An ROC curve analysis compares three diagnostic tests for detecting latent TB infection. Test A has AUC = 0.91, Test B has AUC = 0.74, and Test C has AUC = 0.50. Which statement is CORRECT?
- A Test C is the most sensitive test
- B Test B should be preferred because it balances sensitivity and specificity best
- C Test A has the best overall discriminative ability; Test C performs no better than chance ✓
- D AUC values above 0.70 are considered excellent and clinically usable
Correct answer: C. Test A has the best overall discriminative ability; Test C performs no better than chance
Explanation
The AUC (area under the ROC curve) represents overall discriminative accuracy; AUC of 1.0 is perfect, 0.5 is no better than chance. Test A with AUC 0.91 is excellent, Test B (0.74) is acceptable, and Test C (0.50) has zero discriminative ability. AUC ≥ 0.90 is classified as excellent; 0.80–0.90 good; 0.70–0.80 acceptable. The optimal cut-off on the ROC curve (Youden index) maximises sensitivity + specificity − 1.
Reference: Park's Textbook of Preventive and Social Medicine, 27th ed.
High-yield for: NEET PGINI-CETNExTFMGEUSMLEPLABMRCP
Written and medically reviewed by the StethoPrep medical team.