Positive predictive value is defined as...

• A. The probability that a negative test indicates absence of disease.
• B. The probability that a positive test indicates disease.
• C. The probability that a positive test result is truly disease.
• D. The proportion of diseased individuals in the population.

Answer: (C)

Positive predictive value is the probability that a positive test result belongs to someone who actually has the disease. In other words, it’s P(Disease | Test+), the likelihood that the disease is present given a positive result.

This is best captured by saying the positive test result is truly indicating disease. It equals the number of true positives divided by all positive test results (true positives plus false positives). It’s important to note that PPV depends on how common the disease is in the population: when prevalence is higher, PPV tends to be higher; when prevalence is very low, even many positives may be false positives, lowering PPV.

Example: with a disease prevalence of 10%, a test with 90% sensitivity and 95% specificity yields more true positives than false positives, but still many positives may be false positives, so PPV might be around two-thirds in that scenario. This illustrates why PPV is about the probability that a positive result truly indicates disease, not just that the test tends to be positive or that the person has the disease in general.