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

Modelling clinical trials in heterogeneous samples.

Wenlei Liu1, Wei Zhao, Michele L Shaffer

  • 1Department of Health Evaluation Sciences, Penn State College of Medicine, Hershey, 17033, USA. wliu@hes.hmc.psu.edu

Statistics in Medicine
|July 12, 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

Non-invasive liver fibrosis scores and mortality in a cohort of World Trade Center rescue/recovery workers.

BMJ open gastroenterology·2025
Same author

Training International Medical Graduate Internal Medicine Residents in Pelvic Examinations and Pap Smears.

Journal of general internal medicine·2025
Same author

Inhaled pirfenidone solution (AP01) for IPF: a randomised, open-label, dose-response trial.

Thorax·2023
Same author

Covariation of changing patent ductus arteriosus management and preterm infant outcomes in Pediatrix neonatal intensive care units.

Journal of perinatology : official journal of the California Perinatal Association·2021
Same author

The Trial to Reduce Antimicrobial Use in Nursing Home Residents With Alzheimer Disease and Other Dementias (TRAIN-AD): A Cluster Randomized Clinical Trial.

JAMA internal medicine·2021
Same author

Assessing the Value to the Patient of New Technologies in Anatomic Total Shoulder Arthroplasty.

The Journal of bone and joint surgery. American volume·2021

Population heterogeneity significantly impacts clinical trial results. A proposed two-stage trial design enhances efficacy testing power by identifying sensitive subgroups, leading to more precise treatment effect estimation.

Area of Science:

  • Pharmacogenomics
  • Clinical Trial Design
  • Biostatistics

Background:

  • Individual variability in genetic, phenotypic, and environmental factors influences drug metabolism, clinical response, and side effects.
  • Population heterogeneity's impact on clinical trial findings and treatment effect estimation is not fully understood.
  • Unmeasured covariates, such as genetic susceptibility, contribute to heterogeneity in clinical trial samples.

Purpose of the Study:

  • To quantify the impact of population heterogeneity on treatment effect estimation in clinical trials.
  • To propose and evaluate a two-stage clinical trial design for improved efficacy testing in heterogeneous populations.
  • To address biased estimation of treatment effects caused by population heterogeneity.

Main Methods:

Related Experiment Videos

  • Utilized logistic regression models to quantify heterogeneity's impact on treatment effect estimation in two-armed trials.
  • Proposed a two-stage trial: Stage 1 estimates covariate effects in a training dataset.
  • Stage 2 identifies sensitive subgroups ('responders') for efficacy testing based on drug-related characteristics.

    • Main Results:

    • Population heterogeneity can bias treatment effect estimation in both contaminated and uncontaminated groups.
    • The proposed two-stage trial design significantly increases efficacy testing power compared to a full trial.
    • Two-stage trials are more efficient when covariate effects are larger, enrolling fewer participants for a more specified population.

    Conclusions:

    • Population heterogeneity poses a significant challenge to accurate treatment effect estimation in clinical trials.
    • A two-stage trial design offers a powerful and efficient approach to efficacy testing in heterogeneous populations.
    • Identifying and selecting responders in a two-stage trial leads to more precise and applicable clinical trial findings.