Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Experiment Videos

Estimating and comparing diagnostic tests' accuracy when the gold standard is not binary.

Nancy A Obuchowski1

  • 1Department of Quantitative Health Sciences/Wb4, The Cleveland Clinic Foundation, 9500 Euclid Ave, Cleveland, OH 44195, USA. nobuchow@bio.ri.ccf.org

Academic Radiology
|August 16, 2005
PubMed
Summary
This summary is machine-generated.

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Enhancing Study Design and Analysis of MR Imaging Markers Through Measurement Error Modeling.

Journal of magnetic resonance imaging : JMRI·2026
Same author

Scalable Clinical Annotation with Location Evidence (SCALE).

Computers in biology and medicine·2025
Same author

Association of Statistical Methodology and Design in Preclinical Animal Studies With Successful Translation Into Clinical Phase 2 Trials.

Neurology·2025
Same author

Objective Task-Based Evaluation of Quantitative Medical Imaging Methods: Emerging Frameworks and Future Directions.

PET clinics·2025
Same author

Understanding Repeatability and Reproducibility Coefficients for Quantitative Imaging Biomarkers.

Radiology·2025
Same author

ISIT-GEN: An in silico imaging trial to assess the inter-scanner generalizability of CTLESS for myocardial perfusion SPECT on defect-detection task.

ArXiv·2025

This study presents new nonparametric methods for evaluating diagnostic test accuracy when the gold standard is not binary. These methods avoid bias introduced by dichotomizing continuous or ordinal data, offering reliable comparisons.

Area of Science:

  • Biostatistics
  • Medical Diagnostics
  • Statistical Modeling

Background:

  • Assessing diagnostic test accuracy is crucial in clinical research.
  • Traditional methods often rely on binary gold standards, limiting applicability.
  • Non-binary gold standards (continuous, ordinal, nominal) present unique analytical challenges.

Purpose of the Study:

  • To describe nonparametric estimators for diagnostic test accuracy with non-binary gold standards.
  • To extend existing methods for estimating and comparing areas under receiver operating characteristic (ROC) curves.
  • To provide accurate measures and comparison tests for diagnostic accuracy in diverse gold standard scenarios.

Main Methods:

  • Extension of the DeLong et al. nonparametric method for area under the ROC curve estimation.

Related Experiment Videos

  • Application to continuous, ordinal, and nominal scale gold standards.
  • Illustrative examples demonstrating the practical use of the proposed methods.

    • Main Results:

    • Development of nonparametric measures for diagnostic test accuracy and their variances.
    • Presentation of tests for comparing accuracies of two diagnostic tests in paired designs.
    • Summary measures analogous to the area under the ROC curve are provided for non-binary gold standards.

    Conclusions:

    • Dichotomizing non-binary gold standards can introduce bias when applying traditional ROC methods.
    • The described nonparametric methods are valuable for assessing and comparing test accuracy with non-binary gold standards.
    • These methods share limitations common to other summary accuracy indices.