Post-Test Probability Calculator

The calculation relies on Bayes' theorem translated into odds and probabilities. First, the baseline pre-test probability (prevalence) is converted into pre-test odds using the formula: Pre-Test Odds = Prevalence / (1 - Prevalence). Next, test performance metrics are combined into likelihood ratios. The positive likelihood ratio is calculated as Sensitivity / (1 - Specificity), while the negative likelihood ratio is (1 - Sensitivity) / Specificity. Multiplying the pre-test odds by the appropriate likelihood ratio yields the post-test odds. Finally, these post-test odds are converted back into a percentage probability using the equation: Post-Test Probability = Post-Test Odds / (1 + Post-Test Odds).

Imagine evaluating a new screening test for a condition with a known population prevalence of 10% (0.10). This means the pre-test probability is 0.10, resulting in pre-test odds of 0.10 / (1 - 0.10) = 0.111. Suppose the test has a sensitivity of 85% (0.85) and a specificity of 80% (0.80). First, we find the positive likelihood ratio: 0.85 / (1 - 0.80) = 0.85 / 0.20 = 4.25. Multiplying our pre-test odds by this ratio gives post-test odds of 0.111 * 4.25 = 0.471. Converting this back to a probability yields 0.471 / (1 + 0.471) = 0.320, or a 32.0% post-test probability following a positive result.

Always ensure your baseline prevalence accurately reflects the specific patient population you are testing, as prevalence drastically shifts post-test outcomes. Be cautious when applying generalized sensitivity and specificity metrics to specialized or high-risk subgroups. Finally, remember that a positive test does not automatically confirm a diagnosis if the pre-test probability is exceptionally low.