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

Life expectancy biases in clinical decision modeling

K M Kuntz1, M C Weinstein

  • 1Department of Medicine, Brigham and Women's Hospital, Boston, MA 02115, USA.

Medical Decision Making : an International Journal of the Society for Medical Decision Making
|April 1, 1995
PubMed
Summary

Clinical decision models using life tables can be biased. Misestimation bias in life expectancy increases with longer life expectancy and less data, leading to suboptimal decisions. Misspecification bias in survival models also impacts outcomes.

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

Cost-effectiveness of intravascular ultrasound and optical coherence tomography use for percutaneous coronary intervention procedures.

European heart journal. Quality of care & clinical outcomes·2026
Same author

Prioritizing Research Informing Antibiotic Prophylaxis Guidelines for Knee Arthroplasty Patients.

JDR clinical and translational research·2021
Same author

Is Antibiotic Prophylaxis Cost-effective for Dental Patients Following Total Knee Arthroplasty?

JDR clinical and translational research·2019
Same author

Force of infection of Helicobacter pylori in Mexico: evidence from a national survey using a hierarchical Bayesian model - CORRIGENDUM.

Epidemiology and infection·2018
Same author

Force of infection of Helicobacter pylori in Mexico: evidence from a national survey using a hierarchical Bayesian model.

Epidemiology and infection·2018
Same author

The Harvard-MIT-NEMC Research Training Program in Medical Informatics.

Yearbook of medical informatics·2016

Area of Science:

  • Biostatistics
  • Health Economics
  • Clinical Decision Modeling

Background:

  • Clinical decision models frequently integrate disease-specific survival data with general population life tables.
  • This approach can introduce two significant biases: misestimation bias and misspecification bias.

Purpose of the Study:

  • To investigate the impact of misestimation bias and misspecification bias in survival models used for clinical decision-making.
  • To quantify how factors like life expectancy, sample size, and censoring affect misestimation bias.
  • To evaluate the consequences of survival model misspecification on life expectancy and cost-effectiveness estimates.

Main Methods:

  • Simulation studies were employed to assess misestimation bias under varying conditions (life expectancy, sample size, censoring).

Related Experiment Videos

  • A simple decision analysis framework was used to examine the impact of sample size imbalances.
  • A cost-effectiveness model was utilized to compare excess-mortality and proportional-hazards survival models.

    • Main Results:

    • Misestimation bias magnitude increases with higher life expectancy, smaller sample sizes, and greater censoring percentages.
    • Imbalances in sample sizes across different strategies led to non-optimal long-term decisions in decision analysis.
    • Life expectancies and incremental cost-effectiveness ratios differed significantly between excess-mortality and proportional-hazards models, with predictable extrapolation patterns.

    Conclusions:

    • Standard life tables in clinical decision models can introduce significant misestimation bias, particularly in long-term projections.
    • Survival model misspecification introduces bias in both life expectancy and cost-effectiveness analyses, affecting clinical recommendations.
    • Careful consideration of potential biases in survival modeling is crucial for accurate clinical decision-making and resource allocation.