Introduction. Endoscopic dextranomer/hyaluronic acid copolymer (DxHA) injection is the most commonly used minimally invasive method of surgical treatment of vesicoureteral reflux (VUR) in children.Purpose of the study. To estimate the accuracy of logistic prognostic models and artificial neural network for prediction a single endoscopic injection DxHA in VUR.Materials and methods. We used endoscopic DxHA in 582 patients (783 ureteric units) of all grades reflux (I - 20, II - 133, III - 443, IV - 187), 53 ureters had complete duplication. A total effectiveness of surgery was 53.2%. A binary logistic regression model and an artificial neural network (multilayer perceptron) were created, taking the following as independent variables: grade of reflux, the patient's age and sex, the ureteral duplication and ureteral dilatation index.Results. The univariate logistic regression showed that the selected predictors were strongly related to the outcome of the treatment. Binary logistic regression and neural network developed high accuracy of the predictions, area under ROC-curve was 0,7 for logistic regression model (a sensitivity of 70.7%, and a specificity of 66.3%) and 0.74 for artificial neural network (a sensitivity of 85.5%, a specificity of 65.3%). Synaptic neural network weights and logistic regression parameters were used in a scoring model to predict the outcome of a single endoscopic injection of DxHA in 2 independent hospitals. An outcomes analysis using predictive models in independent clinics showed a good quality of prediction both with the use of logistic regression (75% and 90% of the correct prognosis) and using a neural network (89.7% and 77% of the correct prediction).Conclusion. An artificial neural network and a binary logistic regression model are an effective tool to assist urologists in identifying and applying endoscopic treatments for VUR in children.
Predicting the outcomes of a single endoscopic correction of vesicoureteral reflux using a dextranomer/hyaluronic acid copolymer: selection of the optimal predictive model
