Receiver operating characteristic analysis: A primer

Research output: Contribution to journalArticlepeer-review

102 Scopus citations

Abstract

In summary, the ROC curve has found many useful applications in radiology. While the statistics and mathematics behind ROC analysis can be complex, the ROC curve is fundamentally just a plot of the trade-off between sensitivity and specificity. In fact, many of the assumptions of ROC analysis (binary classification, reliance on a reference standard) are the same as those necessary to calculate sensitivity and specificity. An indication of an observer's degree of diagnostic certainty is the key additional data element that must be collected to calculate an ROC curve. Ongoing developments in ROC analysis will address more complex types of diagnostic situations and will likely expand the applicability of ROC analysis.

Original languageEnglish (US)
Pages (from-to)909-916
Number of pages8
JournalAcademic radiology
Volume12
Issue number7
DOIs
StatePublished - Jul 2005

ASJC Scopus subject areas

  • Radiology Nuclear Medicine and imaging

Fingerprint

Dive into the research topics of 'Receiver operating characteristic analysis: A primer'. Together they form a unique fingerprint.

Cite this