Research Paper Volume 15, Issue 8 pp 3120—3140
An artificial neural network model to diagnose non-obstructive azoospermia based on RNA-binding protein-related genes
Figure 7. The predictive performance of an RF diagnosis model in each cohort. (A–E) The ROC analyses of the RF model in the training cohort (A), GSE45885 cohort (B), GSE45887 cohort (C), GSE145467 cohort (D), and the local cohort (E). (F–J) The confusion matrices of the RF model in the training cohort (F), GSE45885 cohort (G), GSE45887 cohort (H), GSE145467 cohort (I), and the local cohort (J). Abbreviation: RF: random forest.