Fig. 6
From: Bioinformatics analysis of immune-related differentially expressed genes in Kawasaki disease
Diagnostic Model of KD. Genes were progressively filtered by logistic regression, refined by SVM-RFE, and finalized through LASSO regression to obtain the five diagnostic genes. (A) Forest Plot of 12 immunomodulatory related differentially expressed genes (IMRDEGs) included in the Logistic regression model in the KD diagnostic model. (B–C) The number of genes with the lowest error rate (B) and the number of genes with the highest accuracy (C) obtained by the SVM algorithm are visualized. D-E. Diagnostic model plot (D) and variable trajectory plot (E) of LASSO regression model. KD, Kawasaki Disease; IMRDEGs, Immunomodulatory-Related Differentially Expressed Genes; SVM, Support Vector Machine; LASSO, Least Absolute Shrinkage and Selection Operator.
