Diagnostic accuracy of CT-based radiomics for predicting occult lymph node metastasis in early-stage lung adenocarcinoma: a systematic review and meta-analysis

Background: This study aims to evaluate the diagnostic accuracy of CT-based radiomics for predicting occult lymph node metastasis (OLNM) in early-stage lung adenocarcinoma. Methods: Relevant studies up to December 2025 were systematically searched in the databases of PubMed, Embase, Cochrane Library, and Web of Science. Diagnostic accuracy was assessed by pooled estimates of sensitivity, specificity, likelihood ratios, the diagnostic odds ratio, and the summary receiver operating characteristic curve. Subgroup analyses was then conducted to determine sources of heterogeneity. Results: This study evaluated 10 articles and 6,349 patients. By meta-analysis, CT-based radiomics demonstrated good diagnostic performance for OLNM. The pooled sensitivity and specificity were 0.85 and 0.78 in internal validation cohorts and 0.72 and 0.75 in external validation cohorts, respectively. The area under the summary receiver operating characteristic curve was 0.89 and 0.80 for internal and external validation, respectively. Subgroup analyses of the external validation cohorts suggested possible variation in diagnostic performance according to sample size, CT protocol, and segmentation method. Conclusion: CT-based radiomics shows potential for non-invasive prediction of OLNM in early-stage lung adenocarcinoma. Further multicenter prospective studies with harmonized imaging and radiomics pipelines are needed to confirm its clinical applicability. Systematic review registration: CRD420261299869.