Determining the Amount of Anesthetic Medicine to Be Applied by Using Elman’s Recurrent Neural Networks via Resilient Back Propagation
作者： Rüştü Güntürkün
DOI: 10.1007/S10916-009-9262-0
关键词:
摘要: In this study, Elman recurrent neural networks have been defined by using Resilient Back Propagation in order to determine the depth of anesthesia continuation stage and estimate amount medicine be applied at that moment. From 30 patients, 57 distinct EEG recordings collected prior during anaesthesia different levels. The artificial network is composed three layers, namely input layer, middle layer output layer. nonlinear activation function sigmoid (sigmoid function) has used hidden Prediction made means ANN. Training testing ANN previous amount, total power/normal power power/previous. system able correctly purposeful responses average accuracy 95% cases. This method also computationally fast acceptable real-time clinical performance obtained.
springer.com
sci-hub.se 参考文章(14)
Liyu Huang, Weirong Wang, Sekou Singare, Using Back Propagation Feedback Neural Networks and Recurrence Quantification Analysis of EEGs Predict Responses to Incision During Anesthesia Lecture Notes in Computer Science. pp. 364- 373 ,(2006) , 10.1007/11881223_45
F.H. Lopes da Silva, EEG analysis: Theory and Practice Electroencephalography: Basic Principles, Clinical Applications and Related Fields, 4th edition. pp. 1135- 1163 ,(1998)
Ali Aydın Altunkan, Ülkü Çömelekoğlu, Zeliha Özer Koçak, Aynur Özge, Şebnem Atıcı, Uğur Oral, None, Hemodynamic effect of remifentanil on stress response to tracheal intubation: correlations with quantitative EEG analysis - Klinik Psikofarmakoloji Bulteni-bulletin of Clinical Psychopharmacology. ,vol. 11, pp. 235- 241 ,(2001)
P.A. ISAAC, M. ROSEN, LOWER OESOPHAGEAL CONTRACTILITY AND DETECTION OF AWARENESS DURING ANAESTHESIA BJA: British Journal of Anaesthesia. ,vol. 65, pp. 319- 324 ,(1990) , 10.1093/BJA/65.3.319
F Temurtas, R Gunturkun, N Yumusak, H Temurtas, None, Harmonic detection using feed forward and recurrent neural networks for active filters Electric Power Systems Research. ,vol. 72, pp. 33- 40 ,(2004) , 10.1016/J.EPSR.2004.02.005
I.F. RUSSELL, COMPARISON OF WAKEFULNESS WITH TWO ANAESTHETIC REGIMENS BJA: British Journal of Anaesthesia. ,vol. 58, pp. 965- 968 ,(1986) , 10.1093/BJA/58.9.965
Y. Si, J. Gotman, A. Pasupathy, D. Flanagan, B. Rosenblatt, R. Gottesman, An expert system for EEG monitoring in the pediatric intensive care unit Electroencephalography and Clinical Neurophysiology. ,vol. 106, pp. 488- 500 ,(1998) , 10.1016/S0013-4694(97)00154-5
J. Muthuswamy, R.J. Roy, The use of fuzzy integrals and bispectral analysis of the electroencephalogram to predict movement under anesthesia IEEE Transactions on Biomedical Engineering. ,vol. 46, pp. 291- 299 ,(1999) , 10.1109/10.748982
R.P. Brent, Fast training algorithms for multilayer neural nets IEEE Transactions on Neural Networks. ,vol. 2, pp. 346- 354 ,(1991) , 10.1109/72.97911
Christopher J James, Richard D Jones, Philip J Bones, Grant J Carroll, Detection of epileptiform discharges in the EEG by a hybrid system comprising mimetic, self-organized artificial neural network, and fuzzy logic stages Clinical Neurophysiology. ,vol. 110, pp. 2049- 2063 ,(1999) , 10.1016/S1388-2457(99)00168-6