Computed tomography (CT), an efficient radiological technology, is used to detect lung cancer in the clinic. Carcinoembryonic antigen (CEA), a common tumor biomarker, is applied in the detection of various tumors. To highlight the advantages of two‐dimensional techniques and assist clinicians in optimizing lung cancer diagnostic schemes, we established a favorable model combining CT and CEA. In the study, univariate analysis was performed to screen independent predictors in a training cohort of 271 patients with malignant pulmonary nodules (MPNs) and 92 with benign pulmonary nodules (BPNs). Six machine learning–based models involving five CT predictors (mediastinal lymph node enlargement, lobulation, vascular notch sign, spiculation, and nodule number) and lnCEA were constructed and validated in an independent cohort of 129 participants (92 MPNs and 37 BPNs) by SPSS Modeler. A nomogram and the Delong test were generated by R software. Finally, the model established by logistic regression had highest diagnostic efficiency (area under the curve [AUC] = 0.912). Moreover, the diagnostic ability of the logistic model in the validation cohort (AUC = 0.882, 80.4% sensitivity, 75.7% specificity) was higher than that of the Peking University model (AUC = 0.712, 68.5% sensitivity, 70.3% specificity) and the Mayo model (AUC = 0.745, 62.0% sensitivity, 75.7% specificity). Interestingly, for the participants with intermediate (10‐30 mm) and CEA‐negative nodule, the model reached an AUC of 0.835 (72.3% sensitivity, 83.3% specificity). The AUC for the early lung cancer was as high as 0.822 with 67.3% sensitivity and 78.9% specificity. As a conclusion, this promising model presents a new diagnostic strategy for the clinic to distinguish MPNs from BPNs.
Background
The death rate of lung cancer (LC) ranks first in the world. Changes of DNA methylation in peripheral blood may be related to malignant tumors. It is necessary to explore blood-based biomarkers of methylation to detect LC.
Methods
Mass spectrometry assays were conducted to measure DNA methylation levels of seven CpG sites within FUT7 gene in the peripheral blood of 428 patients with LC, 233 patients with benign pulmonary nodule (BPN) and 862 normal controls (NC). The odds ratios (ORs) of all CpG sites were evaluated for their risk to LC using per SD change and tertiles analyses by logistic regression. The predictive ability of the seven FUT7 CpG sites and risk factors were evaluated by receiver operating characteristic curve (ROC).
Results
The methylation levels of seven CpG sites of FUT7 in LC were significantly lower than that in NC (P < 0.05). The per SD decrement of methylation level in CpG_1-7 was significantly associated with 65%, 38%, 59%, 46%, 23%, 20% and 68% higher risk for LC versus NC, respectively, and the adjusted ORs (95% CI) were 2.92 (2.17–3.96), 1.76 (1.29–2.38), 2.83 (2.09–3.82), 3.00 (2.17–4.16), 1.81 (1.35–2.43), 1.48 (1.11–1.97) and 3.04 (2.23–4.16) for the lowest tertiles of methylation level in CpG_1-7 compared with the top tertiles, respectively. The area under the curve (AUC) of FUT7_CpG_1-7 was 0.659 (CI 0.626–0.693), 0.792 (CI 0.736–0.848) and 0.729 (CI 0.665–0.792) in distinguishing LC versus NC, LUSC versus NC and LUSC versus BPN.
Conclusions
Our study revealed an association between FUT7 hypomethylation and LC, especially for LUSC, which provides novel support for the blood-based methylation signatures as potential marker for assessing lung cancer risk.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.