A nomogram for preoperative prediction of invasiveness in solitary pulmonary adenocarcinoma: a multicenter study

The invasive pulmonary adenocarcinoma and preinvasive-minimally invasive lesions usually need different surgical operation methods. This study aims to develop a clinical prediction model for preoperatively assessing invasiveness in solitary pulmonary adenocarcinoma.

From January 2020 to December 2024, patients with solitary pulmonary nodules who underwent preoperative computed tomography (CT) scans in four centers were included. The patients were divided into a training dataset and an external testing dataset. Based on postoperative histopathology, patients were categorized into group A (atypical adenomatous hyperplasia, adenocarcinoma in situ, and minimally invasive adenocarcinoma) and group B (invasive adenocarcinoma). Logistic regression analyses were performed to establish a clinical prediction model and of which its performance was validated. Receiver operating characteristic curve was used to quantify discriminative ability, and a nomogram was generated to visualize the individualized risk probability.

Four hundred and forty-eight patients were included, with 335 patients in the training dataset (Group A: 156; Group B: 179) and 113 patients in the external testing dataset (Group A: 53; Group B: 60). Four independent predictors were identified in the training dataset: cytokeratin 19 fragment (CYFRA 21-1) [odds ratio (OR): 4.175; 95% confidence interval (CI): 1.253-13.904; P=0.02], maximum diameter (OR: 1.247; 95% CI: 1.143-1.361; P<0.001), density type (OR: 6.604; 95% CI: 3.519-12.393; P<0.001), and air bronchogram (OR: 3.149; 95% CI: 1.406-7.051; P=0.005). The nomogram model demonstrated a robust diagnostic performance with area under the curves (AUCs) of 0.925 (95% CI: 0.897-0.953) in the training cohort and 0.895 (95% CI: 0.829-0.961) in the testing cohort.

The integration of tumor markers with CT imaging features enables preoperative noninvasive prediction of invasiveness in pulmonary adenocarcinoma.