VARIATION OF SENSITIVITY, SPECIFICITY, LIKELIHOOD RATIOS AND PREDICTIVE VALUES WITH DISEASE PREVALENCE

The sensitivity, specificity and likelihood ratios of binary diagnosti c tests are often thought of as being independent of disease prevalenc e. Empirical studies, however, have frequently revealed substantial va riation of these measures for the same diagnostic test in different po pulations. One reason for this discrepancy is related to the fact that only few diagnostic tests are inherently dichotomous, The majority of tests are based on categorization of individuals according to one or several underlying continuous traits. For these tests, the magnitude o f diagnostic misclassification depends not only on the magnitude of th e measurement or perception error of the underlying trait(s), but also on the distribution of the underlying trait(s) in the population rela tive to the diagnostic cutpoint. Since this distribution also determin es prevalence of the disease in the population, diagnostic misclassifi cation and disease prevalence are related for this type of test. We as sess the variation of various measures of validity of diagnostic tests with disease prevalence for simple models of the distribution of the underlying trait(s) and the measurement or perception error, We illust rate that variation with disease prevalence is typically strong for se nsitivity and specificity, and even more so for the likelihood ratios, Although positive and negative predictive values also strongly vary w ith disease prevalence, this variation is usually less pronounced than one would expect if sensitivity and specificity were independent of d isease prevalence. (C) 1997 by John Wiley & Sons, Ltd.