Development and validation of a nomogram for predicting 30-day mortality in patients with severe acute pancreatitis and pneumonia

Severe acute pancreatitis (SAP) is associated with high mortality, and pulmonary complications worsen prognosis. However, risk stratification tools for patients with SAP and pneumonia remain underdeveloped. We developed a predictive model for mortality in these patients. A predictive model for early mortality in SAP patients with pneumonia was developed and validated. The training cohort consisted of patients admitted to Xiangya Hospital between April 2017 and May 2021, while external validation used the Medical Information Mart for Intensive Care-IV database. The primary endpoint was 30-day mortality. Predictors were identified using least absolute shrinkage and selection operator regression and incorporated into a nomogram. A total of 220 patients were included, with 30-day mortality of 22.7%. Six predictors were identified: BUN, RDW, age, SBP, HCT, and WBC. Multivariable analysis confirmed BUN and age as independent risk factors and SBP as a protective factor. The nomogram demonstrated good discrimination in the training cohort and moderate discrimination in external validation. The model performed comparably to SOFA and APACHE II scores and outperformed disease-specific scores.We developed and validated a novel prediction model for 30-day mortality in SAP patients with pneumonia, with potential for aiding early risk stratification and clinical decision-making.