The use of relative operating characteristic (ROC) curves in test performance evaluation

Abstract

Relative (or receiver) operating characteristic (ROC) curves are a graphical representation of the relationship between sensitivity and specificity of a laboratory test over all possible diagnostic cutoff values. Laboratory medicine has been slow to adopt the use of ROC curves for the analysis of diagnostic test performance. In this tutorial, we discuss the advantages and limitations of the ROC curve for clinical decision making in laboratory medicine. We demonstrate the construction and statistical uses of ROC analysis, review its published applications in clinical pathology, and comment on its role in the decision analytic framework in laboratory medicine.