Abstract: Objective: The study aimed to develop and evaluate a clinical diagnostic model that combined computer tomography (CT) radiomic features with a nomogram for predicting invasiveness in subsolid pulmonary nodules. Methods: This retrospective study analyzed both clinical and imaging data from patients at our institution who were diagnosed with pathologically confirmed subsolid pulmonary nodules at our institution based on thin-slice CT images. Radiomic features were extracted from these CT images, and LASSO regression with K-fold cross-validation was used to select the most informative features. Three predictive models were constructed via multivariate logistic regression: the first incorporated clinical parameters and conventional imaging features; the second relied solely on radiomic characteristics; and the third was a hybrid clinical-radiomics model. The logistic regression results were visually represented using a nomogram. Receiver operating characteristic curves were utilized to compare the classification predictive performance of the three models for distinguishing ground-glass opacity lung adenocarcinoma IA and non-IA cases. Decision curve analysis (DCA) was employed to assess the clinical utility of these models across different cohorts. Results: A total of 204 subsolid pulmonary nodules from 192 patients were included. They were divided into invasive (n=114) and non-invasive groups (n=90) based on pathological typing. These nodules were divided into a training set (n=143, IA:non-IA 77∶66) and a test set (n=61, IA:non-IA 38∶23). A total of 1316 features were initially extracted from each subsolid nodule. Subsequently, two independent clinical predictors (mean CT value and maximum diameter) and three radiomic features were selected through feature selection and logistic regression for model building. The combined clinical-radiomics model demonstrated superior discriminative capability (AUC=0.920, 95%CI: 0.818~0.931) in distinguishing IA from non-IA within the training set compared to the radiomics model and the clinical model independently (AUC=0.907, 95%CI: 0.792~0.914; AUC=0.822, 95%CI: 0.764~0.895). In the test set, the inclusion of clinical data improved the diagnostic efficacy of the radiomics model. DCA demonstrated that the combined model generally provided greater clinical benefits in most scenarios. Conclusion: The developed clinical-radiomics joint model showed promising performance in predicting the subsolid pulmonary nodule invasiveness.