Objective: To explore the predictive value of dual-energy computed tomography (CT) radiomics nomogram for postoperative recurrence risk in patients with STAS-positive lung adenocarcinoma due to intracavitary dissemination. Methods: A total of 150 patients with STAS-positive lung adenocarcinoma were selected as the research subjects and divided into a recurrence group (n = 47) and a non-recurrence group (n = 103) based on different postoperative outcomes within 1 year. Clinical and pathological data were collected. Preoperative dual-energy CT imaging features, including conventional mixed-energy CT values, iodine concentration on iodine maps, spectral curve slope, effective atomic number, and radiomics scores, were extracted. The Least Absolute Shrinkage and Selection Operator (LASSO) regression method was employed for variable selection. Multivariate Logistic regression analysis was performed to identify independent predictors associated with the study outcome. A nomogram was constructed based on the selected independent predictors to develop the predictive model. The receiver operating characteristic (ROC) curve was used to evaluate the predictive value of the model for postoperative recurrence risk in STAS-positive lung adenocarcinoma patients. Results: The tumor size, conventional mixed-energy CT value, iodine concentration on the iodine basis map, slope of the energy spectrum curve, effective atomic number, and radiomics score of the recurrent group were higher than those of the non-recurrent group (P < 0.05). The proportion of patients with high-grade pathological grading who underwent sublobectomy was lower than that of the non-recurrent group (P < 0.05). Multivariate regression analysis demonstrated that tumor size, conventional mixed-energy CT value, iodine concentration, spectral curve slope, and radiomics score were all independent influencing factors for postoperative recurrence within one year (P < 0.05). The area under the ROC curve (AUC) of the nomogram for predicting postoperative recurrence was 0.891 (95% CI: 0.824~0.959). The calibration curve indicated good agreement between the predicted probabilities of the model and the actual observations. Conclusion: The nomogram model based on dual-energy CT radiomics exhibits a favorable predictive value for the 1-year postoperative recurrence risk in patients with STAS-positive lung adenocarcinoma, providing a reference for postoperative risk stratification.