Evaluation of enzyme-linked immunosorbent assays: a method of data analysis

Abstract

Diagnostic tests are usually evaluated in terms of simple qualitative measures of sensitivity and specificity. When comparing different quantitative assays such as ELISAs, it is often more useful to deal with actual values (sample optical density/cut-off optical density ratio (OD ratio] rather than the qualitative relationship to the cut-off, i.e. positive or negative. This allows for a statistical approach to the questions of sensitivity and specificity. The National HIV Reference Laboratory of Australia has developed an approach for determining statistical estimates of sensitivity and specificity in terms of delta (delta). Delta is defined as the distance of the mean OD ratio of the sample population from the cut-off measured in standard deviation units. This paper discusses the derivation of this measurement and its usefulness when evaluating ELISA tests.