Development and validation of a visual prediction model for severe acute pancreatitis: a retrospective study.

Background: Acute pancreatitis (AP) is a common acute abdominal disease. The early identification of patients at risk of progression to severe AP (SAP) is crucial for developing effective therapeutic and nursing measures. Although many scoring systems exist for SAP risk assessment, none is widely accepted. Systemic inflammatory grade (SIG) is a novel systemic inflammation-based scoring system, but its relationship with AP, as well as the SAP risk prediction model involving SIG, has not been reported. Methodology: The demographic information, clinical data, and laboratory results of patients diagnosed with AP were collected. Baseline comparisons were made using the Wilcoxon rank-sum test, chi-square test and Fisher's exact test. Logistic regression analyses were used to identify independent predictors of SAP; these factors were then used to establish a nomogram model. The model's predictive efficacy and threshold values were evaluated using the receiver operating characteristic (ROC) curve and calibration curve. The decision curve analysis (DCA) and clinical impact curve (CIC) were used to further evaluate the benefit of the model. Results: Five hundred and ninety-two patients aged 18-92 years (median, 43 years) were included. In two stepwise regressions, SIG, C-reactive protein (CRP), prognostic nutritional index (PNI), and white blood cell (WBC) were all considered independent risk factors for SAP ( Conclusion: SIG, CRP, PNI, and WBC represent promising early prognostic markers for severe acute pancreatitis (SAP). A nomogram prediction model utilizing these markers offers effective early prediction for SAP.