An Introduction to the Evaluation of a Diagnostic Test: Sensitivity, Specificity, Predictive Value

Abstract

Starting from a 2×2 cross tabulation of “test response” vs “true disease status” it is possible to calculate the sensitivity, the specificity, the positive predictive value and the negative predictive value of that test. Sensitivity is the probability that a person with the disease will be correctly classified by the test. Specificity is the probability that a person without the disease will be correctly classified by the test. Positive predictive value is the probability that a person with a positive test result is affected by the disease. Negative predictive value is the probability that a person with a negative test result is not affected by the disease. Sensitivity and specificity are characteristic of the test, while predictive values are influenced by the prevalence of the disease in the tested population. (Epidemiology_statistics)