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

Validity of prognostic models: when is a model clinically useful?

Yvonne Vergouwe1, Ewout W Steyerberg, Marinus J C Eijkemans

  • 1Center for Clinical Decision Sciences, Department of Public Health, Erasmus University Rotterdam, The Netherlands.

Seminars in Urologic Oncology
|May 16, 2002
PubMed
Summary

Prognostic models predict patient outcomes but require validation in new populations. Good calibration and discrimination alone do not guarantee clinical usefulness for these predictive tools.

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

Regression Discontinuity Design: Simulation and Application in Two Cardiovascular Trials with Continuous Outcomes.

Epidemiology (Cambridge, Mass.)·2016
Same author

Development of a Prognostic Nomogram for Patients with Peritoneally Metastasized Colorectal Cancer Treated with Cytoreductive Surgery and HIPEC.

Annals of surgical oncology·2016
Same author

Modern modeling techniques had limited external validity in predicting mortality from traumatic brain injury.

Journal of clinical epidemiology·2016
Same author

Calibrating Parameters for Microsimulation Disease Models: A Review and Comparison of Different Goodness-of-Fit Criteria.

Medical decision making : an international journal of the Society for Medical Decision Making·2016
Same author

Feature selection and validated predictive performance in the domain of Legionella pneumophila: a comparative study.

BMC research notes·2016
Same author

Disease-specific survival of patients with invasive cribriform and intraductal prostate cancer at diagnostic biopsy.

Modern pathology : an official journal of the United States and Canadian Academy of Pathology, Inc·2016

Area of Science:

  • Medical Informatics
  • Biostatistics
  • Clinical Epidemiology

Background:

  • Prognostic models are essential for predicting patient outcomes using clinical characteristics.
  • Model performance can degrade when applied to populations different from the derivation cohort.
  • Assessing prognostic model validity in new patient groups is crucial for reliable predictions.

Observation:

  • Model validity encompasses calibration (agreement between predicted and observed probabilities) and discrimination (ability to distinguish outcomes).
  • Clinical usefulness, a third aspect of validity, assesses the model's impact on decision-making.
  • Examples using testicular and prostate cancer models illustrate these validity aspects.

Findings:

  • Calibration and discriminative ability are necessary but insufficient criteria for prognostic model clinical utility.

Related Experiment Videos

  • Prognostic models must demonstrate added value beyond existing information to be considered clinically useful.

    • Implications:

    • Clinical decision-making requires prognostic models that provide demonstrably useful information.
    • Rigorous validation of prognostic models in diverse populations is essential for their effective clinical application.
    • Future research should focus on developing and validating models that enhance clinical decision-making processes.