Table 2 Specificity for the most competitive classifiers and imputation combinations and CF
From: A comparative study: classification vs. user-based collaborative filtering for clinical prediction
Dataset (% missing) | RF-MI | RF-MICE | LR-MI | LR-MICE | CF |
|---|---|---|---|---|---|
NHANES (baseline=3%) | 0.99 | 0.98 | 0.98 | 0.99 | 0.88 |
NHANES (10%) | 0.97 | 0.96 | 0.99 | 0.99 | 0.88 |
SUPPORT (baseline = 16%) | 0.98 | 0.98 | 0.99 | 0.98 | 0.91 |
Kidney (baseline = 10%) | 0.99 | 0.99 | 0.94 | 0.99 | 0.85 |
NHANES (20%) | 0.97 | 0.96 | 0.96 | 0.98 | 0.88 |
SUPPORT (20%) | 0.97 | 0.96 | 0.97 | 0.97 | 0.85 |
Kidney (20%) | 0.97 | 0.94 | 0.96 | 0.98 | 0.84 |
NHANES (30%) | 0.93 | 0.93 | 0.94 | 0.96 | 0.83 |
SUPPORT (30%) | 0.95 | 0.96 | 0.96 | 0.95 | 0.83 |
Kidney (30%) | 0.98 | 0.98 | 0.95 | 0.97 | 0.82 |