Table 2 Comparison of the predictive ability of the Nomogram model and models constructed in previous studies.
Model | AUC | AUC (95%CI) | Sensitivity (%) | Specificity (%) | Precision (%) | Positive predictive value (%) | Negative predictive value (%) | Youden’s index |
|---|---|---|---|---|---|---|---|---|
Training set | ||||||||
Nomogram model | 0.99 | 0.97, 1.00 | 97.96 | 93.88 | 95.92 | 94.12 | 97.87 | 0.92 |
Rhee et al. model | 0.64 | 0.53, 0.76 | 87.76 | 48.98 | 68.37 | 63.24 | 80.00 | 0.37 |
Aspelund et al. model | 0.70 | 0.59, 0.80 | 83.67 | 51.02 | 67.35 | 63.08 | 75.76 | 0.35 |
Hippisley-Cox and Coupland model | 0.67 | 0.57, 0.78 | 61.22 | 73.47 | 67.35 | 69.77 | 65.45 | 0.35 |
Dagliati et al. model | 0.69 | 0.59, 0.80 | 55.10 | 79.59 | 67.35 | 72.97 | 63.93 | 0.35 |
Testing set | ||||||||
Nomogram model | 0.99 | 0.96, 1.00 | 95.00 | 100.00 | 97.50 | 100.00 | 95.24 | 0.95 |
Rhee et al. model | 0.76 | 0.61, 0.92 | 75.00 | 75.00 | 75.00 | 75.00 | 75.00 | 0.50 |
Aspelund et al. model | 0.73 | 0.57, 0.88 | 55.00 | 80.00 | 67.50 | 73.33 | 64.00 | 0.35 |
Hippisley-Cox and Coupland model | 0.77 | 0.62, 0.92 | 80.00 | 75.00 | 77.50 | 76.19 | 78.95 | 0.55 |
Dagliati et al. model | 0.78 | 0.63, 0.92 | 80.00 | 65.00 | 72.50 | 69.57 | 76.47 | 0.45 |
