Skip to main content
Fig. 2 | BMC Cancer

Fig. 2

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

Fig. 2

Model performance on prediction of LUAD prognosis based on somatic mutation features. a. The ROC curves of SVM models based on different sizes of somatic mutation features. The curves were based on the prediction results of 5-fold cross-validation testing datasets. b. Performance comparison of different genetic models. The 5-fold cross-validation results were compared for AUCs of ROC curves (ROC_AUC), Accuracy, Specificity and Sensitivity. Students’ pairwise t tests were performed. Stars represented being significant: * p < 0.05. c. Performance of different genetic models. The values for each performance measurement was represented as ‘mean ± standard deviation’. d. Survival curves of sub-groups of cases classified with different genetic models. The curves were based on the prediction results of 5-fold cross-validation testing datasets, and the standard deviations were shown in error bars. Gehan-Breslow-Wilcoxon test p values on the overall survival difference between sub-groups were indicated

Back to article page