Prediction of malignancy for solitary pulmonary nodules based on imaging, clinical characteristics and tumor marker levels. Issue 5 (September 2021)

• Record Type: Journal Article
• Authors: Hou, Hongjun; Yu, Shui; Xu, Zushan; Zhang, Hongsheng; Liu, Jie; Zhang, Wenjun
• Is Part Of: European journal of cancer prevention. Volume 30:Issue 5(2021)
• Publication Date: 2021-09
• Subjects: computerized tomography -- prediction model -- solitary pulmonary nodule -- tumor markers; Cancer -- Prevention -- Periodicals; Neoplasms -- etiology -- Periodicals; Neoplasms -- prevention & control -- Periodicals; Cancer -- Prevention; Periodicals; 616.994052
• DOI: 10.1097/CEJ.0000000000000637
• Languages: English
• ISSNs: 0959-8278

Abstract

Abstract : Objective: To establish a prediction model of malignancy for solitary pulmonary nodules (SPNs) on the basis of imaging, clinical characteristics and tumor marker levels. Methods: Totally, 341 cases of SPNs were enrolled in this retrospective study, in which 70% were selected as the training group ( n = 238) and the rest 30% as the verification group ( n = 103). The imaging, clinical characteristics and tumor marker levels of patients with benign and malignant SPNs were compared. Influencing factors were identified using multivariate logistic regression analysis. The model was assessed by the area under the curve (AUC) of the receiver operating characteristic curve. Results: Differences were evident between patients with benign and malignant SPNs in age, gender, smoking history, carcinoembryonic antigen (CEA), neuron-specific enolase, nodule location, edge smoothing, spiculation, lobulation, vascular convergence sign, air bronchogram, ground-glass opacity, vacuole sign and calcification (all P < 0.05). Influencing factors for malignancy included age, gender, nodule location, spiculation, vacuole sign and CEA (all P < 0.05). The established model was as follows: Y = −5.368 + 0.055 × age + 1.012 × gender (female = 1, male = 0) + 1.302 × nodule location (right upper lobe = 1, others = 0) + 1.208 × spiculation (yes = 1, no = 0) + 2.164 × vacuole sign (yes = 1, no = 0) −0.054 × CEA. The AUC of the model with CEA was 0.818 (95% confidence interval, 0.763–0.865), with a sensitivity of 64.80% and a specificity of 84.96%, and the stability was better through internal verification. Conclusions: The prediction model established in our study exhibits better accuracy and internal stability in predicting the probability of malignancy for SPNs.