Objective To investigate the significance of spread through air spaces (STAS) in early-stage non-small cell lung cancer (NSCLC) patients undergoing either sublobar resection or lobectomy by pooling evidence available, and to assess the accuracy of frozen sections in determining types of resection among patients with suspected presence of STAS. MethodsStudies were identified by searching databases including PubMed, EMbase, Web of Science, and The Cochrane Library from inception to July 2022. Two researchers independently searched, screened, evaluated literature, and extracted data. Statistical analysis was conducted using RevMan 5.4 and STATA 15.0. The Newcastle-Ottawa Scale (NOS) was used to evaluate the quality of the study. ResultsA total of 26 studies involving 23 surgical related studies (12 266 patients) were included, among which, 11 compared the outcomes of lobectomy with sublobar resection in the STAS-positive patients. NOS score≥6 points. Meta-analysis indicated that presence of STAS shortened patients' survival in both lobectomy group and sublobar resection group (RFS: HR=2.27, 95%CI 1.96-2.63, P＜0.01; OS: HR=2.08, 95%CI 1.74-2.49, P＜0.01). Moreover, lobectomy brought additional survival benefits to STAS-positive patients compared with sublobar resection (RFS: HR=1.97, 95%CI 1.59-2.44, P＜0.01; OS: HR=1.91, 95%CI 1.47-2.48, P＜0.01). Four studies were included to assess the accuracy of identifying presence of STAS on intraoperative frozen sections, of which the pooled sensitivity reached 55% (95%CI 45%-64%), the pooled specificity reached 92% (95%CI 77%-97%), and the pooled area under the curve was 0.68 (95%CI 0.64-0.72) based on the data available. Conclusion This study confirms that presence of STAS is a critical risk factor for patients with early-stage NSCLC. Lobectomy should be recommended as the first choice when presence of STAS is identified on frozen sections, as lobectomy can prolong patients' survival compared with sublobar resection in STAS-positive disease. The specificity of identifying STAS on frozen sections seems to be satisfactory, which may be helpful in determining types of resection. However, more robust methods are urgently in need to make up for the limited sensitivity and accuracy of frozen sections.
ObjectiveTo develop and validate a machine learning model based on preoperative clinical characteristics, laboratory indices, and radiological features for the non-invasive prediction of spread through air spaces (STAS) in patients with early-stage lung adenocarcinoma. Methods Preoperative data from patients with early-stage lung adenocarcinoma who underwent surgical resection at Northern Jiangsu People's Hospital between January 2020 and August 2025 were retrospectively collected. The data included clinical characteristics, laboratory indices, and radiological features. Patients were divided into a STAS-positive and a STAS-negative group based on postoperative pathological findings. The dataset was randomly split into a training set and a testing set at a 7 : 3 ratio. Feature variables were selected using the maximum relevance and minimum redundancy (mRMR) algorithm and the least absolute shrinkage and selection operator (LASSO) regression. Five machine learning models were constructed: logistic regression (LR), random forest (RF), support vector machine (SVM), light gradient boosting machine (LightGBM), and extreme gradient boosting (XGBoost). Model performance was evaluated using the area under the receiver operating characteristic curve (AUC) and decision curve analysis (DCA). The shapley additive explanations (SHAP) method was employed to interpret the optimal prediction model. Results A total of 377 patients were included, comprising 177 (46.9%) males and 200 females (53.1%), with a mean age of (63.31±9.73) years. There were 261 patients in the training set and 116 patients in the testing set. In the training set, statistically significant differences were observed between the STAS-positive group (n=130) and STAS-negative group (n=131) across multiple features, including age, sex, neutrophil-to-lymphocyte ratio (NLR), monocyte-to-lymphocyte ratio (MLR), clinical T stage, and maximum solid component diameter (P<0.05). A final set of 10 feature variables was selected by combining mRMR and LASSO regression, and five machine learning models (LR, RF, SVM, LightGBM, XGBoost) were developed. The XGBoost model demonstrated superior predictive performance in both the training and testing sets, achieving AUCs of 0.947 [95%CI (0.920, 0.975)] and 0.943 [95%CI (0.894, 0.993)], respectively, and achieved the optimal level in the testing set. DCA indicated that the XGBoost model provided a high net clinical benefit across a wide range of threshold probabilities. SHAP analysis revealed that the vessel convergence sign, clinical T stage, age, consolidation-to-tumor ratio (CTR), and MLR were the features with the highest contributions to STAS prediction. Conclusion The XGBoost model effectively predicts preoperative STAS status in early-stage lung adenocarcinoma, exhibiting excellent discriminative performance and good clinical interpretability. Key predictors such as the vessel convergence sign, clinical T stage, age and CTR provide a crucial reference for preoperative risk assessment and the individualized selection of surgical strategies, ultimately benefiting patients.
ObjectiveTo investigate the predictive value of preoperative radiological features on spread through air spaces (STAS) in stage cⅠA lung adenocarcinoma with predominant ground-glass opacity, and to provide a basis for the selection of surgical methods for these patients.MethodsThe clinical data of 768 patients with stage cⅠA lung adenocarcinoma undergoing operation in our hospital from 2017 to 2018 were reviewed, and 333 early stage lung adenocarcinoma patients with predominant ground-glass opacity were selected. There were 92 males and 241 females, with an average age of 57.0±10.0 years. Statistical analysis was performed using SPSS 22.0.ResultsSTAS-positive patients were mostly invasive adenocarcinoma (P=0.037), and had more micropapillary component (P<0.001) and more epidermal growth factor receptor (EGFR) gene mutations (P=0.020). There were no statistically significant differences between the STAS-positive and STAS-negative patients in other clinicopathological features. Univariate analysis showed that the maximum diameter of tumor in lung window (P=0.029), roundness (P=0.035), maximum diameter of solid tumor component in lung window (P<0.001), consolidation/tumor ratio (CTR, P<0.001), maximum area of the tumor in mediastinum window (P=0.001), tumor disappearance ratio (TDR, P<0.001), average CT value (P=0.001) and lobulation sign (P=0.038) were risk factors for STAS positive. Multivariate logistic regression analysis showed that the CTR was an independent predictor of STAS (OR=1.05, 95%CI 1.02 to 1.07, P<0.001), and the area under the receiver operating characteristic (ROC) curve was 0.71 (95%CI 0.58 to 0.85, P=0.002). When the cutoff value was 19%, the sensitivity of predicting STAS was 66.7%, and the specificity was 75.2%.ConclusionCTR is a good radiological feature to predict the occurrence of STAS in early lung adenocarcinoma with predominant ground-glass opacity. For the stagecⅠA lung adenocarcinoma with predominant?ground-glass opacity and CTR ≥19%, the possibility of STAS positive is greater, and sublobar resection needs to be carefully considered.