Development and validation of a clinical-ready nomogram for predicting postoperative pulmonary infection after coronary artery bypass grafting.

BACKGROUND: Postoperative pulmonary infection (PPI) remains a significant complication following coronary artery bypass grafting (CABG). This study aimed to identify key risk factors and develop a predictive model to facilitate early risk stratification and individualized intervention strategies. METHOD: We retrospectively reviewed data from 477 patients who underwent CABG at Zhongnan Hospital of Wuhan University between January, 2020, and December, 2025. Patients were randomly assigned to a training cohort (n = 334) and a validation cohort (n = 143) in a 7:3 ratio. A combination of Boruta random forest algorithm and Least Absolute Shrinkage and Selection Operator (LASSO) regression was used to select optimal predictors. Model performance was evaluated using the area under the receiver operating characteristic curve (AUC) for discrimination, the Hosmer-Lemeshow test and calibration curves for calibration, and decision curve analysis (DCA) for clinical utility. RESULT: Six variables were identified as independent predictors: tracheal intubation >24 h, operative duration >10 h, concomitant surgery, intraoperative red blood cell (RBC) transfusion, intraoperative blood loss, and use of intra-aortic balloon pump (IABP). The model demonstrated good discrimination with an AUC of 0·742 (95% CI 0·668-0·817) in the training cohort and 0·745 (95% CI 0·637-0·853) in the validation cohort. Calibration was excellent in both cohorts (training: χ 2 = 6·179, P = 0·630; validation: χ 2 = 4·894, P = 0·770), and DCA indicated significant clinical net benefit across a wide range of threshold probabilities. CONCLUSION: The developed nomogram, based on six readily available clinical variables, provides a robust and intuitive tool for identifying patients at high risk of PPI after CABG. Early quantification of risk may assist clinicians in optimizing perioperative management.