Bayesian inference for an illness-death model for stroke with cognition as a latent time-dependent risk factor

Ardo van den Hout, Jean-Paul Fox, Rinke H. Klein Entink

Research output: Contribution to journalArticleAcademicpeer-review

8 Citations (Scopus)
28 Downloads (Pure)

Abstract

Longitudinal data can be used to estimate the transition intensities between healthy and unhealthy states prior to death. An illness-death model for history of stroke is presented, where time-dependent transition intensities are regressed on a latent variable representing cognitive function. The change of this function over time is described by a linear growth model with random effects. Occasion-specific cognitive function is measured by an item response model for longitudinal scores on the Mini-Mental State Examination, a questionnaire used to screen for cognitive impairment. The illness-death model will be used to identify and to explore the relationship between occasion-specific cognitive function and stroke. Combining a multi-state model with the latent growth model defines a joint model which extends current statistical inference regarding disease progression and cognitive function. Markov chain Monte Carlo methods are used for Bayesian inference. Data stem from the Medical Research Council Cognitive Function and Ageing Study in the UK (1991–2005).
Original languageEnglish
Pages (from-to)769-787
JournalStatistical methods in medical research
Volume24
Issue number6
DOIs
Publication statusPublished - 2015

Fingerprint

Cognition
Bayesian inference
Risk Factors
Stroke
Growth Model
Monte Carlo Method
Markov Chains
Model
Multi-state Model
Growth
Joint Model
Markov Chain Monte Carlo Methods
Latent Variables
Longitudinal Data
Disease Progression
Biomedical Research
Linear Models
Random Effects
Statistical Inference
Progression

Keywords

  • Item-response theory
  • Markov chain Monte Carlo
  • mini-mental state examination
  • Multi-state model
  • Random effects

Cite this

@article{99c0fe2e7ac34bd8badafcf110850c02,
title = "Bayesian inference for an illness-death model for stroke with cognition as a latent time-dependent risk factor",
abstract = "Longitudinal data can be used to estimate the transition intensities between healthy and unhealthy states prior to death. An illness-death model for history of stroke is presented, where time-dependent transition intensities are regressed on a latent variable representing cognitive function. The change of this function over time is described by a linear growth model with random effects. Occasion-specific cognitive function is measured by an item response model for longitudinal scores on the Mini-Mental State Examination, a questionnaire used to screen for cognitive impairment. The illness-death model will be used to identify and to explore the relationship between occasion-specific cognitive function and stroke. Combining a multi-state model with the latent growth model defines a joint model which extends current statistical inference regarding disease progression and cognitive function. Markov chain Monte Carlo methods are used for Bayesian inference. Data stem from the Medical Research Council Cognitive Function and Ageing Study in the UK (1991–2005).",
keywords = "Item-response theory, Markov chain Monte Carlo, mini-mental state examination, Multi-state model, Random effects",
author = "{van den Hout}, Ardo and Jean-Paul Fox and {Klein Entink}, {Rinke H.}",
year = "2015",
doi = "10.1177/0962280211426359",
language = "English",
volume = "24",
pages = "769--787",
journal = "Statistical methods in medical research",
issn = "0962-2802",
publisher = "SAGE Publications",
number = "6",

}

Bayesian inference for an illness-death model for stroke with cognition as a latent time-dependent risk factor. / van den Hout, Ardo; Fox, Jean-Paul; Klein Entink, Rinke H.

In: Statistical methods in medical research, Vol. 24, No. 6, 2015, p. 769-787.

Research output: Contribution to journalArticleAcademicpeer-review

TY - JOUR

T1 - Bayesian inference for an illness-death model for stroke with cognition as a latent time-dependent risk factor

AU - van den Hout, Ardo

AU - Fox, Jean-Paul

AU - Klein Entink, Rinke H.

PY - 2015

Y1 - 2015

N2 - Longitudinal data can be used to estimate the transition intensities between healthy and unhealthy states prior to death. An illness-death model for history of stroke is presented, where time-dependent transition intensities are regressed on a latent variable representing cognitive function. The change of this function over time is described by a linear growth model with random effects. Occasion-specific cognitive function is measured by an item response model for longitudinal scores on the Mini-Mental State Examination, a questionnaire used to screen for cognitive impairment. The illness-death model will be used to identify and to explore the relationship between occasion-specific cognitive function and stroke. Combining a multi-state model with the latent growth model defines a joint model which extends current statistical inference regarding disease progression and cognitive function. Markov chain Monte Carlo methods are used for Bayesian inference. Data stem from the Medical Research Council Cognitive Function and Ageing Study in the UK (1991–2005).

AB - Longitudinal data can be used to estimate the transition intensities between healthy and unhealthy states prior to death. An illness-death model for history of stroke is presented, where time-dependent transition intensities are regressed on a latent variable representing cognitive function. The change of this function over time is described by a linear growth model with random effects. Occasion-specific cognitive function is measured by an item response model for longitudinal scores on the Mini-Mental State Examination, a questionnaire used to screen for cognitive impairment. The illness-death model will be used to identify and to explore the relationship between occasion-specific cognitive function and stroke. Combining a multi-state model with the latent growth model defines a joint model which extends current statistical inference regarding disease progression and cognitive function. Markov chain Monte Carlo methods are used for Bayesian inference. Data stem from the Medical Research Council Cognitive Function and Ageing Study in the UK (1991–2005).

KW - Item-response theory

KW - Markov chain Monte Carlo

KW - mini-mental state examination

KW - Multi-state model

KW - Random effects

U2 - 10.1177/0962280211426359

DO - 10.1177/0962280211426359

M3 - Article

VL - 24

SP - 769

EP - 787

JO - Statistical methods in medical research

JF - Statistical methods in medical research

SN - 0962-2802

IS - 6

ER -