Table 2 COVID-19 predictions performance table.
From: Developing a COVID-19 mortality risk prediction model when individual-level data are not available
Model | Metric | Value |
|---|---|---|
COVID-19 model | AUROC | 0.943, 95% CI: 0.926–0.956 |
COVID-19 model 10% risk cut-off | Percent positive | 8%, 95% CI: 7–9% |
Sensitivity | 71%, 95% CI: 64–79% | |
PPV | 30%, 95% CI: 26–35% | |
COVID-19 model 5% risk cut-off | Percent positive | 15%, 95% CI: 14–16% |
Sensitivity | 88%, 95% CI: 83–93% | |
PPV | 20%, 95% CI: 17–23% | |
CDC high-risk criteria | Percent positive | 40%, 95% CI: 39–42% |
Sensitivity | 98%, 95% CI: 95–100% | |
PPV | 8%, 95% CI: 7–10% |
