Purpose: Acute pancreatitis is a common gastrointestinal emergency. Approximately 20% of patients with acute pancreatitis develop organ failure, which is significantly associated with adverse outcomes. This study aimed to establish an early prediction model for persistent organ failure in acute pancreatitis patients using 24-hour admission indicators.
Patients and methods: Clinical data and 24-h laboratory indicators of patients diagnosed with acute pancreatitis from January 1, 2017 to January 1, 2022 in Shanxi Bethune Hospital were collected. Patients from 2017 to 2021 were used as the training cohort to establish the prediction model, and patients from 2021 to 2022 were used as the validation cohort. Univariate logistic regression and LASSO regression were used to establish prediction models. The performance of the model was evaluated using area under the curve (AUC), calibration curves, and decision curve analysis (DCA), and subsequently validated in the validation group.
Results: A total of 1166 patients with acute pancreatitis were included, a total of 145 patients suffered from persistent organ failure from 2017 to 2021. Data were initially selected for 100 variables, and after inclusion and exclusion, 46 variables were used for further analysis. Two prediction models were established and nomogram was drawn respectively. After comparison, the prediction values of the two models were similar (The univariate model AUC was 0.867, 95% CI (0.834-0.9). The LASSO model AUC was 0.864, 95% CI (0.828-0.895)), and the model established by LASSO regression was more parsimonious. A web calculator was developed using the model established by LASSO.
Conclusion: Predictive model including 6 risk indicators can be used to predict the risk of persistent organ failure in patients with acute pancreatitis.
Keywords: LASSO regression; acute pancreatitis; nomogram; organ failure; prediction model.
© 2024 Gao et al.