A nomogram for predicting the risk of invasive pulmonary adenocarcinoma for patients with solitary peripheral subsolid nodules

Abstract Objective The subsolid nodule is a common clinical concern. The aim of this study was to construct a nomogram to predict the risk of invasive pulmonary adenocarcinoma in patients with a solitary peripheral subsolid nodule. Methods We reviewed the records of 293 patients who had undergone resection of a solitary peripheral subsolid nodule, including the results of pathologic examinations after surgical resection. Clinical parameters and imaging features were analyzed by the use of univariable and multivariable logistic regression analysis. A nomogram to predict the risk of invasive pulmonary adenocarcinoma was constructed and validated with bootstrap resampling. Results Two hundred seventy-three patients were included for analysis; 35 were diagnosed as benign, 3 as atypical adenomatous hyperplasia, 18 as adenocarcinoma in situ, 58 as minimally invasive adenocarcinoma, and 159 as invasive pulmonary adenocarcinoma. After final regression analysis, the computed tomography attenuation, nodule size, spiculation, signs of vascular convergence, pleural tags, and solid proportion were identified and were entered into the nomogram. The nomogram showed a robust discrimination, with an area under the receiver operating characteristic curve of 0.894. 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 We developed a nomogram that can predict the risk of invasive pulmonary adenocarcinoma for patients with a solitary peripheral subsolid nodule. Validation by the use of bootstrap resampling revealed optimal discrimination and calibration, indicating that the nomogram may have clinical utility. This model has the potential to assist clinicians in making treatment recommendations.