Figure 3
From: Disulfidptosis-associated lncRNAs predict breast cancer subtypes
Evaluation of machine learning Model. (A) ROC curve of verification set (Random Forest model). (B) ROC curve of verification set (Naive Bayesian model). (C) ROC curve of verification set (Support Vector Machine model). (D) ROC curve of verification set (K-Nearest Neighbor model). The ROC curve was constructed through “pROC” R package (version:1.18.0, https://cran.r-project.org/web/packages/pROC/index.html). (E) Sensitivity (Sn), Specificity (Sp), Precision, and F1 Score of verification set. Line graphs was constructed through “ggplot2” R package. (F) The SHAP disease risk factor model identifies critical features and their impact ranges across the dataset. Color coding reflects feature values, with red denoting high values and blue indicating low values.
