Table 3 The performance of all algorithms.
From: Machine learning to predict end stage kidney disease in chronic kidney disease
Accuracy | Sensitivity | Specificity | Precision | F1 Score | AUC | |
|---|---|---|---|---|---|---|
Logistic regression | 0.75 (0.72, 0.79) | 0.79 (0.73, 0.85) | 0.75 (0.71, 0.79) | 0.26 (0.24, 0.29) | 0.38 (0.36, 0.41) | 0.79 (0.77, 0.82) |
Naïve Bayes | 0.86 (0.85, 0.87) | 0.72 (0.68, 0.75) | 0.87 (0.86, 0.89) | 0.37 (0.35, 0.40) | 0.49 (0.46, 0.51) | 0.80 (0.77, 0.82) |
Random forest | 0.82 (0.80, 0.85) | 0.76 (0.71, 0.81) | 0.83 (0.80, 0.86) | 0.34 (0.30, 0.39) | 0.46 (0.43, 0.49) | 0.81 (0.78, 0.83) |
K nearest neighbor | 0.84 (0.81, 0.86) | 0.60 (0.57, 0.64) | 0.86 (0.83, 0.89) | 0.35 (0.30, 0.40) | 0.43 (0.40, 0.46) | 0.73 (0.71, 0.75) |
Decision tree | 0.84 (0.82, 0.86) | 0.44 (0.39, 0.49) | 0.89 (0.86, 0.91) | 0.33 (0.26, 0.40) | 0.35 (0.32, 0.39) | 0.66 (0.63, 0.68) |
KFRE | 0.90 (0.90, 0.91) | 0.47 (0.42, 0.52) | 0.95 (0.94, 0.96) | 0.50 (0.45, 0.55) | 0.48 (0.43, 0.52) | 0.80 (0.78, 0.83) |
