The use of artificial neural networks for differential diagnosis between vesicoureteral reflux and urinary tract infection in children

INTRODUCTION: Vesicoureteral reflux (VUR) and urinary tract infection (UTI) are common problem in children. Our goal is to use different models for the clinical decision of differential diagnosis of VUR and UTI in children.
METHODS: This was a retrospective cross-sectional study enrolled 611 pediatric patients. Detailed information for the patients was obtained from hospital records and patient files. Three models including different variables were evaluated via artificial neural network for differential diagnosis of VUR and recurrent UTI. Clinical findings were included in Model 1, clinical and laboratory findings were included in Model 2, and clinical, laboratory and detailed urinary USG findings were included in Model 3. Cross-validation technique was used to evaluate predictive models by partitioning the original sample into a training set to train the model, and a test set to evaluate it.
RESULTS: Of the 611 children, 425 (69.6%) had VUR and 186 (30.4%) had UTI. Sensitivity of Model 1 and Model 2 were 0.682 and 0.856, respectively. Also, Model 3 showed the best performance and high sensitivity with 0.939 for differential diagnosis.
DISCUSSION AND CONCLUSION: Differential diagnosis between VUR and UTI in children can predict with using clinical, laboratory and USG variables via Artificial Neural Network. The model 3 which was including clinical, laboratory and USG variables together is shown the highest performance and sensitivity.