Joint Latent Class Models: A Tutorial on Practical Applications in Clinical Research
Statistics in Medicine · 2025
DOI: 10.1002/sim.70047 ↗At a glance
Journal article in Statistics in Medicine, 2025. Written by Maéva Kyheng and 2 co-authors. Institution: ULR 2694 - METRICS - Évaluation des Technologies de Santé et des Pratiques Médicales, CHU Lille, Université de Lille, Lille, France. Major MEDLINE topics: Latent Class Analysis, Models, Statistical, Biomedical Research. Cited 6 times so far (Crossref); 28 references. The full text is freely available (open access, CC BY-NC-ND 4.0).
Abstract (original language)
Joint latent class model is a statistical approach allowing to simultaneously account for two outcomes related to disease progression: A longitudinal measure (for example a biomarker) and time‐to‐event, in the context of a heterogeneous population. Within this approach, the linear mixed model, describing the longitudinal measure, is connected to the survival model, describing the risk of event occurrence, via a model for latent classes, describing an unobserved population heterogeneity; thus, the behavior of the two outcomes is assumed to be specific to each latent class. The theoretical properties of the model are established and the model is implemented in software. However, its complexity makes it difficult to manipulate by clinicians. In this paper, we propose a detailed tutorial for clinicians and applied statisticians on how to specify the model in R software in order to respond to concrete clinical questions, how to explore, manipulate, interpret the provided results. The tutorial is based on a real clinical dataset; for each clinical question the mathematical model specification and the R script for implementation are provided, and the estimation results and goodness‐of‐fit measures are detailed and interpreted.
Subjects
MeSH terms (MEDLINE)
Author keywords
Authors and institutions
- ULR 2694 - METRICS - Évaluation des Technologies de Santé et des Pratiques Médicales, CHU Lille, Université de Lille, Lille, France.
ORCID profiles: Maéva Kyheng
Cite
APA
Kyheng, M., Babykina, G., & Duhamel, A. (2025). Joint Latent Class Models: A Tutorial on Practical Applications in Clinical Research. Statistics in Medicine. https://doi.org/10.1002/sim.70047
Vancouver
Kyheng M, Babykina G, Duhamel A. Joint Latent Class Models: A Tutorial on Practical Applications in Clinical Research. Statistics in Medicine. 2025. doi:10.1002/sim.70047
BibTeX
@article{Kyheng2025,
author = {Kyheng, Maéva and Babykina, Génia and Duhamel, Alain},
title = {Joint Latent Class Models: A Tutorial on Practical Applications in Clinical Research},
journal = {Statistics in Medicine},
year = {2025},
doi = {10.1002/sim.70047}
}
EUVIMED