only Reproduce with Permission from the Lancet , 2022 .

[35]  Ian T. Nabney,et al.  Netlab: Algorithms for Pattern Recognition , 2002 .

[36]  Peter S. Sebel,et al.  Development and Clinical Application of Electroencephalographic Bispectrum Monitoring , 2000, Anesthesiology.

[37]  David J. C. MacKay,et al.  The Evidence Framework Applied to Classification Networks , 1992, Neural Computation.

[38]  Marvin H. J. Guber.  Bayesian Spectrum Analysis and Parameter Estimation , 1988 .

[39]  Simon J. Godsill,et al.  Statistical Reconstruction and Analysis of Autoregressive Signals in Impulsive Noise Statistical Reconstruction and Analysis of Autoregressive Signals in Impulsive Noise , 1998 .

[40]  R. Tough,et al.  The estimators of normalized moments of the gamma distribution , 1994 .

[41]  M. Kendall,et al.  Kendall's advanced theory of statistics , 1995 .