Objective: To investigate the efficacy of artificially intelligent CT metrics combined with tumor markers and 7-TAABs in predicting the infiltrative nature of mixed ground-glass nodules in the lungs to provide a basis for rational clinical decision-making. Materials and Methods: The clinical data of patients admitted to Changshu Hospital affiliated with Soochow University (Hospital 1) and the Eighth People’s Hospital of Tongzhou District, Nantong City (Hospital 2) from January 2022 to June 2023 were retrospectively analyzed, and a total of 427 cases were included in the study based on the nadir criteria. Three hundred twenty cases from Hospital 1 were randomly grouped into a training set ([Formula: see text]) and an internal validation set ([Formula: see text]), and 107 cases from Hospital 2 were used for the external validation set. The correlations between patients’ clinicoradiological characteristics, tumor markers, and seven tumor autoantibodies (7-TAABs) were analyzed by the Mantel test and further by univariate and multivariate logistic regression analyses to screen the risk factors for the development of infiltrative tumors in the ground-glass nodes and to establish a joint model, which was combined with the clinicoradiological model and the model of the serological indexes in the internal and external validation sets were performed to compare the subject work characteristics (ROC) curves, clinical calibration curves, and clinical decision curves to evaluate their predictive efficacy and clinical utility. Results: Of the 427 cases included, 174 were in the noninfiltrating group, and 253 were in the infiltrating group. There was a significant relationship between tumor markers, seven tumor autoantibodies, and lung cancer infiltrability, and after multifactorial logistic regression analysis, a bronchial air sign, probability of malignancy, nodule diameter, percentage of solidity, VEGF, proGRP, GAGE7, and 7-TAABs were the risk factors for determining the development of infiltrative lesions in early-stage lung nodules. The clinicoradiological model was superior to the serological index model on both internal and external validation sets (AUC values were: 0.926 versus 0.839, [Formula: see text]; 0.895 versus 0.751, [Formula: see text]), and the combined model was slightly superior to the clinicoradiological model on both internal and external validation sets (AUC values were: 0.928 versus 0.926, [Formula: see text]; 0.914 versus 0.895, [Formula: see text]). The combined model performed optimally in terms of calibration accuracy and net clinical benefit, suggesting that a model constructed based on AI CT metrics combined with tumor markers and 7-TAABs would be beneficial to clinicians in predicting the infiltrative nature of early-stage lung cancer. Conclusion: The column-line diagram model built based on CT indexes improved by artificial intelligence technology combined with tumor markers and 7-TAAB can better predict the infiltration of lung tumors, which has specific clinical application value.
