Prognostic model for acute pancreatitis patients with acute respiratory failure

Acute respiratory failure (ARF) is a frequent complication in patients with acute pancreatitis (AP) and is associated with adverse clinical outcomes. This study aimed to develop a prognostic model for predicting mortality in AP patients complicated by ARF. Data from AP patients diagnosed with ARF were extracted from the Medical Information Mart for Intensive Care-III (MIMIC-III) database. Univariate and multivariate logistic regression analyses were employed to identify risk factors and construct a prognostic model. The predictive performance of the model was assessed using the receiver operating characteristic (ROC) curve. Among the included AP patients with ARF, the 30-day mortality rate was 21.5%. Univariate analysis revealed that older age (p < 0.001), chronic liver disease (p = 0.007), elevated heart rate (p = 0.034), higher red cell distribution width (RDW) (p = 0.018), and increased blood lactate (p = 0.004) were significantly associated with mortality. Multivariate analysis confirmed four independent predictors of mortality: older age (p < 0.001), chronic liver disease (p < 0.001), elevated RDW (p = 0.035), and increased blood lactate (p = 0.002). The final logistic regression model, which incorporated these four variables, demonstrated an area under the ROC curve (AUC) of 0.792. The developed logistic regression model shows good predictive ability and may assist clinicians in assessing the 30-day mortality risk for AP patients with ARF.