Abstract
The estimates of ROC curves, which are frequently used in the assessment of diagnostic tests, may be biased if the sample is restricted to subjects whose disease status has been definitively verified. A method to provide an unbiased estimate of the ROC curve under these sample conditions is proposed. The new method requires information on the probability distribution of test results in the population from which the verified sample is drawn. It is illustrated using data from a study of computed tomography for fever of uncertain origin.
Keywords
Receiver operating characteristicSelection (genetic algorithm)StatisticsSample (material)Selection biasPopulationDiagnostic testDiseaseTest (biology)Computer scienceMathematicsArtificial intelligenceMedicinePathologyPediatrics
Affiliated Institutions
Related Publications
Comparing the Areas under Two or More Correlated Receiver Operating Characteristic Curves: A Nonparametric Approach
Methods of evaluating and comparing the performance of diagnostic tests are of increasing importance as new tests are developed and marketed. When a test is based on an observed...
Computed tomography versus ultrasound of the adrenal gland: a prospective study.
A prospective study of the accuracy of computed tomography (CT) and ultrasound was undertaken in 112 consecutive patients with suspected adrenal disease. CT had a sensitivity of...
The theory of signal detectability
The problem of signal detectability treated in this paper is the following: Suppose an observer is given a voltage varying with time during a prescribed observation interval and...
REPRODUCIBILITY AND RESPONSIVENESS OF EVALUATIVE OUTCOME MEASURES
Objective: This article outlines basic methods for quantifying reproducibility and responsiveness of evaluative outcome measures. Methods: The background noise in stable patient...
ROC Analysis of Mammography and Palpation for Breast Screening
Receiver operating characteristic curves (ROCs) for mammography and clinical palpation individually and in combination are generated using screening data from Breast Cancer Dete...
Publication Info
- Year
- 1984
- Type
- article
- Volume
- 4
- Issue
- 2
- Pages
- 151-164
- Citations
- 104
- Access
- Closed
External Links
Social Impact
Altmetric
PlumX Metrics
Social media, news, blog, policy document mentions
Citation Metrics
104
OpenAlex
Cite This
Robert Gray,
Colin B. Begg,
Robert A. Greenes
(1984).
Construction of Receiver Operating Characteristic Curves when Disease Verification Is Subject to Selection Bias.
Medical Decision Making
, 4
(2)
, 151-164.
https://doi.org/10.1177/0272989x8400400204
Identifiers
- DOI
- 10.1177/0272989x8400400204