Objective：To construct a predictive model for occult mediastinal lymph node metastasis in lung adenocarcinoma based on clinical and imaging features of the primary tumor. Methods：A retrospective analysis was conducted on lung adenocarcinoma patients，who underwent surgical treatment and lymph node dissection with or without occult mediastinal lymph node metastasis on pathology at the First Affiliated Hospital of Nanjing Medical University from 2009 to 2019. Multiple clinical and imaging features of the patient were collected. Univariate and multivariate logistic regression analyses were used to identify independent predictors，and an imaging model incorporating multiple CT characteristics was constructed. Receiver operating characteristic（ROC）curves were established to evaluate the predictive efficacy and clinical utility value of each model. Results：Among the final 780 patients with normal-sized lymph nodes，145 cases exhibited lymph node metastasis. Univariate analysis suggested that tumor size，axial location， nodule characteristics，morphological features，pleural pulling sign，and type of pleural adjacency were significantly associated with lymph node metastasis. Multivariate analysis indicated that tumor size（OR=1.019，95% CI：1.002- 1.036，P=0.028），nodule characteristics（OR=0.361，95% CI：0.202-0.646，P=0.001），pleural tag（OR=1.835，95%CI：1.152-2.924，P=0.011），and presence of mediastinal pleural abutting（OR=1.796，95% CI：1.106- 2.919，P=0.018）were independent predictors of occult mediastinal lymph node metastasis. The imaging model developed based on these predictors showed an area under the curve（AUC）of 0.75，with a sensitivity of 86.2% and specificity of 53.1%. Conclusion：The imaging model based on chest CT scans demonstrates excellent clinical value in predicting occult mediastinal lymph node metastasis in lung adenocarcinoma. It provides a basis for non-invasive preoperative decision making and surgical treatment planning by clinicians.