Prediction of oculocardiac reflex in strabismus surgery using neural networks

Successfully predicting an oculocardiac reflex (OCR) is difficult to achiev e despite various proposed maneuvers. The aim of this study was to test the models built up by neural networks to predict the occurrence of OCR during strabismus surgery in children. Premedication was not given. Atropine 0.01 mg/kg was medicated just before induction. induction was performed with fe ntanyl or ketorolac, followed by propofol. Atracurium or vecuronium was giv en for intubation. Anesthesia was maintained with O-2-N2O with continuous p ropofol infusion. Chi-square test was performed for induction agents, gende r, weight, muscle blockade, repaired muscle, number of repaired muscles, du ration of operation to detect any association between the occurrence of OCR and to develop the model of neural networks. The multi-layer perceptron, r adial basis function and Bayesian backpropagation network were tested. The occurrence of OCR was significantly associated with gender and repaired mus cle (p<0.05). Gender, repaired muscle and age were considered as input for the multi-layer perceptron, radial basis function and Bayesian backpropagat ion network. Three neural networks had predicted the same correction rate i n the occurrence of OCR as being 87.5% overall among 16 patients' records r ested. These models are conceptually different in predicting compared to co nventional maneuvers, and have the advantage of testing individually and fo retelling the propensity. By comparison neural networks use grouped experie ntial data and predict OCR by the learning rule. Neural networks require a relatively abundant number of experienced and homogenous patients' records to establish an accurate model. The multi-layer perceptron, radial basis fu nction and Bayesian backpropagation modeling network may be an alternative way, and preferable to vagal tone maneuvers if the associated relationships to the occurrence of OCR are more clearly defined.