Table 5.
Metrics of predictive models. Se—sensitivity, Sp—specificity, Ka—kappa (normalized proportion of correct answers), Pr—precision, AUC—area under the error curve.
| Models | Test Dataset/Training Dataset | ||||
|---|---|---|---|---|---|
| Se | Sp | Ka | Pr | AUC | |
| ALDH3A2 + ODF2 + QSOX2 + hsa-miR-503-5p + ISUP + pT | 0.89/1.00 | 1.00/1.00 | 0.88/1.00 | 1.00/1.00 | 0.944/1.000 |
| ALDH3A2 + ODF2 + QSOX2 + hsa-miR-503-5p + ISUP | 0.89/1.00 | 0.75/1.00 | 0.64/1.00 | 0.80/1.00 | 0.819/1.000 |
| ALDH3A2 + ODF2 + QSOX2 + hsa-miR-503-5p + pT | 0.78/1.00 | 0.62/1.00 | 0.41/1.00 | 0.70/1.00 | 0.701/1.000 |
| ALDH3A2 + ODF2 + QSOX2 + ISUP + pT | 0.89/1.00 | 0.75/1.00 | 0.64/1.00 | 0.80/1.00 | 0.819/1.000 |
| ALDH3A2 + ODF2 + hsa-miR-503-5p + ISUP + pT | 0.89/1.00 | 0.88/1.00 | 0.76/1.00 | 0.89/1.00 | 0.882/1.000 |
| ALDH3A2 + QSOX2 + hsa-miR-503-5p + ISUP + pT | 0.89/0.89 | 0.88/1.00 | 0.76/0.86 | 0.89/1.00 | 0.882/0.944 |
| ODF2 + QSOX2 + hsa-miR-503-5p + ISUP + pT | 0.78/1.00 | 1.00/1.00 | 0.77/1.00 | 1.00/1.00 | 0.889/1.000 |