Research Paper Volume 16, Issue 9 pp 8361—8377
Comprehensive bioinformatics analytics and in vivo validation reveal SLC31A1 as an emerging diagnostic biomarker for acute myocardial infarction
Figure 3. Evaluation of the robustness of the 9 mainstream machine algorithms to identify the best ones for AI construction. (A, B) Precision-Recall (PR) curve in the training set and validation set, respectively. (C, D) Receiver Operative Characteristic (ROC) curve performed in the training set and validation set, respectively. (E) Calibration curve demonstrating the bias between predictive values and realistic values for the machine learning algorithms involved in the present study. (F) DCA for the machine learning algorithms involved in the present study.