Evidence-appraisal glossary
ROC curve and AUC
An ROC curve plots a test's true-positive rate against its false-positive rate across every possible cutoff. The area under the curve (AUC) condenses that plot into one number: the probability the test ranks a random positive case above a random negative one. 0.5 is chance; 1.0 is perfect.
Also called: ROC, AUC, AUROC, c-statistic, receiver operating characteristic.
A receiver operating characteristic (ROC) curve shows the trade-off between sensitivity (true-positive rate) and 1 minus specificity (false-positive rate) as the decision threshold for a test or model varies. The area under the curve (AUC), also called the c-statistic, equals the probability that the test assigns a higher score to a randomly chosen case than to a randomly chosen non-case. An AUC of 0.5 means no better than a coin flip; 1.0 means perfect separation. When reading a study, check the AUC as a measure of discrimination, but remember it says nothing about whether predicted probabilities are numerically correct, and it can look impressive even when the test performs poorly at the specific cutoff clinicians would actually use. Example: a diagnostic model with an AUC of 0.80 ranks a random diseased patient above a random healthy one 80 percent of the time, though its usefulness still depends on which threshold is chosen.
This is a plain-language methodology definition for reading research. It is general education, not medical advice.