Research Article

15-lncRNA-Based Classifier-Clinicopathologic Nomogram Improves the Prediction of Recurrence in Patients with Hepatocellular Carcinoma

Figure 2

Selection of RFS-associated lncRNAs by the LASSO analysis in the training set. (a) LASSO coefficient profiles of the 30 lncRNAs. A vertical line is drawn at the optimal value by the minimum criteria and results in fifteen nonzero coefficients. The fifteen lncRNAs—AC012625.1, AC068481.1, AC092675.1, AC093772.1, AC109779.1, AC118653.1, AC246785.3, AL121985.1, AL121985.1, AP002478.1, ARHGEF7.AS1, GACAT3, LINC00462, LINC01700, and LINC02429, respectively—were selected in the LASSO Cox regression model. (b) The fifteen lncRNAs selected by the LASSO Cox regression analysis. The two dotted vertical lines are drawn at the optimal values by minimum criteria (left) and 1 - s.e. criteria (right).
(a)
(b)