Assessing Rater Performance without a "Gold Standard" Using Consensus Theory

This study illustrates the use of consensus theory to assess the diagnostic performances of raters and to estimate case diagnoses in the absence of a criterion or "gold" standard. A description is provided of how consensus theory "pools" information provided by raters, estimating rater competencies and differentially weighting their responses. Although the model assumes that raters respond without bias (i.e., sensitivity = specificity), a Monte Carlo simulation with 1,200 data sets shows that model estimates appear to be robust even with bias. The model is illustrated on a set of elbow radiographs, and consensus-model estimates are compared with those obtained from follow-up data. Results indicate that with high rater competencies, the model retrieves accurate estimates of competency and case diagnoses even when raters' responses are biased.