Assessment of depth of anesthesia using principal component analysis


A new approach to estimating level of uncon-sciousness based on Principal Component Analysis (PCA) is proposed. The Electroen-cephalogram (EEG) data was captured in both Intensive Care Unit (ICU) and operating room, using different anesthetic drugs. Assuming the central nervous system as a 20-tuple source, window length of 20 seconds is applied to EEG. The mentioned window is considered as 20 nonoverlapping mixed-signals (epoch). PCA algorithm is applied to these epochs, and larg-est remaining eigenvalue (LRE) and smallest remaining eigenvalue (SRE) were extracted. Correlation between extracted parameters (LRE and SRE) and depth of anesthesia (DOA) was measured using Prediction probability (PK). The results show the superiority of SRE than LRE in predicting DOA in the case of ICU and isoflurane, and the slight superiority of LRE than SRE in propofol induction. Finally, a mixture model containing both LRE and SRE could predict DOA as well as Relative Beta Ratio (RBR), which expresses the high capability of the proposed PCA based method in estimating DOA.

Share and Cite:

Taheri, M. , Ahmadi, B. , Amirfattahi, R. and Mansouri, M. (2009) Assessment of depth of anesthesia using principal component analysis. Journal of Biomedical Science and Engineering, 2, 9-15. doi: 10.4236/jbise.2009.21002.

Conflicts of Interest

The authors declare no conflicts of interest.


[1] R. D. Miller, (2005) Miller’s Anesthesia, Sixth edition, Elsevier Churchill Livingstone, 1227-1264.
[2] E. Freye and J. V. Levy, (2005) “Cerebral monitoring in the op-erating room and the intensive care unit: An introductory for the clinician and a guide for the novice wanting to open a window to the brain. Part I: The electroencephalogram”, J Clin Monit Com-put, 1-76.
[3] L. C. Jameson and T.B. Sloan, (2006) “Using EEG to monitor anesthesia drug effects during surgery”, J Clin Monit Comput, 445-472.
[4] I. J. Rampil, (1998) “A primer for EEG signal processing in an-esthesia”, Anesthesiology, 980-1002.
[5] H. S. Traast and C. J. Kalkman, (1995) “Electroencephalographic Characteristics of emergence from propofol/sufentanil total in-travenous anesthesia”, Anesth Analg, 366-371.
[6] T. Zikov, S. Bibian, G. A. Dumont, M. Huzmezan, and C. R. Ries, (2006) “Quantifying cortical activity during general anesthesia using wavelet analysis”, IEEE Trans. Biomed. Eng., Vol. 53, No. 4, 617-632.
[7] R. Ferenets, T. Lipping, A. Anier, V. Jantti, S. Melto, and S. Hovilehto, (2006) "Comparison of entropy and complexity meas-ures for the assessment of depth of sedation? IEEE Trans. Bio-med. Eng., Vol. 53, No. 6, 1067-1077.
[8] C. Robert, P. Karasinski, C. D. Arreto, and J. F. Gaudy, (2002) “Monitoring Anesthesia using neural networks: A survey”, J Clin. Monit. Comput, Vol. 17, 259-267.
[9] V. Lalitha and C. Eswaran, (2007) “Automated Detection of Anesthetic Depth Levels Using Chaotic Features with Artificial Neural Networks”, J Med Syst, 445-452.
[10] R. Bender, B. Schultz, and U. Grouven, (1992) “Classification of EEG signals into general stages of anesthesia in real time using autoregressive models”, Conf Proc of the 16th Annual Confer-ence of the Gesellschaft fur Klassifikatione, University of Dort-mund.
[11] D. R. Drover, H. J. Lemmens, E. T. Pierce, et al, (2002) “Patient State Index: titration of delivery and recovery from propofol, alfentanil, and nitrous oxide anesthesia”, Anesthesiology, 82-89.
[12] J. V. Stone, (2004) Independent Component Analysis: A Tutorial Introduction, Bradford Book.
[13] K. I. Diamantaras and S. Y. Kung, (1996) Principal Component Neural Networks. Theory and Applications, Adaptive and Learn-ing Systems for Signal Processing, Communications and Control, John Wiley & Sons Inc., New York.
[14] M. Turk and A. Pentland, (1991) “Eigenfaces for recognition”, Journal of Cognitive Neuroscience, 71-86.
[15] S. Y. Kung, K. Diamantaras, and J. Taur. (1991) “Neural net-works for extracting pure/constrained/oriented principal compo-nents. In J. R. Vaccaro, editor”, SVD and Signal Processing El--sevier Science, Amsterdam, 57-81.
[16] M. P. S. Chawla, (2008) “A comparative analysis of principal component and independent component techniques for electro-cardiograms”, Neural Computing & Applications.
[17] Hyv¨arinen, A., J. Karhunen, and E. Oja, (2001) Independent Component Analysis., John Wiley & Sons Inc., New York.
[18] R. Vigario, V. Jousmaki, M. Hamalainen, R. Hari, and E. Oja, (1998) "Independent component analysis for identification of ar-tifacts in magnetoencephalographic recordings? In Advances in Neural Information Processing Systems, MIT Press, Vol. 10, 229-235.
[19] S. Makeig, A. J. Bell, T. P. Jung, and T. Sejnowski, (1996) “In-dependent component analysis of electroencephalographic data”, Advances in Neural Information Processing Systems, MIT Press, Vol. 8, 145-151.
[20] G. D. Brown, S. Yamada, and T. J Sejnowski, (2001) “Independ-ent components analysis (ica) at the neural cocktail party”, Trends in neuroscience, Vol. 24, 54-63.
[21] P. O. Hoyer and A. Hyv¨arinen, (2000) “Independent compo-nent analysis applied to feature extraction from colour and stereo images”, Network: Computation in Neural Systems, Vol. 11, 191-210.
[22] Parra, L., C. D. Spence, P. Sajda, A. Ziehe, and K.-R. M¨uller, (2000) Unmixing hyperspectral data. In Advances in Neural In-formation Processing Systems 12, MIT Press, 942-948.
[23] S. Hagihira, M. Takashina, T. Mori, T. Mashimo, and I. Yoshiya, (2001) “Practical issues in bispectral analysis of electroencepha-lographic signals”, Anesth Analg, Vol. 93, 966-970.

Copyright © 2023 by authors and Scientific Research Publishing Inc.

Creative Commons License

This work and the related PDF file are licensed under a Creative Commons Attribution 4.0 International License.