PPV and NPV Post Test Probability Calculator

Clinical calculation support · Verify results before clinical use

Diagnostic Test Predictive Values

Enter sensitivity, specificity, and pretest probability as percentages (0–100).

Bayes-based

Probability of a positive test among people who have the condition.

%

Probability of a negative test among people who do not have the condition.

%

Estimated probability of the condition before this test, expressed as a percentage.

%

Understanding PPV and NPV

Positive predictive value (PPV) is the probability that a person has the condition given a positive test. Negative predictive value (NPV) is the probability that a person does not have the condition given a negative test.

Both depend on sensitivity, specificity, and pretest probability. Predictive values therefore change with the clinical setting and the population being tested; they should not be treated as fixed properties of a test.

Equations used

MeasureFormula
PPV(Sensitivity × Pretest probability) ÷ [(Sensitivity × Pretest probability) + ((1 − Specificity) × (1 − Pretest probability))]
NPV[Specificity × (1 − Pretest probability)] ÷ [((1 − Sensitivity) × Pretest probability) + (Specificity × (1 − Pretest probability))]

Clinical context

  • A higher pretest probability generally increases PPV and decreases NPV, all else being equal.
  • A lower pretest probability generally decreases PPV and increases NPV, all else being equal.
  • Use a pretest probability appropriate to the patient and clinical setting. Do not substitute population prevalence automatically when the individual clinical probability differs.
  • These estimates do not independently determine whether treatment, further testing, or referral is indicated.

Interpretation and limitations

The calculator applies standard Bayes-based predictive-value equations using the sensitivity and specificity entered by the user. It assumes those estimates are applicable to the patient and setting being considered.

Before interpreting a result

  • Confirm the source, threshold, and population from which sensitivity and specificity were derived.
  • Consider spectrum effects, verification bias, and uncertainty in diagnostic-accuracy estimates where relevant.
  • Interpret results alongside the history, examination, other tests, and clinical judgement.
  • A value may be undefined at mathematically degenerate boundary combinations where the probability of that test result is zero.

References

Grimes DA, Schulz KF.

Uses and abuses of screening tests. The Lancet. 2002;359(9309):881–884. DOI: 10.1016/S0140-6736(02)07948-5; PMID: 11897304.

Deeks JJ, Altman DG.

Diagnostic tests 4: likelihood ratios. BMJ. 2004;329:168–169. DOI: 10.1136/bmj.329.7458.168; PMID: 15258077.

Altman DG, Bland JM.

Diagnostic tests 2: Predictive values. BMJ. 1994;309:102. DOI: 10.1136/bmj.309.6947.102; PMID: 8038641.