Development and validation of a nomogram for predicting 28-day mortality in patients with severe community-acquired pneumonia

Abstract

Severe community-acquired pneumonia (SCAP) progresses rapidly, is associated with poor prognosis. Early assessment and timely intervention are crucial for improving the short-term outcomes of patients this study aims to develop and validate a Nomogram prognostic prediction model for SCAP. Clinical data of 1,316 patients with SCAP from the MIMIC-IV database were used as the training cohort, and 177 patients from the Affiliated Hospital of Soochow University served as the external validation cohort. Candidate variables were selected using LASSO regression, and independent predictors were identified by multivariable logistic regression to construct a nomogram. Model performance was evaluated through the area under the receiver operating characteristic curve (AUC), calibration curves, and decision curve analysis (DCA). The nomogram incorporated six variables, including albumin, total bilirubin, blood urea nitrogen, lactate, age, and the neutrophil-to-lymphocyte ratio (NLR). It showed moderate ability, with an AUC of 0.718 (95% CI, 0.686–0.750) in the training cohort and 0.774 (95% CI, 0.703–0.844) in the validation cohort, both of which were higher than those of the APACHE II. Calibration curves demonstrated good agreement between predicted and observed outcomes, and DCA indicated the potential clinical utility of the nomogram. The NLR-based nomogram developed for predicting 28-day mortality in patients with SCAP showed moderate predictive performance and is simple to apply. After further validation, it may serve as a practical tool for early risk screening and triage.