Table 6 Comparison of the ML performance with combined feature sets
From: RCC-Supporter: supporting renal cell carcinoma treatment decision-making using machine learning
Decision Tree | Random Forest | GBM | ||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|
Precision | Recall | F-1 score | Accuracy | Precision | Recall | F-1 score | Accuracy | Precision | Recall | F-1 score | Accuracy | |
RF + Expert | 0.82\(\:\pm\:\)0.03 | 0.77\(\:\pm\:\)0.03 | 0.79\(\:\pm\:\)0.03 | 0.89\(\:\pm\:\)0.03 | 0.87\(\:\pm\:\)0.03 | 0.79\(\:\pm\:\)0.03 | 0.81\(\:\pm\:\)0.03 | 0.90\(\:\pm\:\)0.02 | 0.84\(\:\pm\:\)0.03 | 0.81\(\:\pm\:\)0.03 | 0.82\(\:\pm\:\)0.03 | 0.90\(\:\pm\:\)0.02 |
RF + GBM | 0.84\(\:\pm\:\)0.03 | 0.79\(\:\pm\:\)0.03 | 0.80\(\:\pm\:\)0.03 | 0.90\(\:\pm\:\)0.02 | 0.87\(\:\pm\:\)0.03 | 0.79\(\:\pm\:\)0.03 | 0.81\(\:\pm\:\)0.03 | 0.90\(\:\pm\:\)0.02 | 0.85\(\:\pm\:\)0.03 | 0.80\(\:\pm\:\)0.03 | 0.82\(\:\pm\:\)0.03 | 0.90\(\:\pm\:\)0.02 |
GBM + Expert | 0.83\(\:\pm\:\)0.03 | 0.77\(\:\pm\:\)0.03 | 0.79\(\:\pm\:\)0.03 | 0.89\(\:\pm\:\)0.03 | 0.87\(\:\pm\:\)0.03 | 0.79\(\:\pm\:\)0.03 | 0.81\(\:\pm\:\)0.03 | 0.90\(\:\pm\:\)0.02 | 0.86\(\:\pm\:\)0.03 | 0.81\(\:\pm\:\)0.03 | 0.83\(\:\pm\:\)0.03 | 0.91\(\:\pm\:\)0.02 |
GBM + RF + Expert | 0.83\(\:\pm\:\)0.03 | 0.78\(\:\pm\:\)0.03 | 0.80\(\:\pm\:\)0.03 | 0.90\(\:\pm\:\)0.03 | 0.86\(\:\pm\:\)0.03 | 0.78\(\:\pm\:\)0.03 | 0.80\(\:\pm\:\)0.03 | 0.90\(\:\pm\:\)0.03 | 0.84\(\:\pm\:\)0.03 | 0.81\(\:\pm\:\)0.03 | 0.82\(\:\pm\:\)0.03 | 0.90\(\:\pm\:\)0.02 |