Clustering of trajectories with mixed effects classification model: Inference taking into account classification uncertainties.

SEM-CEM algorithms classification confidence interval longitudinal data mixed effects model

Journal

Statistics in medicine
ISSN: 1097-0258
Titre abrégé: Stat Med
Pays: England
ID NLM: 8215016

Informations de publication

Date de publication:
10 Nov 2023
Historique:
revised: 30 06 2023
received: 23 12 2022
accepted: 01 08 2023
pubmed: 15 8 2023
medline: 15 8 2023
entrez: 15 8 2023
Statut: ppublish

Résumé

Classifying patient biomarker trajectories into groups has become frequent in clinical research. Mixed effects classification models can be used to model the heterogeneity of longitudinal data. The estimated parameters of typical trajectories and the partition can be provided by the classification version of the expectation maximization algorithm, named CEM. However, the variance of the parameter estimates obtained underestimates the true variance because classification uncertainties are not taken into account. This article takes into account these uncertainties by using the stochastic EM algorithm (SEM), a stochastic version of the CEM algorithm, after convergence of the CEM algorithm. The simulations showed correct coverage probabilities of the 95% confidence intervals (close to 95% except for scenarios with high bias in typical trajectories). The method was applied on a trial, called low-cyclo, that compared the effects of low vs standard cyclosporine A doses on creatinine levels after cardiac transplantation. It identified groups of patients for whom low-dose cyclosporine may be relevant, but with high uncertainty on the dose-effect estimate.

Identifiants

pubmed: 37580957
doi: 10.1002/sim.9876
doi:

Types de publication

Journal Article

Langues

eng

Sous-ensembles de citation

IM

Pagination

4570-4581

Informations de copyright

© 2023 The Authors. Statistics in Medicine published by John Wiley & Sons Ltd.

Références

Nagin DS, Odgers C. Group-based trajectory modeling in clinical research. Annu Rev Clin Psychol. 2010;6:109-138.
Pickels A, Croudace T. Latent mixture models for multivariate and longitudinal outcomes. Methods Med Res. 2010;19(3):271-289. doi:10.1177/0962280209105016
Klich A, Ecochard R, Subtil F. Unequal intra-group variance in trajectory classification. Stat Med. 2018;37(28):4155-4166. doi:10.1002/sim.7921
Subtil F, Boussari O, Bastard M, Etard JF, Ecochard R, Génolini C. An alternative classification to mixture modeling for longitudinal counts or binary measures. Stat Methods Med Res. 2017;26:453-470. doi:10.1177/0962280214549040
Klich A, Ecochard R, Subtil F. Trajectory clustering using mixed classification models. Stat Med. 2021;40:1-15.
Celeux G, Goavert G. Comparison of the mixture and the classification maximum likelihood in cluster analysis. J Stat Comput Simul. 1993;47:127-146.
Celeux G, Goavert G. A classification EM algorithm for clustering and two stochastic versions. Comput Stat Data Anal. 1992;14:315-332.
Dempster AP, Laird N, Rubin DB. Maximum likelihood from incomplete data via the EM algorithm. J Roy Stat Soc B. 1977;39(1):1-38.
McLachlan GJ, Krishnan T. The EM Algorithm and Extensions. 2nd ed. New York: John Wiley & Sons; 2007.
Pinheiro JC, Bates DM. Mixed-Effects Models in S and S-PLUS. New York: Springer; 2000.
Rubin DB. Multiple Imputation for Nonresponse in Surveys. New York: John Wiley & Sons; 2004.
Celeux G, Diebolt J. The SEM algorithm: a probabilistic teacher algorithm derived from the EM algorithm for the mixture problem. Comput Stat Q. 1985;2:73-82.
Biernacki C, Celeux G, Goavert G. Choosing starting values for the EM algorithm for getting the highest likelihood in multivariate Gaussian mixture models. Comput Stat Data Anal. 2003;41:561-575.
Diallo TMO, Morin AJS, Lu HZ. Impact of misspecifications of the latent variance-covariance and residual matrices on the class enumeration accuracy of growth mixture models. Struct Equ Model. 2016;23(4):507-531.
Kim ES, Wang Y. Class enumeration and parameter recovery of growth mixture modeling and second-order growth mixture modeling in the presence of measurement noninvariance between latent classes. Front Psychol. 2017;8:1499.
Soullier N. Traitement de la non-réponse par imputation multiple; 2012. http://www.jms-insee.fr/2012/S06_3_ACTE_SOULLIER_JMS2012.PDF
Heggeseth BC, Jewell NP. The impact of covariance misspecification in multivariate Gaussian mixtures on estimation and inference: an application to longitudinal modeling. Stat Med. 2013;32:2790-2803.
Boissonat P, Gaillard S, Mercier C, et al. Impact of the early reduction of cyclosporine on renal function in heart transplant patients: a French randomised controlled trial. Trails. 2012;13(231):231. doi:10.1186/1745-6215-13-231
Maringwa JT, Geys H, Shkedy Z, et al. Application of semiparametric mixed models and simultaneaous confidence bands in a cardiovascular safety experiment with longitudinal data. J Biopharm Stat. 2008;18:1043-1062.

Auteurs

Charlotte Dugourd (C)

Service de Biostatistique, Hospices Civils de Lyon, Lyon, France.
Université de Lyon, Lyon, France.
Université Lyon 1, Villeurbanne, France.
CNRS, Laboratoire de Biométrie et Biologie Évolutive UMR 5558, Villeurbanne, France.

Amna Abichou-Klich (A)

Service de Biostatistique, Hospices Civils de Lyon, Lyon, France.
Université de Lyon, Lyon, France.
Université Lyon 1, Villeurbanne, France.
CNRS, Laboratoire de Biométrie et Biologie Évolutive UMR 5558, Villeurbanne, France.

René Ecochard (R)

Service de Biostatistique, Hospices Civils de Lyon, Lyon, France.
Université de Lyon, Lyon, France.
Université Lyon 1, Villeurbanne, France.
CNRS, Laboratoire de Biométrie et Biologie Évolutive UMR 5558, Villeurbanne, France.

Fabien Subtil (F)

Service de Biostatistique, Hospices Civils de Lyon, Lyon, France.
Université de Lyon, Lyon, France.
Université Lyon 1, Villeurbanne, France.
CNRS, Laboratoire de Biométrie et Biologie Évolutive UMR 5558, Villeurbanne, France.

Classifications MeSH