Development of a nomogram for predicting radiation‑induced pneumonia in patients with lung cancer undergoing close‑range radiotherapy with radioactive I particles.

The most common and potentially fatal side effect of postoperative radiotherapy using radioactive I particles in the chest is radiation-induced pneumonia (RP). The present study aimed to develop a nomogram to accurately predict RP in patients with lung cancer following this type of radiotherapy. A retrospective analysis was conducted on data from 436 patients with advanced lung cancer who underwent close-range radiotherapy using radioactive I particles at the General Hospital of Northern Theater Command from January 2016 to December 2023 (Shenyang, China). Risk factors for RP were identified through least absolute shrinkage and selection operator logistic regression and multivariable logistic regression analysis. These factors were then used to construct a dynamic nomogram. The predictive performance of the nomogram was validated using receiver operating characteristic (ROC) curves, calibration plots, and decision curve analysis. Additionally, the grading of RP and Kaplan-Meier analysis were performed. Preoperative N and M staging, the maximum dose and whether chemotherapy was administered were identified as significant predictors of RP. A dynamic nomogram for predicting RP was developed based on these risk factors. The area under the ROC curve was 0.878 (95% CI, 0.814-0.942) for the training cohort and 0.828 (95% CI, 0.787-0.870) for the validation cohort, indicating favorable discriminatory ability. The nomogram demonstrated excellent calibration. In both cohorts, the maximum dose parameter provided the most significant clinical benefits, supporting its promising clinical utility. Patients staged as T and T preoperatively were more likely to develop RP compared with those staged as T (P<0.001). Likewise, patients staged as M preoperatively, those receiving a maximum dose above the mean, and those who had undergone chemotherapy exhibited a higher probability of developing RP (P<0.001). The developed nomogram offers a precise and user-friendly tool for clinical application in predicting the risk of RP in patients with lung cancer undergoing close-range radiotherapy with radioactive I particles.