An integrated random forest– and LASSO-derived nomogram for predicting postoperative nosocomial infections in colorectal cancer patients

We sought to delineate the independent risk factors underlying postoperative nosocomial infections in colorectal cancer patients and to construct and validate a nomogram for individualized risk prediction, thereby enabling early clinical identification of high-risk individuals and the implementation of targeted preventive strategies. We conducted a retrospective cohort study including 1,760 patients who underwent colorectal cancer surgery between 2020 and 2024. Postoperative nosocomial infection was defined as any hospital-acquired infection occurring within 30 days after surgery, including lower respiratory tract infection, surgical-site infection, multiple-site infections, and other-site infections. Patients admitted in 2020–2022 comprised the training cohort (n = 1,146), and those admitted in 2023–2024 served as a temporal validation cohort (n = 614). Univariable analyses were performed to screen candidate predictors. Predictor importance was ranked using a random forest model, and least absolute shrinkage and selection operator (LASSO) regression with 10-fold cross-validation was applied to reduce overfitting and multicollinearity. Predictors retained after feature selection were entered into multivariable logistic regression to construct a nomogram. Model performance was evaluated by discrimination (AUC), calibration plots, and decision-curve analysis (DCA). Postoperative hospital-acquired infection occurred in 166/1,760 (9.43%) patients. Lower respiratory tract infection was the most common subtype, followed by surgical-site infection. LASSO retained eight predictors with non-zero coefficients, and multivariable logistic regression confirmed that age, coronary heart disease, perioperative blood transfusion, colostomy, surgical approach, ASA grade, persistent fever for 3 consecutive days, and postoperative complications were independently associated with postoperative hospital-acquired infection. The nomogram showed good discrimination, with an AUC of 0.860 in the training cohort and 0.843 in the validation cohort. Calibration was good in the training cohort and acceptable in the validation cohort, with modest deviations at lower predicted probabilities. DCA demonstrated a positive net benefit across a broad range of clinically relevant threshold probabilities in both cohorts. Our nomogram enables precise stratification of colorectal cancer patients by their postoperative infection risk, highlighting perioperative factors—such as operative duration, surgical approach, and ASA grade—that warrant targeted management. Future prospective, multicentre validation will be essential to refine and generalize the model’s applicability.