Predicting risk for portal vein thrombosis in acute pancreatitis patients: A comparison of radical basis function artificial neural network and logistic regression models


    loading  Checking for direct PDF access through Ovid

Abstract

Objective:To construct a radical basis function (RBF) artificial neural networks (ANNs) model to predict the incidence of acute pancreatitis (AP)-induced portal vein thrombosis.Methods:The analysis included 353 patients with AP who had admitted between January 2011 and December 2015. RBF ANNs model and logistic regression model were constructed based on eleven factors relevant to AP respectively. Statistical indexes were used to evaluate the value of the prediction in two models.Results:The predict sensitivity, specificity, positive predictive value, negative predictive value and accuracy by RBF ANNs model for PVT were 73.3%, 91.4%, 68.8%, 93.0% and 87.7%, respectively. There were significant differences between the RBF ANNs and logistic regression models in these parameters (P < 0.05). In addition, a comparison of the area under receiver operating characteristic curves of the two models showed a statistically significant difference (P < 0.05).Conclusion:The RBF ANNs model is more likely to predict the occurrence of PVT induced by AP than logistic regression model. D-dimer, AMY, Hct and PT were important prediction factors of approval for AP-induced PVT.HighlightsIt is the first time to establish RBF model for prediction the occurrence of portal vein thrombosis (PVT) following to AP.RBF model is more sensitive, specific and accurate than logistic regression model in prediction the occurrence of PVT.D-dimer, AMY, Hct and PT are the important factors for PVT following to AP concluded by our algorithm.

    loading  Loading Related Articles