Prediction of Proximal Ureteral Stones Clearance after Shock Wave Lithotripsy Using an Artificial Neural Network.

Abstract

The cumulative effect of measurable parameters on proximal ureteral stone clearance followed by the shock wave lithotripsy was assessed via the application of an artificial neural network. From January 2015 to January 2020, 1182 patients with upper ureteral stone underwent extracorporeal shock wave lithotripsy (ESWL) with supine position. The corresponding significance of each variable inputted in this network was determined by means of Wilk's generalized likelihood ratio test. If the connection weight of a given variable can be set to zero while maximizing the accuracy of the network classification, the variable is not considered an important predictor of stone removal. A total of 1174 cases (excluding 8 cases) were randomly assigned into a training group (813 cases), testing group (270 cases), and keeping group (91 cases). We evaluated artificial neural network analysis to the stone clearance rate of the training group, with a predictive accuracy of 93.2% (482/517 cases). While the predictive accuracy of the stone clearance rate of the training group was 75.3% (223 cases/296 cases). The order of importance of independent variables was stone length > course (d) > patient's age > Stone Width > PH value. The neural network possess a huge prediction potential for the invalidation of ESWL.