The Area under an ROC Curve with Limited Information

Medical Decision MakingPublished 1 March 2003

Wilbert B. van den Hout

DOI10.1177/0272989x03251246

Source URL

Citations33

SJR quartileQ1

SJR score1.48

SNIP1.35

TL;DR

The area under the receiver operating characteristic (ROC) curve of a diagnostic test can be used as a summary measure for its discriminative ability, and assuming that the unknown ROC curve is concave renders a higher minmax approximation for the area under it.

Abstract

The area under the receiver operating characteristic (ROC) curve of a diagnostic test can be used as a summary measure for its discriminative ability. If only a single point of an ROC curve is available, then the entire form of the ROC curve is unknown and the area under it cannot be calculated. Assuming that the unknown ROC curve is either monotone or concave, lower and upper bounds are derived for the area. From these bounds, the minmax approximations are obtained. Compared to only assuming monotonicity, assuming that the unknown ROC curve is concave renders a higher minmax approximation for the area under it, with tighter bounds.

Keywords

Computer ScienceDecision SciencesHealth Professions

RadiologyThe meaning and use of the area under a receiver operating characteristic (ROC) curve.

21,812 Citations1982J A Hanley, Barbara J. McNeil

A representation and interpretation of the area under a receiver operating characteristic (ROC) curve obtained by the "rating" method, or by mathematical predictions based on patient characteristics, is presented and it is shown that in such a setting the area represents the probability that a randomly chosen diseased subject is (correctly) rated or ranked with greater suspicion than a random chosen non-diseased subject.

Statistics in MedicineMULTIVARIABLE PROGNOSTIC MODELS: ISSUES IN DEVELOPING MODELS, EVALUATING ASSUMPTIONS AND ADEQUACY, AND MEASURING AND REDUCING ERRORS

9,798 Citations1996Frank E. Harrell, Kerry L. Lee +1 more

Journal of Clinical EpidemiologyMeta-analytic methods for diagnostic test accuracy

467 Citations1995Les Irwig, Petra Macaskill +2 more

A method is developed to estimate Summary Receiver Operating Characteristic Curves, thereby taking account of possible test threshold differences between studies, and to highlight important defects in quality and how they affect summary estimates.

Medical Decision MakingA General Regression Methodology for ROC Curve Estimation

272 Citations1988Anna N.A. Tosteson, Colin B. Begg

The new method provides a mechanism for pinpointing the effect that interobserver variability has on the ROC curve, and allows for the adjustment of ROC curves for temporal variation and case mix, and provides a way to assess the incremental diagnostic value of a test.

Medical Decision MakingThe Area under the ROC Curve and Its Competitors

185 Citations1991Jørgen Hilden

The area under the receiver operating characteristic (ROC) curve is shown here to be an inconsistent criterion: tests of indistinguishable clinical impacts may have different areas and a class of diagnosticity measures (DMs) of proven optimality is proposed instead.

Medical Decision MakingDetermining the Area under the ROC Curve for a Binary Diagnostic Test

127 Citations2000Scott B. Cantor, Michael W. Kattan

The authors provide a simple calculation for the unbiased estimation of the area under the ROC curve for a binary diagnostic test or a continuously valued test result that is effectively used in a binary way.

Academic RadiologyComparison of receiver operating characteristic curves on the basis of optimal operating points

80 Citations1996Ethan J. Halpern, Michael Albert +3 more

ROC curves may be compared on the basis of utilities associated with their OOPs to provide results that differ from comparisons of curves at a fixed false-positive fraction.

Medical Decision MakingROC Curves and the Areas under Them for Dichotomized Tests

26 Citations1994Yvonne T. van der Schouw, Huub Straatman +1 more

The authors present equations for estimating the area under the ROC curve and the AUC when only one pair of a true- and a false-positive rate is given, for inherently logistically and normally distributed data.