Which metric is an example of a predictive value used in clinical decision-making?

• A. Sensitivity
• B. Specificity
• C. False positive rate
• D. Positive Predictive Value

Answer: (D)

Predictive values give the probability that a patient truly has (or does not have) a disease based on the test result. Positive predictive value is the probability that someone actually has the disease given a positive test result, and that is precisely how clinicians translate a positive test into a decision about diagnosis or management. This metric integrates test performance with how common the disease is in the population, because PPV rises when the disease is more prevalent and falls when it is rarer.

Sensitivity and specificity describe how the test performs conditional on disease status or non-disease status, independent of how common the disease is in the population. They answer: if the disease is present, how often is the test positive? and if the disease is absent, how often is the test negative? They are not predictive values themselves. The false positive rate is simply 1 minus specificity, also not a predictive value.