Positive predictive value

Last revised by Daniel J Bell on 26 May 2022

Positive predictive value of a test/investigation is defined as the proportion of patients with positive results being truly diseased.


Positive predictive value = true positives (TP) detected / total positive results

(total positive results = true positive (TP) + false positive (FP)

Bayes' theorem

One can also determine the PPV with an estimate of sensitivity, specificity, and pretest probability (p).

PPV = [(sensitivity) x (p)] / [sensitivity x (p) + (1 - specificity) x (1 - p)]

Practical points

  • unlike sensitivity and specificity, PPV is highly dependent on the prevalence of the disease in the target population

ADVERTISEMENT: Supporters see fewer/no ads

Cases and figures

  • Figure 1
    Drag here to reorder.
  • Updating… Please wait.

     Unable to process the form. Check for errors and try again.

     Thank you for updating your details.