Objective: Cardiotoxicity is an important complication that affects the quality of life of patients with lung cancer after antitumor therapy. This study aimed to develop and validate a nomogram model for predicting the risk of cardiac injury after antitumor therapy in patients with advanced lung cancer. Methods:A total of 404 patients with advanced lung cancer who underwent baseline myocardial enzyme testing at the Affiliated Hospital of North Sichuan Medical College between June 2019 and December 2024 were retrospectively enrolled and randomly assigned to a training cohort and a validation cohort at a ratio of 7:3. Missing data were handled using multiple imputation by chained equations (MICE). In the training cohort, important variables were screened using random forest and extreme gradient boosting (XGBoost) algorithms, and the intersection of the top 12 variables ranked by importance in the two algorithms was selected as candidate predictors. Multivariable logistic regression analysis was then performed, and the results were pooled according to Rubin’s rules to identify independent predictors and construct a nomogram prediction model. The discrimination, calibration, and clinical utility of the model were evaluated using receiver operating characteristic (ROC) curves, calibration curves, the Hosmer–Lemeshow goodness-of-fit test, decision curve analysis (DCA), and clinical impact curves (CICs).Results:XGBoost and random forest algorithms were used to identify the top 12 feature variables ranked by importance, respectively. The intersection of these variables was obtained using a Venn diagram, yielding nine candidate variables. Multivariable logistic regression analysis further identified four independent predictors: age, creatine kinase-MB isoenzyme (CKMB), the neutrophil plus monocyte-to-lymphocyte ratio (NMLR), and serum creatinine (Cr). The nomogram model constructed based on these predictors achieved an area under the receiver operating characteristic curve (AUC) of 0.742 (95% CI: 0.684–0.799) in the training cohort and 0.714 (95% CI: 0.619–0.808) in the validation cohort, indicating good discriminative ability. The calibration curves in both cohorts showed good agreement with the ideal curve, suggesting favorable calibration. Decision curve analysis (DCA) indicated that the model had clinical value for predicting the risk of cardiac injury after antitumor therapy in patients with advanced lung cancer.Conclusion: The prediction model developed in this study can effectively assess the risk of cardiac injury after antitumor therapy in patients with advanced lung cancer. It may provide a useful reference for the early identification of high-risk patients and for developing individualized monitoring and intervention strategies.