Fig. 3 | Scientific Reports

Fig. 3

From: Development of a MVI associated HCC prognostic model through single cell transcriptomic analysis and 101 machine learning algorithms

Fig. 3

(A) C-index of different models constructed using 101 machine-learning algorithm combinations in the TCGA training set and ICGC external validation set. (B) C-index comparison of the prognostic model based on model genes and 38 published HCC prognostic models in the TCGA-LIHC training set and ICGC external validation sets. (C) AUC values of TCGA training set and ICGC validation set at 1, 3, and 5 years. (D) KM analysis between high- and low-risk groups in TCGA datasets. (E) KM analysis between high- and low-risk groups in ICGC datasets. (F) Meta analysis of univariate cox regression in TCGA-LIHC training set and ICGC external validation set. (G) Meta analysis of univariate cox regression of the prognostic model based on model genes and 38 published HCC prognostic models in the TCGA-LIHC training set and ICGC validation sets.

Back to article page