CT and CEA-based machine learning model for predicting malignant pulmonary nodules

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.

The use of carcinoembryonic antigen levels to predict lung nodule malignancy: a meta-analysis

OBJECTIVES

To assess the diagnostic value of serum carcinoembryonic antigen (CEA) as a diagnostic biomarker that can be used to differentiate between benign and malignant lung nodules (LNs).

METHODS

PubMed, Cochrane Library, and Embase were reviewed from January 2000 to April 2020 for eligible studies. Stata v12.0 was used to conduct this meta-analysis.

RESULTS

Our initial literature search identified 511 potentially relevant studies, of which 11 were ultimately included in the present meta-analysis. Ten studies were retrospective and only 1 study was prospective. Overall these studies incorporated 2760 patients and 2760 total LNs (1733 malignant, 1027 benign). Pooled sensitivity, specificity, positive likelihood ratio (PLR), negative likelihood ratio (NLR), and diagnostic odds ratio (DOR) values for these studies were 0.33 (95% CI: 0.20-0.49), 0.92 (95% CI: 0.85-0.96), 3.96 (95% CI: 2.84-5.54), 0.73 (95% CI: 0.62-0.87), and 5.42 (95% CI: 3.77-7.78), respectively. The area under curve (AUC) value was 0.77, consistent with moderate diagnostic accuracy. We detected significant heterogeneity when calculating pooled sensitivity (I² = 95.9%, P = 0.00), specificity (I² = 92.0%, P = 0.00), PLR (I² = 61.7%, P = 0.00), NLR (I² = 92.8%, P = 0.00), and DOR (I² = 93.8%, P = 0.00). No significant evidence of publication bias was detected via Deeks' funnel plot asymmetry test (P = 0.371). Meta-regression analysis revealed different reference standards to be closely associated with both sensitivity and specificity.

CONCLUSIONS

Serum CEA can achieve moderate diagnostic performance as a means of differentiating between malignant and benign LNs.