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

Bayesian multivariate growth curve latent class models for mixed outcomes.

Benjamin E Leiby1, Thomas R Ten Have, Kevin G Lynch

  • 1Division of Biostatistics, Thomas Jefferson University, 1015 Chestnut St. Suite M100, Philadelphia, PA 19107, U.S.A.

Statistics in Medicine
|September 11, 2012
PubMed
Summary

This study introduces novel multivariate growth curve latent class models to identify patient subgroups based on multiple symptoms over time. The method successfully identified patient subgroups in a clinical trial for interstitial cystitis, aiding treatment assessment.

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

Three-arm randomised controlled trial of text message reminders and financial incentives to improve antidepressant adherence among adults in primary care with depression: study protocol.

BMJ open·2026
Same author

Adjunctive Psychosocial Interventions and Opioid Abstinence Among Patients Receiving Buprenorphine: A Randomized Clinical Trial.

JAMA network open·2026
Same author

Adiposity and inflammation mediate altered metabolic profile in individuals with opioid use disorder.

Journal of psychiatric research·2026
Same author

Adiposity and inflammation mediate altered metabolic profiles in individuals with opioid use disorder.

medRxiv : the preprint server for health sciences·2026
Same author

Response of reticulocyte and red blood cell indices to single-dose intravenous iron in pregnant women with moderate iron deficiency anemia: secondary analysis of the RAPIDIRON trial.

The journal of maternal-fetal & neonatal medicine : the official journal of the European Association of Perinatal Medicine, the Federation of Asia and Oceania Perinatal Societies, the International Society of Perinatal Obstetricians·2026
Same author

RAMP-UP: Pharmacist-Led Methadone Titration for Hospitalized Patients With Opioid Use Disorder.

Substance use & addiction journal·2026

Area of Science:

  • Biostatistics
  • Clinical Trial Analysis
  • Longitudinal Data Analysis

Background:

  • Clinical studies often involve multifaceted diseases requiring multiple outcomes for accurate assessment.
  • Analyzing multivariate outcomes is challenging for determining disease improvement, especially in symptom-defined syndromes.
  • Identifying distinct patient subgroups is crucial for personalized treatment and prognosis.

Purpose of the Study:

  • To propose multivariate growth curve latent class models for grouping subjects based on longitudinal symptom data.
  • To define latent classes by distinctive longitudinal profiles of a latent variable summarizing multivariate outcomes.
  • To develop a flexible Bayesian hierarchical model accommodating various outcome types (continuous, binary, ordinal, count).

Main Methods:

Keywords:
latent classlatent variablelongitudinalrandomized trials

Related Experiment Videos

  • Development of multivariate growth curve latent class models.
  • Utilizing a Bayesian hierarchical framework for model estimation.
  • Validation through simulation studies.
  • Application to a randomized clinical trial for interstitial cystitis treatment.

Main Results:

  • The proposed models effectively group subjects based on multiple, repeatedly measured symptoms.
  • Distinct longitudinal profiles of a latent variable were identified for different patient subgroups.
  • The model successfully identified a subgroup of interstitial cystitis patients who responded effectively to Bacillus Calmette-Guerin treatment.

Conclusions:

  • Multivariate growth curve latent class models provide a robust framework for analyzing complex longitudinal data in clinical studies.
  • These models facilitate the identification of patient subgroups with distinct disease trajectories.
  • The approach aids in understanding treatment efficacy within specific patient populations, as demonstrated in the interstitial cystitis trial.