Receiver operating characteristic curve

The ROC curve plots sensitivity against 1-specificity (ie, the false-positive rate) for all cut-off values measured for the diagnostic test. The ROC curve for a specific diagnostic test (black curved line) demonstrates the interchange between sensitivity and specificity for different cut-off values. For example, point A indicates a fairly strict cut-off; it has high specificity (ie, low false-positive rate) but poor sensitivity (approximately 40%). By contrast, point B indicates a more liberal cut-off; it has better sensitivity (>90%) but poor specificity (approximately 30% [ie, false-positive rate 70%]). The AUC of the ROC curve represents the overall accuracy of the test. A test that performs no better than chance would be represented by a straight line (dashed red line) with an AUC of 0.5. A near-perfect test would have a rectangular configuration (dashed blue line) with an AUC approaching 1.0.