Automated Detection of Anesthetic Depth Levels Using Chaotic Features with Artificial Neural Networks

Monitoring the depth of anesthesia (DOA) during surgery is very important in order to avoid patients’ interoperative awareness. Since the traditional methods of assessing DOA which involve monitoring the heart rate, pupil size, sweating etc, may vary from patient to patient depending on the type of surgery and the type of drug administered, modern methods based on electroencephalogram (EEG) are preferred. EEG being a nonlinear signal, it is appropriate to use nonlinear chaotic parameters to identify the anesthetic depth levels. This paper discusses an automated detection method of anesthetic depth levels based on EEG recordings using non-linear chaotic features and neural network classifiers. Three nonlinear parameters, namely, correlation dimension (CD), Lyapunov exponent (LE) and Hurst exponent (HE) are used as features and two neural network models, namely, multi-layer perceptron network (feed forward model) and Elman network (feedback model) are used for classification. The neural network models are trained and tested with single and multiple features derived from chaotic parameters and the performances are evaluated in terms of sensitivity, specificity and overall accuracy. It is found from the experimental results that the Lyapunov exponent feature with Elman network yields an overall accuracy of 99% in detecting the anesthetic depth levels.

[1]  Das.  Applicability of Lyapunov Exponent in EEG data analysis , 2022 .

[2]  Dazong Jiang,et al.  Detecting nonlinearity in multichannel epileptic EEG , 1997, Proceedings of the 19th Annual International Conference of the IEEE Engineering in Medicine and Biology Society. 'Magnificent Milestones and Emerging Opportunities in Medical Engineering' (Cat. No.97CH36136).

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

[4]  Ah Chung Tsoi,et al.  Classification of Electroencephalogram Using Artificial Neural Networks , 1993, NIPS.

[5]  Howard B. Demuth,et al.  Neutral network toolbox for use with Matlab , 1995 .

[6]  K. Rasheed,et al.  HURST EXPONENT AND FINANCIAL MARKET PREDICTABILITY , 2005 .

[7]  Jin Xu,et al.  Monitoring depth of anesthesia based on complexity of electroencephalogram , 2004, IEEE International Workshop on Biomedical Circuits and Systems, 2004..

[8]  Ah Chung Tsoi,et al.  Nonlinear considerations in EEG signal classification , 1997, IEEE Trans. Signal Process..

[9]  D. Hoyer,et al.  Nonlinear analysis of heart rate and respiratory dynamics , 1997, IEEE Engineering in Medicine and Biology Magazine.

[10]  Albert Wauquier,et al.  Monitoring Depth of Anesthesia with the EEG , 1986 .

[11]  U. Rajendra Acharya,et al.  Non-linear analysis of EEG signals at various sleep stages , 2005, Comput. Methods Programs Biomed..

[12]  P. Grassberger,et al.  Characterization of Strange Attractors , 1983 .

[13]  Daniel Graupe,et al.  Principles of Artificial Neural Networks , 2018, Advanced Series in Circuits and Systems.

[14]  X. -S. Zhang,et al.  Predicting movement during anaesthesia by complexity analysis of electroencephalograms , 1999, Medical & Biological Engineering & Computing.

[15]  Carsten Thomsen,et al.  COMPUTERIZED MONITORING OF DEPTH OF ANAESTHESIA WITH ISOFLURANE , 1989 .

[16]  J Röschke,et al.  The calculation of the first positive Lyapunov exponent in sleep EEG data. , 1993, Electroencephalography and clinical neurophysiology.

[17]  R. Hornero,et al.  Estimating complexity from EEG background activity of epileptic patients. , 1999, IEEE engineering in medicine and biology magazine : the quarterly magazine of the Engineering in Medicine & Biology Society.

[18]  J. Bassingthwaighte,et al.  Evaluating rescaled range analysis for time series , 1994, Annals of Biomedical Engineering.

[19]  S. Rajashekaran,et al.  Neural Networks, Fuzzy Logic and Genetic Algorithms , 2004 .

[20]  U. Ruttimann,et al.  Determining the Hurst exponent of fractal time series and its application to electrocardiographic analysis , 1999, Comput. Biol. Medicine.

[21]  Craig Ellis.  The sampling properties of Hurst exponent estimates , 2007 .

[22]  R.J. Roy,et al.  Design of a recognition system to predict movement during anesthesia , 1997, IEEE Transactions on Biomedical Engineering.

[23]  J. Drummond,et al.  A comparison of median frequency, spectral edge frequency, a frequency band power ratio, total power, and dominance shift in the determination of depth of anesthesia , 1991, Acta anaesthesiologica Scandinavica.

[24]  Schreiber,et al.  Quantification of depth of anesthesia by nonlinear time series analysis of brain electrical activity , 2000, Physical review. E, Statistical physics, plasmas, fluids, and related interdisciplinary topics.

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

[26]  I J Rampil,et al.  Monitoring depth of anesthesia , 2001, Current opinion in anaesthesiology.

[27]  N Lippman,et al.  Fractal rhythms of the heart. , 1992, Journal of electrocardiology.

[28]  Jaeseung Jeong,et al.  Quantification of emotion by nonlinear analysis of the chaotic dynamics of electroencephalograms during perception of 1/f music , 1998, Biological Cybernetics.

[29]  I. E. Kanounikov,et al.  Comparison of fractal characteristics of the electroencephalogram at schoolchildren 10-12 years old in norm and with difficulties in learning , 1999, IJCNN'99. International Joint Conference on Neural Networks. Proceedings (Cat. No.99CH36339).

[30]  Simon Haykin,et al.  Neural network approaches to image compression , 1995, Proc. IEEE.

[31]  Erik W. Jensen,et al.  EEG complexity as a measure of depth of anesthesia for patients , 2001, IEEE Trans. Biomed. Eng..

[32]  C. M. Lim,et al.  Characterization of EEG - A comparative study , 2005, Comput. Methods Programs Biomed..

[33]  R.J. Roy,et al.  The use of fuzzy integrals and bispectral analysis of the electroencephalogram to predict movement under anesthesia , 1999, IEEE Transactions on Biomedical Engineering.

[34]  I. E. Kanounikov,et al.  Dependence of one of the fractal characteristics (Hurst exponent) of the human electroencephalogram on the cortical area and type of activity , 1999, IJCNN'99. International Joint Conference on Neural Networks. Proceedings (Cat. No.99CH36339).

[35]  Vikram Srinivasan,et al.  EEG BASED AUTOMATED DETECTION OF ANESTHETIC LEVELS USING A RECURRENT ARTIFICIAL NEURAL NETWORK , 2005 .

[36]  R. Acharya U,et al.  Nonlinear analysis of EEG signals at different mental states , 2004, Biomedical engineering online.

[37]  A. Wolf,et al.  Determining Lyapunov exponents from a time series , 1985 .

[38]  Xu-Sheng Zhang,et al.  Depth of anesthesia estimation by adaptive-network-based fuzzy inference system , 1999, Proceedings of the First Joint BMES/EMBS Conference. 1999 IEEE Engineering in Medicine and Biology 21st Annual Conference and the 1999 Annual Fall Meeting of the Biomedical Engineering Society (Cat. N.

[39]  Zheng Chongxun,et al.  A new method to monitor depth of anesthesia based on the autocorrelation EEG signals , 2005, Proceedings. 2005 First International Conference on Neural Interface and Control, 2005..

[40]  Soo-Yong Kim,et al.  Nonlinear Dynamic Analysis of the EEG in Patients with Alzheimer’s Disease and Vascular Dementia , 2001, Journal of clinical neurophysiology : official publication of the American Electroencephalographic Society.

[41]  R. C. Watt,et al.  Human EEG dimensionality and depth of anesthesia , 1994, Proceedings of 16th Annual International Conference of the IEEE Engineering in Medicine and Biology Society.

[42]  Niels Wessel,et al.  Correlation dimension analysis of heart rate variability in patients with dilated cardiomyopathy , 2005, Comput. Methods Programs Biomed..

[43]  L. Johnson,et al.  Bispectrum Analysis of Electroencephalogram Signals during Waking and Sleeping , 1971, Science.

[44]  Daniel Graupe,et al.  A neural-network-based detection of epilepsy , 2004, Neurological research.

[45]  S. Rombouts,et al.  Investigation of EEG non-linearity in dementia and Parkinson's disease. , 1995, Electroencephalography and clinical neurophysiology.