Table 4. Comparison of AUCs of the nomogram model, MOTCT, POICT and PSI for predicting the severity of COVID-19.
| Feature evaluated | AUC value (95% CI) | Cutoff value | Sensitivity (%) | Specificity (%) | Accuracy (%) | PPV (%) | NPV (%) | P values |
|---|---|---|---|---|---|---|---|---|
| Nomogram model | 0.900 (0.849–0.952) | 136.5 | 86.1 | 80.0 | 84.7 | 93.5 | 63.2 | |
| MOTCT, mg | 0.813 (0.732–0.894) | 107,720.0 | 80.0 | 75.5 | 76.5 | 49.3 | 92.7 | 0.003a |
| POICT, % | 0.805 (0.724–0.886) | 5.9 | 73.7 | 78.8 | 77.6 | 50.8 | 90.8 | 0.001b |
| PSI score | 0.751 (0.668–0.833) | 63.5 | 60.0 | 81.5 | 76.5 | 49.1 | 87.2 | <0.001c |
COVID-19, coronavirus disease 2019; AUC, area under the receiver operating characteristic curve; 95% CI, 95% confidence intervals; PPV, positive predictive value; NPV, negative predictive value; MOICT, the mass of infection in the whole lung; POICT, the percentage of infection in the whole lung; PSI, pneumonia severity index; a, b, and c, the nomogram model is significantly better than MOICT, POICT and PSI, respectively.