Abstract: OBJECTIVE To analyze the factors associated with carbapenem-resistant Acinetobacter baumannii (CRAB) infection in patients with postoperative ventilator-associated pneumonia (VAP) through machine learning methods, thereby providing a basis for understanding the high-risk characteristics of CRAB infection in this population and optimizing infection prevention and control strategies. METHODS We retrospectively included a cohort of patients who developed VAP after surgery and were admitted to the intensive care unit (ICU) at the General Hospital of the Northern Theater Command from 2022 to 2025. The Boruta algorithm combined with least absolute shrinkage and selection operator (LASSO) regression was employed to screen key variables. Based on this, random forest, gradient boosting, light gradient boosting machine, extra trees, support vector machine and logistic regression models were developed. Model performance was evaluated in the test set through the area under the curve (AUC), calibration curve, Brier score and decision curve analysis (DCA). The optimal model was interpreted through the Shapley Additive Explanations (SHAP). RESULTS A total of 894 patients with VAP were enrolled, with a CRAB infection rate of 44.85%. Ten variables, including length of hospital stay, duration of central venous catheter placement, duration of ventilator use and carbapenem antibiotic use, were ultimately included. The AUC values of the models ranged from 0.846 to 0.864. The random forest model showed the highest AUC (0.864, 95% CI: 0.817-0.904) and the best calibration performance (Brier=0.150), and achieved a high clinical net benefit within the threshold probability range of 0.1-0.8. SHAP analysis revealed that the duration of central venous catheter placement, duration of ventilator use, length of ICU stay and carbapenem antibiotic use were the primary associated factors. CONCLUSIONS Machine learning results indicate that the duration of central venous catheter placement, days of mechanical ventilation, length of ICU stay and exposure to carbapenem antibiotics are core factors associated with CRAB infection in postoperative VAP patients. These findings provide a basis for identifying key infection prevention and control priorities and formulating strategies for this population.