Abstract
BACKGROUND: The authors aimed to create a novel model to predict lymphatic metastasis in thymic epithelial tumors. METHODS: Data of 1018 patients were collected from the Surveillance, Epidemiology, and End Results database from 2004 to 2015. To construct a nomogram, the least absolute shrinkage and selection operator (LASSO) regression model was used to select candidate features of the training cohort from 2004 to 2013. A simple model called the Lymphatic Node Metastasis Risk Scoring System (LNMRS) was constructed to predict lymphatic metastasis. Using patients from 2014 to 2015 as the validation cohort, the predictive performance of the model was determined by receiver operating characteristic (ROC) curves. RESULTS: The LASSO regression model showed that age, extension, and histology type were significantly associated with lymph node metastasis, which were used to construct the nomogram. Through analysis of the area under the curve (AUC), the nomogram achieved a AUC value of 0.80 (95 % confidence interval [Cl] 0.75-0.85) in the training cohort and 0.82 (95 % Cl 0.70-0.93) in the validation cohort, and had closed calibration curves. Based on the nomogram, the authors constructed the LNMRS model, which had an AUC of 0.80 (95 % Cl 0.75-0.85) in the training cohort and 0.82 (95% Cl 0.70-0.93) in the validation cohort. The ROC curves indicated that the LNMRS had excellent predictive performance for lymph node metastasis. CONCLUSION: This study established a nomogram for predicting lymph node metastasis. The LNMRS model, constructed to predict lymphatic involvement of patients, was more convenient than the nomogram.