fig5

Figure 5. Multivariate regression and machine learning models for wound age estimation using the triad system. (A-C) Optimal multivariate linear regression models for the mmu-miR-15b-5p/Rsad2/RSAD2 triad (A), mmu-miR-31-5p/Cst6/CST6 triad (B), and mmu-miR-1983/Krt77/KRT77 triad (C). X₁, X₂, and X₃ represent the expression levels of miRNA, target mRNA, and corresponding protein, respectively; (D and E) Random Forest (D) and XGBoost (E) models for the mmu-miR-15b-5p/Rsad2/RSAD2 triad, constructed within the optimal post-injury windows; (F and G) Random Forest (F) and XGBoost (G) models for the mmu-miR-31-5p/Cst6/CST6 triad, constructed within the optimal post-injury windows; (H and I) Random Forest (H) and XGBoost (I) models for the mmu-miR-1983/Krt77/KRT77 triad, constructed within the optimal post-injury windows.