BMC Medical Informatics and Decision Making (May 2024)
Prediction for post-ERCP pancreatitis in non-elderly patients with common bile duct stones: a cross-sectional study at a major Chinese tertiary hospital (2015–2023)
Abstract
Abstract Background Post-ERCP pancreatitis is one of the most common adverse events in ERCP-related procedures. The purpose of this study is to construct an online model to predict the risk of post-ERCP pancreatitis in non-elderly patients with common bile duct stones through screening of relevant clinical parameters. Methods A total of 919 cases were selected from 7154 cases from a major Chinese tertiary hospital. Multivariable logistic regression model was fitted using the variables selected by the LASSO regression from 28 potential predictor variables. The internal and external validation was assessed by evaluating the receiver operating characteristic curve and the area under curve. Restricted cubic spline modelling was used to explore non-linear associations. The interactive Web application developed for risk prediction was built using the R “shiny” package. Results The incidence of post-ERCP pancreatitis was 5.22% (48/919) and significantly higher in non-elderly patients with female, high blood pressure, the history of pancreatitis, difficult intubation, endoscopic sphincterotomy, lower alkaline phosphatase and smaller diameter of common bile duct. The predictive performance in the test and external validation set was 0.915 (95% CI, 0.858–0.972) and 0.838 (95% CI, 0.689–0.986), respectively. The multivariate restricted cubic spline results showed that the incidence of pancreatitis was increased at 33–50 years old, neutrophil percentage > 58.90%, hemoglobin > 131 g/L, platelet 241.40 × 109/L, total bilirubin > 18.39 umol / L, aspartate amino transferase < 36.56 IU / L, alkaline phosphatase < 124.92 IU / L, Albumin < 42.21 g / L and common bile duct diameter between 7.25 and 10.02 mm. In addition, a web server was developed that supports query for immediate PEP risk. Conclusion The visualized networked version of the above model is able to most accurately predict the risk of PEP in non-elderly patients with choledocholithiasis and allows clinicians to assess the risk of PEP in real time and provide preventive treatment measures as early as possible.
Keywords