Fig. 9

Random forest and decision tree analysis. Based on the expression value of each FA gene and related clinical traits, we utilized the cytogenetic risk as the outcome variable. We obtained the values of mean decrease accuracy (a) and mean decrease Gini (b) for random forest analysis using a “randomforest” R package. The result was visualized using the “ggdotchart” function. Subsequently, we performed ROC analysis with the “pROC” R package (c). For the decision tree analysis, we randomly selected 2/3 samples as the training set and 1/3 as the testing set and visualized the result using the “rpart” R package (d)