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

Alternative methods to evaluate trial level surrogacy.

Josè Cortiñas Abrahantes1, Ziv Shkedy, Geert Molenberghs

  • 1Center for Statistics, Hasselt University, Campus Diepenbeek, B3590 Diepenbeek, Belgium. jose.cortinas@uhasselt.be

Clinical Trials (London, England)
|June 19, 2008
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

Evaluation of the study carried out by ANSES on the effectiveness of sanitary shucking of queen scallops (<i>Aequipecten opercularis</i>) contaminated by okadaic acid toxins.

EFSA journal. European Food Safety Authority·2026
Same author

Evaluation of surrogate endpoints for survival outcomes using the surrogate package in R.

Computer methods and programs in biomedicine·2026
Same author

Integrating oral health screening into general practice: validation study of the Oral Health Screener.

Scientific reports·2026
Same author

Time-Scale Target Parameters and Two-Step Estimation in Longitudinal Trials for Progressive Diseases.

Statistics in medicine·2026
Same author

Handling Missing Data in Participants with Baseline but No Post-Baseline Data.

Pharmaceutical statistics·2026
Same author

Use of clustering techniques for clinical and epidemiological research: practical tips using an example from rheumatology.

Journal of clinical epidemiology·2026
Same journal

A statistical evaluation of decision-making methods and the efficiency of Bayesian multi-arm multi-stage trials.

Clinical trials (London, England)·2026
Same journal

Accounting for non-adherence: A re-analysis of the Liraglutide Effect and Action in Diabetes: Evaluation of Cardiovascular Outcome Results trial.

Clinical trials (London, England)·2026
Same journal

Phase I design for partially ordered groups with late-onset toxicity.

Clinical trials (London, England)·2026
Same journal

Trial informed consent forms, the Declaration of Helsinki and the SPIRIT 2025 statement.

Clinical trials (London, England)·2026
Same journal

17th Annual University of Pennsylvania Conference on statistical issues in clinical trials - Covariate adjustment in randomized clinical trials: New methods and applications (Morning panel discussion).

Clinical trials (London, England)·2026
Same journal

17th Annual University of Pennsylvania Conference on statistical issues in clinical trials - Covariate adjustment in randomized clinical trials: New methods and applications (Afternoon panel discussion).

Clinical trials (London, England)·2026
See all related articles

This study introduces advanced machine learning methods for evaluating trial-level surrogacy, offering more stable and reliable measures. Cross-validation is crucial for accurate surrogacy estimates, avoiding overly optimistic results.

Area of Science:

  • Biostatistics
  • Clinical Trial Methodology
  • Machine Learning in Medicine

Background:

  • Established foundations for surrogate endpoint evaluation in clinical trials by Prentice, Freedman, Graubard, Schatzkin, Buyse, Alonso, and Molenberghs.
  • Previous methodologies often relied on specific assumptions about the association between treatment effects and distributions.

Purpose of the Study:

  • To propose and evaluate alternative procedures for assessing trial-level surrogacy without pre-specifying the type of association.
  • To investigate a cross-validation correction for surrogacy measures and construct confidence intervals.

Main Methods:

  • Employed machine learning techniques including regression trees, bagging, random forests, and support vector machines.
  • Utilized bootstrap methods for confidence intervals and cross-validation for correction.

Related Experiment Videos

  • Applied methods to clinical studies in ophthalmology, colorectal cancer, and schizophrenia.

    • Main Results:

    • Random forest and bagging models yielded more stable surrogacy measures with narrower confidence intervals compared to linear regression and support vector regression.
    • Trial-level surrogacy estimates for advanced colorectal cancer differed significantly from previously reported findings.
    • Alternative methods, particularly random forest and bagging, demonstrated robust performance.

    Conclusions:

    • Flexible modeling techniques enhance the evaluation of surrogate endpoints by accommodating diverse associations.
    • Cross-validation is essential to prevent overestimation of trial-level surrogacy.
    • Bootstrap methods are recommended for confidence intervals over the delta method due to its limitations with large samples and potential for range violation.