Predictive Value Calculator
Enter the four cells of a diagnostic 2×2 table to get positive and negative predictive value, sensitivity and specificity.
How it works
PPV = TP ÷ (TP + FP) · NPV = TN ÷ (TN + FN) · Sensitivity = TP ÷ (TP + FN) · Specificity = TN ÷ (TN + FP)
Predictive values answer the question a patient actually cares about: given my test result, how likely is it correct? PPV is the share of positive tests that are truly diseased; NPV is the share of negative tests that are truly healthy. Unlike sensitivity and specificity — which are properties of the test — predictive values depend heavily on how common the disease is in the group being tested, so a very good test can still produce a low PPV when the condition is rare.
Worked example
From TP = 90, FP = 15, FN = 10, TN = 85 (total 200): PPV = 90 ÷ 105 = 85.7%, NPV = 85 ÷ 95 = 89.5%, sensitivity = 90 ÷ 100 = 90%, specificity = 85 ÷ 100 = 85%. Prevalence in this sample is 100 ÷ 200 = 50%.
Sources: Positive and negative predictive values — Wikipedia
Frequently asked questions
Why do predictive values change with prevalence?
When disease is rare, even a small false-positive rate produces many false alarms relative to true cases, pulling PPV down. The same test in a high-prevalence clinic has a far higher PPV. To adjust a test’s intrinsic sensitivity and specificity to a new prevalence, use the prevalence-adjusted calculator.
What is the difference between PPV and sensitivity?
Sensitivity reads down the disease column — of those who have the disease, how many test positive. PPV reads across the test-positive row — of those who test positive, how many have the disease. They answer different questions and can differ widely.
What if a table cell is zero?
A zero is fine as long as the relevant denominator is positive. If there are no positive tests at all (TP + FP = 0), PPV is undefined and shown as a dash; the same applies to NPV when there are no negative tests.
Related calculators
Educational statistics tool, not medical advice.