Joint models for the longitudinal analysis of measurement scales in the presence of informative dropout
Methods. 2022-07-01; 203: 142-151
DOI: 10.1016/j.ymeth.2022.03.003
Lire sur PubMed
Saulnier T(1), Philipps V(2), Meissner WG(3), Rascol O(4), Pavy-Le Traon A(5), Foubert-Samier A(6), Proust-Lima C(2).
Author information:
(1)Univ. Bordeaux, Inserm, Bordeaux Population Health Research Center, UMR1219,
F-33000 Bordeaux, France. Electronic address: .
(2)Univ. Bordeaux, Inserm, Bordeaux Population Health Research Center, UMR1219,
F-33000 Bordeaux, France.
(3)CHU Bordeaux, Service de Neurologie des Maladies Neurodégénératives, IMNc,
CRMR AMS, F-33000 Bordeaux, France; Univ. Bordeaux, CNRS, IMN, UMR 5293, F-33000
Bordeaux, France.
(4)French Reference Centre for MSA, University Hospital Toulouse, F-31000
Toulouse, France; Inserm, Toulouse University and CHU Toulouse, Clinical
Investigation Center CIC 1436, NS-Park/F-CRIN Network, NeuroToul COEN Center,
and Departments of Neurosciences and Clinical Pharmacology, F-31000 Toulouse,
France.
(5)French Reference Centre for MSA, University Hospital Toulouse, F-31000
Toulouse, France; Institut des Maladies Métaboliques et Cardiovasculaires,
Inserm U1297, univ. Toulouse, F-31000 Toulouse, France.
(6)Univ. Bordeaux, Inserm, Bordeaux Population Health Research Center, UMR1219,
F-33000 Bordeaux, France; CHU Bordeaux, Service de Neurologie des Maladies
Neurodégénératives, IMNc, CRMR AMS, F-33000 Bordeaux, France; Univ. Bordeaux,
CNRS, IMN, UMR 5293, F-33000 Bordeaux, France.
In health cohort studies, repeated measures of markers are often used to
describe the natural history of a disease. Joint models allow to study their
evolution by taking into account the possible informative dropout usually due to
clinical events. However, joint modeling developments mostly focused on
continuous Gaussian markers while, in an increasing number of studies, the
actual quantity of interest is non-directly measurable; it constitutes a latent
variable evaluated by a set of observed indicators from questionnaires or
measurement scales. Classical examples include anxiety, fatigue, cognition. In
this work, we explain how joint models can be extended to the framework of a
latent quantity measured over time by indicators of different nature (e.g.
continuous, binary, ordinal). The longitudinal submodel describes the evolution
over time of the quantity of interest defined as a latent process in a
structural mixed model, and links the latent process to each observation of the
indicators through appropriate measurement models. Simultaneously, the risk of
multi-cause event is modelled via a proportional cause-specific hazard model
that includes a function of the mixed model elements as linear predictor to take
into account the association between the latent process and the risk of event.
Estimation, carried out in the maximum likelihood framework and implemented in
the R-package JLPM, has been validated by simulations. The methodology is
illustrated in the French cohort on Multiple-System Atrophy (MSA), a rare and
fatal neurodegenerative disease, with the study of dysphagia progression over
time stopped by the occurrence of death.
Copyright © 2022 Elsevier Inc. All rights reserved.
DOI: 10.1016/j.ymeth.2022.03.003
PMID: 35283328 [Indexed for MEDLINE]