Nomogram for predicting prognostic risk in severe pulmonary tuberculosis: a retrospective analysis from the MIMIC-IV database.

BACKGROUND

The treatment of severe pulmonary tuberculosis (PTB) remains challenging, highlighting the need for prognostic tools. This study aimed to establish and validate a nomogram for predicting overall survival (OS) of PTB patients in the intensive care unit (ICU).

METHODS

A retrospective analysis was performed using the Medical Information Mart for Intensive Care IV (MIMIC-IV) database. A total of 1,105 PTB patients were identified and randomly divided into training and validation cohorts. Least absolute shrinkage and selection operator (LASSO) regression was applied for variable selection, followed by Cox regression to construct a predictive model. A nomogram was developed based on the selected predictors. Model performance was assessed by receiver operating characteristic (ROC) curves, calibration plots, and decision curve analysis (DCA).

RESULTS

Eight predictors were identified: age, Acute Physiology Score (APS) III, partial pressure of oxygen (PO2), mean heart rate, mean temperature, platelet (PLT), albumin (ALB), and red blood cell (RBC) count. A nomogram was constructed to predict survival at 28, 180, and 365 days. The concordance index (C-index), area under the curve (AUC), and calibration plots showed good discrimination and calibration in both cohorts. Compared with APS III, the model demonstrated higher net reclassification improvement (NRI) and integrated discrimination improvement (IDI), confirming its superior clinical utility.

CONCLUSIONS

We developed and validated a prognostic nomogram integrating eight clinical variables to predict survival in ICU patients with PTB. This tool may assist clinicians in early risk stratification and personalized management.