[Accuracy evaluation of diagnostic test in laboratory]

Abstract

The theory and application of ROC curve are briefly introduced in this paper. Three main ROC curve related indices, area under curve (AUC), partial area under curve (pAUC), and sensitivity at a particular false-positive-rate (1-specificity) [Se(FPR=e)], are used to analyze a real data of five hepatitis B surface agent kits with calculated steps and explanation, including the bootstrap method for statistical inference of these indices.