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

A bivariate parametric model for survival and intermediate event times

L D Epstein1, A Muñoz

  • 1Department of Biostatistics, Johns Hopkins School of Public Health, Baltimore, Maryland 21205, USA.

Statistics in Medicine
|June 15, 1996
PubMed
Summary

This study introduces a new statistical approach to analyze intermediate events, like secondary diagnoses, and terminal events, such as death, in disease progression. The method improves understanding of how these events influence survival outcomes in patient cohorts.

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

Natural history of human immunodeficiency virus type 1 viremia after seroconversion and proximal to AIDS in a large cohort of homosexual men. Multicenter AIDS Cohort Study.

The Journal of infectious diseases·2000
Same author

[Recurrent spontaneous carotid dissection].

Revista de neurologia·2000
Same author

Safety and efficacy of Omniscan (gadodiamide injection) at 0.1 mmol/kg for MRI in infants younger than 6 months of age: phase III open multicenter study.

Investigative radiology·2000
Same author

Percutaneous vertebroplasty: a special syringe for cement injection.

AJNR. American journal of neuroradiology·2000
Same author

OESCLIM: an advanced delivery system for HRT.

Maturitas·2000
Same author

Fenfluramine-induced increase in preproenkephalin mRNA levels in the striatum: interaction between the serotonergic, glutamatergic, and dopaminergic systems.

Synapse (New York, N.Y.)·2000

Area of Science:

  • Epidemiology
  • Biostatistics
  • Survival Analysis

Background:

  • Analyzing secondary diagnoses (intermediate events) and their impact on survival (terminal events) is crucial in diseases like acquired immune deficiency syndrome (AIDS).
  • Traditional methods often censor intermediate event times using terminal event times, which may not accurately reflect risk.
  • A more appropriate approach considers the terminal event as removing individuals from the risk set for the intermediate event.

Purpose of the Study:

  • To propose a novel statistical framework for analyzing the relationship between intermediate events and terminal events.
  • To develop a method that accurately models the competing risks and their impact on survival.
  • To provide tools for estimating key probabilities related to intermediate and terminal events.

Main Methods:

Related Experiment Videos

  • Developed a statistical approach using separate parametric models for the marginal distribution of survival time (terminal event) and the conditional distribution of time to the intermediate event.
  • Introduced a central quantity: the probability of the intermediate event occurring given the terminal event at a specific time.
  • Utilized Weibull distributions to model the relationship between events, allowing parameter control over the shape of the probability function.

Main Results:

  • The proposed model allows for the estimation of various probabilities, including the overall proportion of individuals experiencing the intermediate event.
  • It enables the characterization of the intermediate event's distribution among affected individuals.
  • The model facilitates the calculation of residual survival time after the intermediate event, given the terminal event.

Conclusions:

  • The new statistical approach provides a more accurate way to analyze the interplay between intermediate and terminal events in survival data.
  • This method enhances the understanding of disease progression and the factors influencing patient outcomes.
  • The application to HIV/AIDS and Kaposi's sarcoma (KS) demonstrates the model's utility in real-world epidemiological studies.