Table 6 Performance of Random Forest Predictors at the optimal operating point.
From: Machine learning based predictors for COVID-19 disease severity
Model | Sensitivity | Specificity | PPV | NPV |
|---|---|---|---|---|
ICU (w. lab markers) | 0.73 (0.63, 0.83) | 0.74 (0.67, 0.81) | 0.60 (0.50, 0.70) | 0.84 (0.77, 0.90) |
ICU (no lab markers) | 0.64 (0.53, 0.74) | 0.64 (0.56, 0.72) | 0.48 (0.39, 0.58) | 0.77 (0.69, 0.84) |
ICU (five features) | 0.70 (0.60, 0.81) | 0.70 (0.63, 0.78) | 0.56 (0.46, 0.66) | 0.82 (0.75, 0.88) |
Ventilation (w. lab markers) | 0.72 (0.60, 0.85) | 0.73 (0.67, 0.80) | 0.44 (0.33, 0.55) | 0.90 (0.85, 0.95) |
Ventilation (no lab markers) | 0.60 (0.46, 0.74) | 0.61 (0.53, 0.68) | 0.30 (0.21, 0.39) | 0.84 (0.77, 0.91) |
Ventilation (five features) | 0.74 (0.62, 0.87) | 0.75 (0.68, 0.81) | 0.45 (0.34, 0.57) | 0.91 (0.86, 0.96) |
