23 March 2021 : Database Analysis
Construction of Decision Trees Based on Gene Expression Omnibus Data to Classify Bladder Cancer and Its Subtypes
Jia-Quan Zhou1C, Xin-Li Kang1DE, Cong-Jie Xu1EF, Shuan Liu1BD, Yang Wang1AG*DOI: 10.12659/MSM.929394
Med Sci Monit 2021; 27:e929394
Figure 5 (A, C, D) Decision tree, used to classify normal samples and tumor samples. The area under the curve (AUC) was 0.845 in the training set and 0.7133 in the testing set. (B, E, F) Decision tree, used to classify muscle-infiltrating tumor samples and non-muscle-infiltrating tumor samples, AUC is 0.7133 in the training set and 0.7038 in the testing set.