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

Purpose: 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.& para;& para;Methods: 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.& para;& para;Results: 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.& para;& para;Conclusion: 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. (C) 2016 Published by Elsevier Masson SAS.