Modelling growth and decline in lung function in Duchenne's muscular dystrophy with an augmented linear mixed effects model

Marc A. Scott, Robert G. Norman, Kenneth I. Berger

Research output: Contribution to journalArticle

Abstract

Longitudinal modelling of lung function in Duchenne's muscular dystrophy is complicated by a mixture of both growth and decline in lung function within each subject, an unknown point of separation between these phases and significant heterogeneity between individual trajectories. Linear mixed effects models can be used, assuming a single changepoint for all cases; however, this assumption may be incorrect. The paper describes an extension of linear mixed effects modelling in which random changepoints are integrated into the model as parameters and estimated by using a stochastic EM algorithm. We find that use of this 'mixture modelling' approach improves the fit significantly.

Original languageEnglish (US)
Pages (from-to)507-521
Number of pages15
JournalJournal of the Royal Statistical Society. Series C: Applied Statistics
Volume53
Issue number3
DOIs
StatePublished - 2004

Fingerprint

Linear Mixed Effects Model
Change Point
Lung
Mixed Effects
Mixture Modeling
Stochastic Algorithms
EM Algorithm
Modeling
Trajectory
Unknown
Model
Change point

Keywords

  • Changepoint models
  • Duchenne's muscular dystrophy
  • Longitudinal data
  • Lung function
  • Mixed effects models
  • Mixture models

ASJC Scopus subject areas

  • Mathematics(all)
  • Statistics and Probability

Cite this

@article{9d0d4096c4bb40e186fa2f98e6cac7a1,
title = "Modelling growth and decline in lung function in Duchenne's muscular dystrophy with an augmented linear mixed effects model",
abstract = "Longitudinal modelling of lung function in Duchenne's muscular dystrophy is complicated by a mixture of both growth and decline in lung function within each subject, an unknown point of separation between these phases and significant heterogeneity between individual trajectories. Linear mixed effects models can be used, assuming a single changepoint for all cases; however, this assumption may be incorrect. The paper describes an extension of linear mixed effects modelling in which random changepoints are integrated into the model as parameters and estimated by using a stochastic EM algorithm. We find that use of this 'mixture modelling' approach improves the fit significantly.",
keywords = "Changepoint models, Duchenne's muscular dystrophy, Longitudinal data, Lung function, Mixed effects models, Mixture models",
author = "Scott, {Marc A.} and Norman, {Robert G.} and Berger, {Kenneth I.}",
year = "2004",
doi = "10.1111/j.1467-9876.2004.05278.x",
language = "English (US)",
volume = "53",
pages = "507--521",
journal = "Journal of the Royal Statistical Society. Series C: Applied Statistics",
issn = "0035-9254",
publisher = "Wiley-Blackwell",
number = "3",

}

TY - JOUR

T1 - Modelling growth and decline in lung function in Duchenne's muscular dystrophy with an augmented linear mixed effects model

AU - Scott, Marc A.

AU - Norman, Robert G.

AU - Berger, Kenneth I.

PY - 2004

Y1 - 2004

N2 - Longitudinal modelling of lung function in Duchenne's muscular dystrophy is complicated by a mixture of both growth and decline in lung function within each subject, an unknown point of separation between these phases and significant heterogeneity between individual trajectories. Linear mixed effects models can be used, assuming a single changepoint for all cases; however, this assumption may be incorrect. The paper describes an extension of linear mixed effects modelling in which random changepoints are integrated into the model as parameters and estimated by using a stochastic EM algorithm. We find that use of this 'mixture modelling' approach improves the fit significantly.

AB - Longitudinal modelling of lung function in Duchenne's muscular dystrophy is complicated by a mixture of both growth and decline in lung function within each subject, an unknown point of separation between these phases and significant heterogeneity between individual trajectories. Linear mixed effects models can be used, assuming a single changepoint for all cases; however, this assumption may be incorrect. The paper describes an extension of linear mixed effects modelling in which random changepoints are integrated into the model as parameters and estimated by using a stochastic EM algorithm. We find that use of this 'mixture modelling' approach improves the fit significantly.

KW - Changepoint models

KW - Duchenne's muscular dystrophy

KW - Longitudinal data

KW - Lung function

KW - Mixed effects models

KW - Mixture models

UR - http://www.scopus.com/inward/record.url?scp=3042776903&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=3042776903&partnerID=8YFLogxK

U2 - 10.1111/j.1467-9876.2004.05278.x

DO - 10.1111/j.1467-9876.2004.05278.x

M3 - Article

AN - SCOPUS:3042776903

VL - 53

SP - 507

EP - 521

JO - Journal of the Royal Statistical Society. Series C: Applied Statistics

JF - Journal of the Royal Statistical Society. Series C: Applied Statistics

SN - 0035-9254

IS - 3

ER -