To the Editor: When inferences are being drawn from test results, it is imperative that test performance be properly interpreted. In a letter in the March 24 issue,1 Bass et al. suggest that positive serologic tests could be used as markers for asymptomatic toxocariasis. We think that their conclusion overstates the predictive value of the enzyme-linked immunosorbent assay (ELISA) titer that they used. Bayes' formula allows calculation of the predictive value of a positive test if the sensitivity and specificity of the test and the pretest risk of disease are known. The limited information provided on Bass' patients without eosinophilia.
ASJC Scopus subject areas