A nomogram for predicting the risk of invasive adenocarcinoma in patients with a sub-solid nodule

Objective  To develop a model for predicting the risk of invasive pulmonary adenocarcinoma for sub-solid nodules, and provide a reference for the formulation of appropriate clinical diagnosis and treatment strategies for subsolid nodules.

Methods  Totally, 221 patients with SSN who underwent surgical resection with a definite postoperative pathology from November 2019 to December 2020 in Xinhua Hospital Affiliated to Shanghai Jiao Tong University School of Medicine were included, patients' clinical data, serum tumor markers, and 17 parameters in radiological data were analyzed. The variables included in the model were screened by LASSO regression, then a risk evaluation nomogram model was established and verified.

Results  Among the 221 patients with SSN, there were 2 atypical adenomatous hyperplasia (AAH), 44 adenocarcinomas in situ (AIS), 102 minimally invasive adenocarcinomas (MIA), and 73 invasive adenocarcinomas (IA). Five factors were selected by LASSO regression, including the maximum diameter of lung nodule, CT attenuation, shape, lobulation, and diameter of the solid component. The calibration curves for the probability of invasive pulmonary adenocarcinoma showed optimal agreement between the probability as predicted by the nomogram and the actual probability.

Conclusions  The factors including the maximum diameter of lung nodule, CT attenuation, shape, lobulation, and diameter of the solid component might help to predict the risk of invasive pulmonary adenocarcinoma for sub-solid nodules and provide guidance for the subsequent personalized treatment.