Glossary
Positive Predictive Value
Also called: PPV, precision
The proportion of positive results that are genuinely positive, which depends heavily on how common the condition is in the tested population.
PPV answers the question a clinician actually asks: this result came back positive, how likely is it to be real. Unlike sensitivity and specificity, it changes with disease prevalence in the population being tested.
Where This Gets Misread
This is where most screening AI claims quietly fall apart. A model with excellent sensitivity and specificity applied to a low-prevalence population produces mostly false positives, and no improvement in the model fixes it. Performance figures from an enriched study set do not survive the move to real screening prevalence.