Comparative statistical properties of expected utility and area under the ROC curve for laboratory studies of observer performance in screening mammography

摘要

Rationale and ObjectivesOur objective is to determine whether expected utility (EU) and the area under the ROC (AUC) are consistent with one another as endpoints of observer performance studies in mammography. These two measures characterize ROC performance somewhat differently. We compare these two study endpoints at the level of individual reader effects, statistical inference, and components of variance across readers and cases.