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

Survival model predictive accuracy and ROC curves.

Patrick J Heagerty1, Yingye Zheng

  • 1Department of Biostatistics, University of Washington, P.O. Box 357232, Seattle, Washington 98195-7232, USA. heagerty@u.washington.edu

Biometrics
|March 2, 2005
PubMed
Summary

This study introduces novel time-dependent accuracy measures for survival models, enhancing predictive accuracy assessment beyond traditional R2 and sensitivity/specificity. These methods improve understanding of model performance over time.

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

Clinical Validation of a Multiplex Urine Biomarker Assay for Surveillance of Recurrent Bladder Cancer.

Clinical cancer research : an official journal of the American Association for Cancer Research·2026
Same author

Data sharing in stepped-wedge cluster randomized trials: suboptimal data availability despite "data available upon request".

Journal of clinical epidemiology·2026
Same author

Impacts of a Public Health Emergency on Cancer Testing Rates, Follow-up, and Cancer Diagnosis: an Evaluation of the COVID-19 Pandemic.

Cancer epidemiology, biomarkers & prevention : a publication of the American Association for Cancer Research, cosponsored by the American Society of Preventive Oncology·2026
Same author

Spinal Manipulation and Clinician-Supported Self-Management for Preventing Chronic Low Back Pain Impact: The PACBACK Randomized Clinical Trial.

JAMA internal medicine·2026
Same author

CRT-Estimands Framework: consensus based extension of the ICH E9(R1) addendum for cluster randomised trials.

BMJ (Clinical research ed.)·2026
Same author

A tutorial on conducting sample size and power calculations for detecting treatment effect heterogeneity in cluster randomized trials with linear mixed models.

International journal of epidemiology·2026

Area of Science:

  • Biostatistics
  • Survival Analysis
  • Machine Learning Evaluation

Background:

  • Assessing survival model predictive accuracy is crucial for clinical and research applications.
  • Existing metrics like R2 and standard sensitivity/specificity have limitations for time-to-event data.
  • Time-dependent evaluation is essential due to evolving risk over time.

Purpose of the Study:

  • To propose novel time-dependent accuracy summaries for survival models.
  • To connect these summaries with existing concordance measures (e.g., Kendall's tau).
  • To demonstrate practical estimation using standard statistical software and Cox regression output.

Main Methods:

  • Development of time-specific sensitivity and specificity calculated over risk sets.

Related Experiment Videos

  • Linking accuracy summaries to a global concordance measure (variant of Kendall's tau).
  • Utilizing semiparametric estimation methods suitable for proportional and nonproportional hazards.

    • Main Results:

    • Introduction of time-dependent accuracy summaries based on risk sets.
    • Demonstration of how Cox regression output can estimate time-dependent sensitivity, specificity, and ROC curves.
    • Validation through simulations and application to real survival data.

    Conclusions:

    • The proposed time-dependent accuracy measures offer a more comprehensive evaluation of survival models.
    • These methods provide valuable insights into model performance across different time points.
    • The approach is practical and can be implemented using readily available statistical tools.