Skip to main content

Table 14 Comparison of the performance of Random Forest (RF) classifier having 10, 50 and 100 trees with different feature set considered at each split (1, 2, 4, 8, and 12) using sampling

From: Comparison of machine learning techniques to predict all-cause mortality using fitness data: the Henry ford exercIse testing (FIT) project

  No. of tree =10 No. of tree =50 No. of tree =100
F = 1 F = 2 F = 4 F = 8 F = 12 F = 1 F = 2 F = 4 F = 8 F = 12 F = 1 F = 2 F = 4 F = 8 F = 12
Sensitivity 90.62% 91.01% 89.46% 87.40% 86.90% 96.07% 95.47% 94.67% 93.63% 93.14% 96.73% 95.97% 94.85% 93.95% 93.59%
Specificity 96.49% 96.56% 96.67% 96.79% 96.83% 96.84% 96.85% 97.06% 97.11% 97.15% 96.88% 96.88% 97.04% 97.19% 97.18%
Precision 72.78% 73.40% 74.28% 75.31% 75.67% 75.50% 75.57% 77.27% 77.73% 77.99% 75.74% 75.81% 77.08% 78.35% 78.28%
F-score 80.72% 81.26% 81.17% 80.90% 80.90% 84.55% 84.36% 85.09% 84.94% 84.90% 84.96% 84.71% 85.05% 85.44% 85.25%
AUC 80.72 81.26 81.17 80.90 80.90 0.97 0.97 0.97 0.97 0.97 0.97 0.97 0.97 0.97 0.97
RMSE 0.2 0.19 0.2 0.2 0.2 0.18 0.18 0.18 0.18 0.18 0.18 0.18 0.18 0.18 0.18