Skip to main content

Table 6 Predictive performance using all 16 features in decision trees, random forests, and support vector machines for healthy controls (HCs) versus rheumatoid arthritis (RA) patients and osteoarthritis (OA) versus RA patients

From: Isotypes of autoantibodies against novel differential 4-hydroxy-2-nonenal-modified peptide adducts in serum is associated with rheumatoid arthritis in Taiwanese women

Algorithms* Accuracy Precision F1 score Sensitivity Specificity AUC
HC v.s. RA
 DT 0.75 (0.70–0.79) 0.77 (0.69–0.86) 0.69 (0.63–0.75) 0.62 (0.56–0.69) 0.85 (0.81–0.90) 0.74 (0.69–0.78)
 RF 0.80 (0.79–0.82) 0.83 (0.81–0.85) 0.79 (0.77–0.80) 0.76 (0.74–0.79) 0.84 (0.82–0.87) 0.88 (0.87–0.89)
 SVM 0.71 (0.64–0.78)) 0.90 (0.78–1.00) 0.62 (0.51–0.73) 0.49 (0.37–0.62) 0.94 (0.89–1.00) 0.86 (0.78–0.93)
OA v.s. RA
 DT 0.78 (0.73–0.83) 0.90 (0.85–0.95) 0.77 (0.70–0.84) 0.68 (0.58–0.78) 0.89 (0.82–0.96) 0.79 (0.74–0.83)
 RF 0.80 (0.75–0.85) 0.84 (0.78–0.90) 0.84 (0.80–0.88) 0.86 (0.79–0.92) 0.68 (0.52–0.85) 0.87 (0.82–0.92)
 SVM 0.66 (0.56–0.70) 0.66 (0.56–0.70) 0.79 (0.72–0.82 0.47 (0.33–0.60) 0.93 (0.88–0.99) 0.82 (0.80–0.85)
  1. *DT, decision trees; RF, random forests; SVM, support vector machines