Abstract
This study was undertaken to determine whether artificial neural network (ANN) processing of mid-latency auditory evoked potentials (MLAEPs) can identify different anesthetic states during propofol anesthesia, and to determine those parameters that are most useful in the identification process. Twenty-one patients undergoing elective abdominal surgery were studied. To maintain general anesthesia, the patients received propofol (3–5 mg kg−1 h−1 intravenously). Epidural analgesia at the level of T4-5 blocked painful stimuli. MLAEP was recorded continuously with patients awake, during induction, during maintenance of general anesthesia, and during emergence until the patients were recovered from anesthesia. Latencies of the 5 MLAEP peaks and three peak to peak amplitudes were measured, along with hemodynamic parameters (heart rate, systolic, and diastolic arterial blood pressure). Four-layer ANNs were used to model the relationship between the parameters of the MLAEP and the four different states (awake, adequate anesthesia, during/before intraoperative movement, and emergence from anesthesia). The best identification accuracy was obtained using only the five latencies. The combination of five latencies and three amplitudes did not improve the identification accuracy. Use of the only the three hemodynamic parameters produced a much poorer identification. This study suggests that the MLAEP has useful information for identifying different anesthetic states, especially in its latencies. A nonlinear discrimination approach, such as the ANN, can effectively capture the relation between the MLAEP patterns and the different states of anesthesia. © 2001 Biomedical Engineering Society.
PAC01: 4364Ri, 8719Nn, 8719Uv, 8780Tq, 8719Hh, 8780Xa
Similar content being viewed by others
REFERENCES
Blitt, C. D., and R. L. Hines. Monitoring in Anesthesia and Critical Care Medicine, 3rd ed. Churchill Livingstone, 1995, p. 429.
Davies, F. W., H. Mantzaridis, G. N. C. Kenny, and A. C. Fisher. Middle latency auditory evoked potentials during re-peated transitions from consciousness to unconsciousness. Anaesthesia 51:107–113, 1996.
Doi, M., R. J. Gajraj, H. Mantzaridis, and G. N. C. Kenny. Relationship between calculated blood concentration of pro-pofol and electrophysiological variables during emergence from anaesthesia: Comparison of bispectral index, spectral edge frequency, median frequency and auditory evoked po-tential index. Br. J. Anaesth. 78:180–184, 1997.
Drummond, J. C. Monitoring depth of anesthesia. Anesthesi-ology93:876–882, 2000.
Dutton, R. C., W. D. Smith, I. J. Rampil, B. S. Chortkoff, and E. I. Eger. Forty-hertz midlatency auditory evoked po-tential activity predicts wakeful response during desflurane and propofol anesthesia in volunteers. Anesthesiology 91:209–220, 1999.
Evans, J. M., Clinical signs and autonomic responses. In: Consciousness, Awareness and Pain in General Anaesthesia, edited by M. Rosen, and J. N. Lunn. London: Butterworth, 1987, pp. 184–192.
Fiset, P., L. Mathers, R. Engstrom, D. Fitzgerald, S. C. Brand, F. Hsu, and S. L. Shafer. Pharmacokinetics of computer-controlled alfentanil administration in children un-dergoing cardiac surgery. Anesthesiology 83:944–955, 1995.
Hansson, M., T. Gansler, and G. Salomonsson. A system for tracking changes in the midlatency evoked potential during anesthesia. IEEE Trans. Biomed. Eng. 45:323–334, 1998.
Haykin, S. Neural Networks: A Comprehensive Foundation. New York: Macmillan College Publishing Company, 1994, pp. 138–235.
Highleyman, W. H. The design and analysis of pattern rec-ognition experiments. Bell Syst. Tech. J. 41:723–744, 1962.
Huang, J. W., Y-Y. Lu, A. Nayak, and R. J. Roy. Depth of anesthesia estimation and control. IEEE Trans. Biomed. Eng.46:71–81, 1999.
Iselin-Chaves, I. A., H. El Moalem, T. J. Gan, B. Ginsberg, S. R. N. Dufore, and P. S. A. Glass. Changes in the auditory evoked potentials and the bispectral index following propofol or propofol and alfentanil. Anesthesiology 92:1300–1310, 2000.
Leon, M. A., and J. Rasanen. Neural network-based detection of esophageal intubation in anesthetized patients. J. Clin. Monit. 12:165–169, 1996.
Madler, C., I. Keller, D. Schwender, and E. Poppel. Sensory information processing during general anesthesia. Effect of isoflurane on auditory evoked neuronal oscillations. Anaes-thesia66:81–87, 1991.
Mirchandani, G. and W. Cao. On hidden nodes for neural nets. IEEE Trans. Circuits Syst. 36:661–664, 1989.
Mylrea, K. C., J. A. Orr, and D. R. Westenskow. Integration of monitoring for intelligent alarms in anesthesia: Neural networks-can they help? J. Clin. Monit. 9:31–37, 1993.
Nayak, A., and R. J. Roy. Anesthesia control using midla-tency auditory evoked potentials. IEEE Trans. Biomed. Eng.45:409–421, 1998.
Schraag, S., U. Bothner, R. Gajraj, G. N. Kenny, and M. Georgieff. The performance of electroencephalogram bispec-tral index and auditory evoked potential index to predict loss of consciousness during propofol infusion. Anesth. Analg.89:1311–1315, 1999.
Schwender, D., M. Daunderer, S. Mulzer, S. Klasing, U. Finsterer, and K. Peter. Midlatency auditory evoked poten-tials predict movements during anesthesia with isoflurane or propofol. Anesth. Analg. 85:164–173, 1997.
Schwender, D., A. Kaiser, S. Klasing, K. Peter, and E. Pop-pel. Midlatency auditory evoked potentials and explicit and implicit memory in patients undergoing cardiac surgery. An-esthesiology80:493–501, 1994.
Schwender, D., E. Weninger, M. Daunderer, S. Klasing, E. Poppel, and K. Peter. Anesthesia with increasing doses of sufentanil and midlatency auditory evoked potentials in hu-mans. Anesth. Analg. 80:499–505, 1995.
Sharma, A. and R. J. Roy. Design of a recognition system to predict movement during anesthesia. IEEE Trans. Biomed. Eng. 44:505–511, 1997.
Thornton, C. Evoked potentials in anaesthesia. Eur. J. Anes-thesiol.8:89–107, 1991.
Thornton, C., P. Creagh-Barry, and C. Jordan. Somatosen-sory and auditory evoked responses recorded simultaneously: Differential effects of nitrous oxide and isoflurane. Br. J. Anaesth. 68:508–514, 1992.
Thornton, C., M. P. Barrowcliffe, K. M. Konieczko, P. Ventham, C. J. Dove, D. E. F. Newton, and C. J. Jones. The auditory evoked response as an indicator of awareness. Br. J. Anaesthesia 63:113–115, 1989.
Thornton, C., K. M. Konieczko, J. G. Jones, C. Jordan, C. J. Dove, and C. P. H. Heneghan. Effect of surgical stimulation on the auditory evoked response. Br. J. Anaesthesia 60:372–378, 1988.
Vogel, M. A. and A. K. C. Wong. PFS clustering method. IEEE Trans. Pattern Anal. Mach. Intell. 1:237–245, 1979.
Author information
Authors and Affiliations
Rights and permissions
About this article
Cite this article
Zhang, XS., Roy, R.J., Schwender, D. et al. Discrimination of Anesthetic States using Mid-Latency Auditory Evoked Potential and Artificial Neural Networks. Annals of Biomedical Engineering 29, 446–453 (2001). https://doi.org/10.1114/1.1366673
Issue Date:
DOI: https://doi.org/10.1114/1.1366673