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

Bayesian approaches to modeling the conditional dependence between multiple diagnostic tests.

N Dendukuri1, L Joseph

  • 1Department of Epidemiology and Biostatistics, McGill University, Montreal, Quebec, Canada. nandini.dendukuri@smhc.qc.ca

Biometrics
|March 17, 2001
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

Lung ultrasonography used as a diagnostic test for respiratory disease diagnosis in calves: systematic review and meta-analysis using a Bayesian latent-class modelling approach.

Journal of dairy science·2026
Same author

Effectiveness of preimplantation genetic testing in sickle cell disease: insights from a single-center experience.

Journal of assisted reproduction and genetics·2026
Same author

Evaluating the Impact of Patient Education on Knowledge, Self-Efficacy, and Quality of Life in Chronic Obstructive Pulmonary Disease.

La Clinica terapeutica·2025
Same author

Position paper on advancing sickle cell disease management in France by bridging the clinical practices and guidelines through expert insights.

Transfusion and apheresis science : official journal of the World Apheresis Association : official journal of the European Society for Haemapheresis·2024
Same author

Randomized preclinical study of machine perfusion in vascularized composite allografts.

The British journal of surgery·2021
Same author

Systematic review and meta-analysis of refractometry for diagnosis of inadequate transfer of passive immunity in dairy calves: Quantifying how accuracy varies with threshold using a Bayesian approach.

Preventive veterinary medicine·2021
Same journal

Fast penalized generalized estimating equations for large longitudinal functional datasets.

Biometrics·2026
Same journal

Causally-interpretable random-effects meta-analysis.

Biometrics·2026
Same journal

Statistical inference for mean function of partially observed functional time series.

Biometrics·2026
Same journal

Subgroup identification via Interaction Tree and Mixed Model for Repeated Measures with application to Alzheimer's disease.

Biometrics·2026
Same journal

Finite mixtures of linear quantile regressions with concomitant variables: a solution to endogeneity in longitudinal data modeling.

Biometrics·2026
Same journal

Discussion on "INTACT: a method for integration of longitudinal physical activity data from multiple sources" by Jingru Zhang, Erjia Cui, Hongzhe Li, and Haochang Shou.

Biometrics·2026
See all related articles

This study introduces a Bayesian method to accurately estimate disease prevalence and diagnostic test performance, even when tests are conditionally dependent. The approach is particularly useful with only two tests, offering more reliable results than traditional methods.

Area of Science:

  • Biostatistics
  • Epidemiology
  • Medical Diagnostics

Background:

  • Diagnostic test analyses often assume conditional independence, which may not hold true in real-world scenarios, especially without a gold standard test.
  • Traditional statistical models require at least four diagnostic tests for identifiable solutions when accounting for conditional dependence, a requirement often unfeasible.
  • Conditional dependence between diagnostic tests can lead to biased estimates of disease prevalence and test accuracy.

Purpose of the Study:

  • To develop a Bayesian approach for inferring disease prevalence and diagnostic test properties while accounting for conditional dependence between tests.
  • To specifically address situations with only two diagnostic tests, where traditional methods are often non-identifiable.
  • To propose both fixed and random effects models to accommodate potential variations in test properties.

Related Experiment Videos

Main Methods:

  • Employed a Bayesian framework to model disease prevalence and test characteristics.
  • Developed fixed and random effects models to handle conditional dependence between diagnostic tests.
  • Utilized prior information to address non-identifiability issues inherent in models with fewer than four tests.

Main Results:

  • The Bayesian approach provides adjusted inferences for disease prevalence and test properties, even with only two conditionally dependent tests.
  • Posterior distributions are sensitive to prior information, especially with limited test data, highlighting the importance of accurate prior specification.
  • When test correlation is known precisely, the methods effectively adjust for dependence; otherwise, they incorporate uncertainty, leading to wider interval estimates.

Conclusions:

  • The proposed Bayesian methods offer a viable solution for estimating disease prevalence and test accuracy in the presence of conditional dependence, particularly with limited diagnostic tests.
  • The strong dependence on prior information underscores the need for careful selection and validation of priors in non-identifiable models.
  • The methods provide robust inferences by explicitly acknowledging and incorporating the uncertainty associated with unknown test correlations.