Building and verifying a severity prediction model of acute pancreatitis (AP) based on BISAP, MEWS and routine test indexes

Abstract

To discuss the value of the Bedside Index for Severity in Acute Pancreatitis (BISAP), Modified Early Warning Score (MEWS), serum Ca2+, similarly hereinafter, and red cell distribution width (RDW) for predicting the severity grade of acute pancreatitis and to develop and verify a more accurate scoring system to predict the severity of AP. In 302 patients with AP, we calculated BISAP and MEWS scores and conducted regression analyses on the relationships of BISAP scoring, RDW, MEWS, and serum Ca2+ with the severity of AP using single-factor logistics. The variables with statistical significance in the single-factor logistic regression were used in a multi-factor logistic regression model; forward stepwise regression was used to screen variables and build a multi-factor prediction model. A receiver operating characteristic curve (ROC curve) was constructed, and the significance of multi- and single-factor prediction models in predicting the severity of AP using the area under the ROC curve (AUC) was evaluated. The internal validity of the model was verified through bootstrapping. Among 302 patients with AP, 209 had mild acute pancreatitis (MAP) and 93 had severe acute pancreatitis (SAP). According to single-factor logistic regression analysis, we found that BISAP, MEWS and serum Ca2+ are prediction indexes of the severity of AP (P-value<0.001), whereas RDW is not a prediction index of AP severity (P-value>0.05). The multi-factor logistic regression analysis showed that BISAP and serum Ca2+ are independent prediction indexes of AP severity (P-value<0.001), and MEWS is not an independent prediction index of AP severity (P-value>0.05); BISAP is negatively related to serum Ca2+ (r=-0.330, P-value<0.001). The constructed model is as follows: ln()=7.306+1.151*BISAP-4.516*serum Ca2+. The predictive ability of each model for SAP follows the order of the combined BISAP and serum Ca2+ prediction model>Ca2+>BISAP. There is no statistical significance for the predictive ability of BISAP and serum Ca2+ (P-value>0.05); however, there is remarkable statistical significance for the predictive ability using the newly built prediction model as well as BISAP and serum Ca2+ individually (P-value<0.01). Verification of the internal validity of the models by bootstrapping is favorable. BISAP and serum Ca2+ have high predictive value for the severity of AP. However, the model built by combining BISAP and serum Ca2+ is remarkably superior to those of BISAP and serum Ca2+ individually. Furthermore, this model is simple, practical and appropriate for clinical use.