Skip to main content
Fig. 3 | BMC Cancer

Fig. 3

From: LUADpp: an effective prediction model on prognosis of lung adenocarcinomas based on somatic mutational features

Fig. 3

Performance comparison of the prognosis prediction models based on somatic mutation features and clinical stage information. a. Correlation between clinical TNM stages and LUAD prognosis. The bars represented different clinical stages while the height of bars represented corresponding case numbers. For each stage, the good and poor prognosis subgroups were shown in different colors. b. Survival curves of sub-groups of cases classified with SVM models based on stage (left) or combined stage and somatic mutation features (right). The curves were based on the prediction results of 5-fold cross-validation testing datasets. c. The ROC curves of SVM models based on stage, somatic mutation features and the combined features. The curves were based on the prediction results of 5-fold cross-validation testing datasets. d. Performance comparison of different genetic models. The 5-fold cross-validation results were compared for ROC_AUC and Accuracy, and the standard deviations were shown in error bars. Students’ pairwise t tests were performed. ** and **** represented p < 0.01 and p < 0.001, respectively

Back to article page