Skip to main content
. 2022 Aug 8;12(13):5931–5948. doi: 10.7150/thno.74281

Figure 2.

Figure 2

The prognostic value of the TIIClnc signature. A. A total of 101 combinations of machine learning algorithms for the TIIClnc signatures via a 10-fold cross-validation framework. The C-index of each model was calculated across validation datasets, including TCGA LGG, Xiangya in-house, CGGA LGG, and GSE108474 datasets. B. The exhibition of the 16 most valuable TIIClncRNAs based on the CoxBoost algorithm. C. The number of trees for determining the TIIClnc signature with minimal error and the importance of the 16 most valuable TIIClncRNAs based on the RSF algorithm. D. Kaplan-Meier survival curve of OS between patients with a high score of TIIClnc signature and with a low score of TIIClnc signature in the TCGA LGG, Xiangya in-house, CGGA LGG, and GSE108474 datasets. E. Time-dependent ROC curves of 1-year, 2-year, 3-year, 4-year, and 5-year OS in the CGGA LGG, Xiangya in-house, TCGA LGG, and GSE108474 datasets.