Nothing Special   »   [go: up one dir, main page]
Skip to main content

Advertisement

Springer Nature Link
Log in

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

  • Published:
Journal of Medical Systems Aims and scope Submit manuscript

Abstract

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.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Subscribe and save

Springer+ Basic
$34.99 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6

Similar content being viewed by others

References

  1. Zhang, X. S., Roy, R. J., and Jensen, E. W., EEG complexity as a measure of depth of Anesthesia for patients. IEEE Trans. Biomed. Eng. 48(12):1424–1433, 2001.

    Article  Google Scholar 

  2. Lianyi, Z., and Chongxun, Z., A new method to monitor depth of anesthesia based on the autocorrelation EEG signals. Proc International conference on Neural Interface and Control; 26–28 May, 123–126, 2005.

  3. Krikic, M., Roberts, S. J., Rezek, I. A., et al., EEG-based assessment of anesthetic-depth using neural networks. Proc IEE Colloquium Artif Intel Methods Biosignal Analysis 100(10):1–6, 1996, Apr.

    Google Scholar 

  4. Zhang, X. S., and Roy, R. J., Depth of Anesthesia estimation by adaptive network based fuzzy inference system. Proc of BMES/EMBS Conference; Oct 13–16, ’99: 391.

  5. Zhang, X. S., and Roy, R. J., Predicting movement during anesthesia by complexity analysis of the EEG. Med. Biol. Eng. Comput. 37:327–334, 1999.

    Article  Google Scholar 

  6. Stanski, D. R., Monitoring depth of anesthesia. In: Miller, R. D., (Ed.), Anesthesia. New York: Churchill Livingstone, 1127–1159, 1994.

    Google Scholar 

  7. Rampil, I. J., A primer, EEG signal processing in anesthesia. Anesthesiology 89:980–1002, 1998.

    Article  Google Scholar 

  8. Thomsen, C. E., Christensen, K. N., and Rosenflack, A., Computerized monitoring of depth of anesthesia with isoflurane. British Journal of Anaesthesia 63:36–43, 1989.

    Article  Google Scholar 

  9. Sharma, A., and Roy, R. J., Design of a recognition system to predict movement during anesthesia. IEEE Trans. Biomed. Eng. 44:505–511, 1997, June.

    Article  Google Scholar 

  10. Widman, G., Schreiber, T., Rehberg, B., et al., Quantification of depth of anesthesia by nonlinear time series analysis of brain electrical activity. Phys. Rev. E 62:4898–4903, 2000.

    Article  Google Scholar 

  11. Drummond, J. C., Brann, C. A., Perkins, D. E., 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. Acta Anaesthesiol. Scand. 35:693–699, 1991.

    Article  Google Scholar 

  12. Muthuswamy, J., and Roy, R. J., The use of fuzzy integrals and bispectral analysis of the electroencephalogram to predict movement under anesthesia. IEEE Trans. Biomed. Eng. 46(3):291–302, 1999.

    Article  Google Scholar 

  13. Barnett, T. P., Johnson, L. C., Naitoh, P., Nicks, H., and Nute, C., Bispectrum analysis of electroencephalogram signals during waking and sleeping. Science 22:501–513, 1994.

    Google Scholar 

  14. Hazarika, N., Tsoi, A. C., and Sergejew, A. A., Nonlinear considerations in EEG signal classification. IEEE Trans. Signal Process. 45(4):829–836, 1997.

    Article  Google Scholar 

  15. Jaesesung, J., Joung, M. K., and Kim, S. Y., Quantification of emotion by nonlinear analysis of the chaotic dynamics of electroencephalograms during perception of 1/f music. Biol. Cybern. 78:217–225, 1998.

    Article  Google Scholar 

  16. Kannathal, N., Acharya, U. R., Fadilah, A., Thelma, T., and Sadasivan, K., Nonlinear analysis of EEG signals at different mental states. Biomed. Eng. Online 3:7, 2004.

    Article  Google Scholar 

  17. Jaesesung, J., Ho, C. J., Kim, S. Y., and Seol-Heui, H., Nonlinear dynamical analysis of the EEG in patients with Alzheimer’s disease and vascular dementia. Clin. Neurophysiol. 18(1):58–67, 2001.

    Article  Google Scholar 

  18. Xu, J., Zheng, C., Jing, G., and Lu, D., Monitoring depth of anesthesia based on complexity of electroencephalogram. IEEE International Workshop on Biomedical Circuits and Systems, 2004, pp. S2/5-9–12 26, Dec. 2004.

  19. Watt, R. C., Springfield, C. L., Maslana, E. S., Kanemoto, A. Mylrea, K., Human EEG dimensionality and depth of anesthesia, engineering advances: new opportunities for biomedical engineers. Proceedings of the 16th Annual International Conference of the IEEE EMBS 1994, 223–224 vol. 27, Nov 1994.

  20. Carvajal, R., Wessel, N., Vallverdu, M., Caminal, P., and Voss, A., Correlation dimension analysis of heart rate variability in patients with dilated cardiomyopathy. Comput. Methods Programs Biomed. 78:133–140, 2005.

    Article  Google Scholar 

  21. Hoyer, D., Schmidt, K., Bauer, R., Zwiener, U., Kohler, M., Luthke, B., and Eiselt, M., Nonlinear analysis of heart rate and respiratory dynamics. IEEE Eng. Med. Biol. Mag. 16(1):31–39, 1997.

    Article  Google Scholar 

  22. Stein, K. M., Lippman, N., and Kligfield, P., Fractal rhythms of the heart. J. Electrocardiol. 24:72–76, 1992.

    Google Scholar 

  23. Hornero, R., Espino, P., Alonso, A., and Lopez, M., Estimating complexity from EEG background activity of epileptic patients. IEEE Eng. Med. Biol. Mag. 18(6):73–79, 1999.

    Article  Google Scholar 

  24. Stam, C. J., Jelles, B., Achtereekte, H. A. M., Rombouts, S. A. R. B., Slaets, J. P. J., and Keunen, R. W. M., Investigation of EEG non-linearity in dementia and Parkinson’s disease. Electroencephalogr. Clin. Neurophysiol. 95:309–317, 1995.

    Article  Google Scholar 

  25. Taigang, H. E., Chongxun, Z., and Dazong, J., Detecting nonlinearity in multichannel epileptic EEG. In: Proceedings of the 19th Annual EMBS International Conference. Vol. 3. 1202–1204, 1997, October.

  26. Das, A., Das, P., and Roy, A. B., Applicability of Lyapunov exponent in EEG data analysis. Complex. Int. 9, 2002.

  27. Qian, B., and Rasheed, K., Hurst exponent and financial market predictability. In: Proceedings of The 2nd IASTED international conference on financial engineering and applications. Cambridge, MA, USA, 203–209, 2004.

  28. Kanounikov, I. E., Antonova, E. V., Kiselev, B. V., and Belov, D. R., Dependence of one of the fractal characteristics (Hurst Exponent) of the human electroencephalogram on the cortical area and type of Activity.

  29. Acharya, U. R., Kannathal, N., Faust, O., et al., Nonlinear analysis of EEG signals at various sleep stages. Comput. Methods Programs Biomed. 80:37–45, 2005.

    Article  Google Scholar 

  30. Ellis, C., The sampling properties of Hurst exponent estimates. Physica A, 2006, DOI 10.1016/j.physica.2006.08.046.

  31. Srinivasan, V., Eswaran, C., and Sriraam, N., EEG based automated detection of anesthetic levels using a recurrent artificial neural network. Int. J. Bioelectromagn. (IJBEM) 7(2):267–270, 2005, Tampere, Finland.

    Google Scholar 

  32. Grassberger, P., and Pracaccia, I., Characterization of strange attractors. Phys. Rev. Lett. 50:346–349, 1983.

    Article  MathSciNet  Google Scholar 

  33. Wolf, A., Swift, J. B., Swinney, L. H., and Vastano, J. A., Determining Lyapunov exponent from a time series. Physica D. 16:285–317, 1985.

    Article  MATH  MathSciNet  Google Scholar 

  34. Fell, J., Rochke, J., and Beckmann, P., The calculation of the first positive Lyapunov exponent in sleep EEG data. Electroencephalogram Clinical Neurophysiology 86:348–352, 1993.

    Article  Google Scholar 

  35. Kanounikov, I. E., and Antonova, E. V., Comparison of fractal characteristics of the electroencephalogram at schoolchildren 10–12 years old in norm and with difficulties in learning, In: Proceedings of International Joint Conference on Neural Networks. Vol. 1. 239–242, 1999, July.

  36. Bassingthwaighte, J. B., and Raymond, G. M., Evaluating rescaled range analysis for time series. Ann. Biomed. Eng. 22(4):432–444, 1994, Jul–Aug.

    Article  Google Scholar 

  37. DePetrillo, P. B., et al., Determining the Hurst exponent of fractal time series and its application to electrocardiographic analysis. Comput. Biol. Med. 29(6):393–406, 1999, November.

    Article  Google Scholar 

  38. Kannathal, N., Rajendra Acharya, U., Lim, C. M., and Sadasivan, P. K., Characterization of EEG—a comparative study. Comput. Methods Programs Biomed. 80(1):17–23, 2005, October.

    Article  Google Scholar 

  39. Dony, D., and Haykin, S., Neural network approaches to image compression. Proc. IEEE 83:288–303, 1995.

    Article  Google Scholar 

  40. Nigam, V. P., and Graupe, D., A neural-network-based detection of epilepsy. Neurol. Res. 26:55–60, 2004.

    Article  Google Scholar 

  41. Tsoi, A. C., So, D. S. C., and Sergejew, A., Classification of electroencephalogram using artificial neural networks. Adv. Neural Inf. Process. Syst. 6:1151–1158, 1994.

    Google Scholar 

  42. Graupe, D., Principles of artificial neural networks. World Scientific Press: Singapore, 1997.

    Google Scholar 

  43. Demuth, H., and Beale, M., Neural network toolbox (for use with Matlab) Math works. Natick, Massachusetts, 2000.

  44. Rajasekaran, S., Pai, G., and Vijayalakshmi, A., Neural networks, fuzzy logic and genetic algorithms. Prentice Hall: India, 2003.

    Google Scholar 

  45. Davidson, Bill, Matlab program for Hurst exponent, October 2003.

Download references

Author information

Authors and Affiliations

  1. Faculty of Information Technology, Multimedia University, Cyberjaya, Malaysia

    V. Lalitha

  2. Center for Multimedia Computing, Faculty of Information Technology, Multimedia University, Cyberjaya, Malaysia

    C. Eswaran

Authors
  1. V. Lalitha
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. C. Eswaran
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to V. Lalitha.

Rights and permissions

Reprints and permissions

About this article

Cite this article

Lalitha, V., Eswaran, C. Automated Detection of Anesthetic Depth Levels Using Chaotic Features with Artificial Neural Networks. J Med Syst 31, 445–452 (2007). https://doi.org/10.1007/s10916-007-9083-y

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s10916-007-9083-y

Keywords

Search

Navigation