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

Confidence intervals for predictive values with an emphasis to case-control studies.

Nathaniel D Mercaldo1, Kit F Lau, Xiao H Zhou

  • 1Department of Biostatistics, University of Washington, Seattle, WA 98027, USA.

Statistics in Medicine
|August 24, 2006
PubMed
Summary

This study introduces a new method for estimating positive and negative predictive values (PPV/NPV) and their confidence intervals for diagnostic tests. The method improves accuracy for individual patient risk assessment in diseases like Alzheimer's and breast cancer.

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

Weight Gain on Lorlatinib is Associated with Accumulation of Visceral Adipose Tissue.

Journal of thoracic oncology : official publication of the International Association for the Study of Lung Cancer·2026
Same author

Impact of Postlabeling Delay on Arterial Spin-Labeling MRI-Based Measures of Cerebral Blood Flow in a Simultaneous PET/MRI Study of Aging.

AJNR. American journal of neuroradiology·2026
Same author

Magnetic susceptibility matched fluid for neuroimaging assessed in histology and stereology: A pilot study.

Journal of neuropathology and experimental neurology·2026
Same author

Molecular tumor volume on PSMA PET/CT is an independent imaging biomarker associated with progression-free survival in patients with oligorecurrent prostate cancer.

American journal of nuclear medicine and molecular imaging·2025
Same author

Venous arterial spin labeling MRI signal is associated with oxygen supply-independent reduction in cerebral oxygen extraction in typically aging older adults.

Imaging neuroscience (Cambridge, Mass.)·2025
Same author

Associations of Well-Being Measures With Suicidal Ideation in Surgeons.

The Journal of surgical research·2025

Area of Science:

  • Biostatistics
  • Medical Diagnostics
  • Genetics

Background:

  • Diagnostic test accuracy is often described by sensitivity and specificity, which are prevalence-independent.
  • However, positive and negative predictive values (PPV and NPV) are crucial for assessing diagnostic accuracy in individual patients.
  • PPV and NPV are influenced by both test accuracy and disease prevalence, making confidence interval estimation complex.

Purpose of the Study:

  • To develop a novel method for estimating PPV and NPV, including their confidence intervals.
  • To compare different confidence interval estimation methods (standard, adjusted, logit-transformed) for PPV and NPV.
  • To apply the developed methods to real-world case-control studies.

Main Methods:

  • A simulation study was conducted to compare coverage probabilities and interval lengths of various confidence interval methods.

Related Experiment Videos

  • The novel estimation method for PPV and NPV was developed.
  • The methods were applied to two case-control studies: ApoE.e4 for Alzheimer's disease and a 70-gene signature for breast cancer metastasis.

    • Main Results:

    • The simulation study provided insights into the performance of different confidence interval estimation techniques.
    • The novel method was successfully applied to analyze diagnostic and prognostic tests.
    • The study demonstrated the utility of the new approach in evaluating genetic and gene-expression-based biomarkers.

    Conclusions:

    • A novel and effective method for estimating PPV, NPV, and their confidence intervals has been developed.
    • The proposed method offers improved accuracy for individual patient risk assessment.
    • The approach is applicable to various diagnostic and prognostic scenarios, including genetic and genomic applications.