Epithelial–mesenchymal transition biomarkers and support vector machine guided model in preoperatively predicting regional lymph node metastasis for rectal cancer

• Published in: British journal of cancer 2012-05, Vol.106 (11), p.1735-1741
• Main Authors: Fan, X-J, Wan, X-B, Huang, Y, Cai, H-M, Fu, X-H, Yang, Z-L, Chen, D-K, Song, S-X, Wu, P-H, Liu, Q, Wang, L, Wang, J-P
• Format: Article
• Language: English
• Subjects: 631/67/1857; 631/67/322; 692/699/67/1504/1885/1777; Adolescent; Adult; Aged; Aged, 80 and over; Algorithms; Antigens; Area Under Curve; Bioindicators; Biological and medical sciences; Biomarkers; Biomarkers, Tumor - analysis; Biomedical and Life Sciences; Biomedicine; Cancer; Cancer Research; Clinical Study; Colorectal cancer; Drug Resistance; Epidemiology; Epithelial-Mesenchymal Transition; Female; Hematologic and hematopoietic diseases; Humans; Immunohistochemistry; Leukemias. Malignant lymphomas. Malignant reticulosis. Myelofibrosis; lymph nodes; Lymphatic Metastasis; Lymphatic system; Male; Medical prognosis; Medical research; Medical sciences; Metastasis; Middle Aged; Molecular Medicine; Neoplasm Staging; Oncology; Patients; Power; Predictive Value of Tests; Prognosis; Rectal Neoplasms - chemistry; Rectal Neoplasms - pathology; Risk Factors; ROC Curve; Sensitivity; Support Vector Machine; Support vector machines; Tissue Array Analysis; Tumors; Variables; Young Adult
• ISSN: 0007-0920; 1532-1827
• DOI: 10.1038/bjc.2012.82

Background: Current imaging modalities are inadequate in preoperatively predicting regional lymph node metastasis (RLNM) status in rectal cancer (RC). Here, we designed support vector machine (SVM) model to address this issue by integrating epithelial–mesenchymal-transition (EMT)-related biomarkers along with clinicopathological variables. Methods: Using tissue microarrays and immunohistochemistry, the EMT-related biomarkers expression was measured in 193 RC patients. Of which, 74 patients were assigned to the training set to select the robust variables for designing SVM model. The SVM model predictive value was validated in the testing set (119 patients). Results: In training set, eight variables, including six EMT-related biomarkers and two clinicopathological variables, were selected to devise SVM model. In testing set, we identified 63 patients with high risk to RLNM and 56 patients with low risk. The sensitivity, specificity and overall accuracy of SVM in predicting RLNM were 68.3%, 81.1% and 72.3%, respectively. Importantly, multivariate logistic regression analysis showed that SVM model was indeed an independent predictor of RLNM status (odds ratio, 11.536; 95% confidence interval, 4.113–32.361; P