Machine learning combining external validation to explore the immunopathogenesis of diabetic foot ulcer and predict therapeutic drugs
Fig 5
Construction of RF, SVM, KNN, NNET, LASSO and DT machine models.
(A) Intersection of the differentially expressed genes and immune-related genes. (B) The cumulative residual distribution of the six models. (C) Residual Boxplots of the six machine learning models, where the red dots indicate the root mean square of the residuals. (D) ROC analysis of six machine learning models with fivefold cross-validation in the test set. (E) The important features in RF, SVM, KNN, NNET, LASSO and DT.