Monitoring Depth of Anesthesia
This chapter examines the use of complexity analysis, approximate entropy, wavelet transforms, artificial neural networks, fuzzy logic, and neuro-fuzzy method (adaptive network-based fuzzy inference systems) to determine the depth of anesthesia (DOA) of a patient by analyzing mid-latency auditory evoked potentials (MLAEP) and electroencephalograms (EEG). Comparisons are made of the success and computational efficiency of each technique using the data of experimental dogs with different anesthetic modalities.
KeywordsArtificial Neural Network Fuzzy Logic Mean Arterial Pressure Fuzzy Inference System Adaptive Network Base Fuzzy Inference System
Unable to display preview. Download preview PDF.
- Linkens, D.A. (1992), “Adaptive and intelligent control in anesthesia,” IEEE Control Systems, pp. 6–11.Google Scholar
- Huang, J.W., Held, C.M., and Roy, R.J. (1999), “Hemodynamic management with multiple drugs using fuzzy logic,” in Teodorescu, H.-N., Kandel, A., and Jain, L.C. (Eds.), Fuzzy and Neuro-Fuzzy Systems in Medicine, CRC Press (Boca Raton, London, New York, and Washington DC), chapter 11, pp. 319–340.Google Scholar
- Haykin, S. (1994), Neural Networks: a Comprehensive Foundation, New York: Macmillan College Publishing Company.Google Scholar
- Goldmann, L. (1988), “Information processing under general anaesthesia: a review,” I R. Soc. Med., vol. 81, pp. 224–227.Google Scholar
- Klecka, W.R. (1980), Discriminant Analysis, London, Sage Publications.Google Scholar
- Zhang, X.-S. and Roy, R.J. (2000), “Fuzzy knowledge model for estimating the depth of anesthesia,” Proc. of Int. Conf of Artif. Neural Networks in Eng. (ANNIE) 2000, St. Louis, MI.Google Scholar
- Fathi-Torbaghan, M. and Hildebrand, L. (1999), “Complex system analysis using CI methods,” Proc. of the SPIE, vol. 3722, pp. 330341.Google Scholar