Figure 3. Construction of machine learning models. (A) The cumulative residual distribution of the four models; (B) Residual boxplots of the four machine learning models, where the red dots indicate the root mean square of the residuals; (C) ROC analysis of four machine learning models with 5-fold cross-validation in the test set; (D) The important features in SVM, RF, XGB, and GLM; (E) Construction of a nomogram to predict DFU risk based on a 5-gene SVM model; (F, G) Calibration curves.