Development of a risk scoring model for predicting visceral pleural invasion in clinical stage T1N0M0 lung...

Visceral pleural invasion (VPI) significantly impacts the staging and prognosis of non-small cell lung cancer (NSCLC). Accurate preoperative prediction of VPI remains challenging owing to the limitations of current imaging-based approaches. In this study, we aimed to develop and validate a risk prediction model for VPI using pleural carcinoembryonic antigen (CEA), maximum standardized uptake value (SUVmax), and nodule type.

In this retrospective study, we analyzed patients with NSCLC and pleural contact who underwent surgery between 2017 and 2024. Pleural carcinoembryonic antigen (pCEA), SUVmax, and nodule type were identified as independent predictors of VPI using multivariable logistic regression. A risk-scoring model was developed and validated using independent cohorts.

In the multivariate analysis, elevated pCEA [odds ratio (OR), 3.00; 95% confidence interval (CI): 1.14-7.87; P=0.02], elevated SUVmax (OR, 5.25; 95% CI: 1.90-14.50; P=0.001), and nodule type (OR, 3.89; 95% CI: 1.42-10.68; P=0.008) were identified as independent risk factors for VPI. The model assigned scores based on these variables, with higher scores correlating with an increased probability of VPI. In the validation cohort of 95 patients, VPI probabilities ranged from 0% for a score of 0 to 69.2% for a score of 5. The model demonstrated strong predictive performance, achieving an area under the curve of 0.829 (95% CI: 0.7378-0.9200), a sensitivity of 79.2% (95% CI: 0.6250-0.9177), a specificity of 71.8% (95% CI: 0.6056-0.8310), and a positive predictive value of 51.3%.

The proposed VPI risk model serves as a practical and accurate tool for preoperative VPI prediction, thereby enhancing clinical staging and enabling personalized surgical planning. The incorporation of pCEA emphasizes its potential clinical utility. However, external validation is necessary to establish its broader applicability.