Table 3. Relationship between AUC and diagnostic accuracy.
Items | Evaluation Criteria | |||||
---|---|---|---|---|---|---|
AUC[9] | 0.9–1.0 | 0.8–0.9 | 0.7–0.8 | 0.6–0.7 | 0.5–0.6 | <0.5 |
Diagnostic accuracy | Excellent | Very good | Good | Sufficient | Bad | Test not useful |
Note: [9] means area under the ROC curve, the closer the curve is located at upper-left hand corner and the large the AUC, the better the model is.