Fig. 6

Construction of the prognosis prediction model for HCC patients. a The ROC curve displays the sensitivity and specificity of the prognosis prediction model. The area under the curve (AUC) reached 0.923. b The colour-coded heatmap corresponding to the consensus matrix for k = 7 obtained by applying consensus clustering from the test set. c Survival curves of the seven clusters predicted from the test set using the prognosis model. The log-rank test was used to assess the statistical significance of the difference