Methods for constructing longitudinal disease progression curves using sparse short- term individual data

Research output: ThesisDoctoral Thesis

62 Downloads (Pure)

Abstract

Different methodologies for constructing and quantifying the underlying long-term trajectories for Alzheimer's disease (AD) markers are developed and compared using real world and simulated data. A novel four-step approach utilising derivative information on the disease progression, standard non-linear mixed effects models, and a Bayesian approach are examined. The four-step approach and the Bayesian approach provide similar outcomes in terms of disease progression, but the latter deals with sparse data, commonly seen in AD progression, more effectively through the introduction of informative priors. The standard non-linear mixed effects model approach is shown to be inefficient for this purpose.
Original languageEnglish
QualificationDoctor of Philosophy
Awarding Institution
  • The University of Western Australia
Supervisors/Advisors
  • Turlach, Berwin, Supervisor
  • Murray, Kevin, Supervisor
  • Burnham, Samantha C., Supervisor, External person
Thesis sponsors
Award date4 Apr 2018
DOIs
Publication statusUnpublished - 2018

Fingerprint

Trajectories
Derivatives

Cite this

@phdthesis{e124a66788c34a5288c631d2e17939bf,
title = "Methods for constructing longitudinal disease progression curves using sparse short- term individual data",
abstract = "Different methodologies for constructing and quantifying the underlying long-term trajectories for Alzheimer's disease (AD) markers are developed and compared using real world and simulated data. A novel four-step approach utilising derivative information on the disease progression, standard non-linear mixed effects models, and a Bayesian approach are examined. The four-step approach and the Bayesian approach provide similar outcomes in terms of disease progression, but the latter deals with sparse data, commonly seen in AD progression, more effectively through the introduction of informative priors. The standard non-linear mixed effects model approach is shown to be inefficient for this purpose.",
keywords = "Alzheimer's disease, Sigmoidal curves, Longitudinal trajectories, Bayesian, Propensity scores, Five-paramater logistic function, Frequentist, ADNI and AIBL",
author = "Budgeon, {Charley Ann}",
year = "2018",
doi = "10.4225/23/5ae2793b66b60",
language = "English",
school = "The University of Western Australia",

}

TY - THES

T1 - Methods for constructing longitudinal disease progression curves using sparse short- term individual data

AU - Budgeon, Charley Ann

PY - 2018

Y1 - 2018

N2 - Different methodologies for constructing and quantifying the underlying long-term trajectories for Alzheimer's disease (AD) markers are developed and compared using real world and simulated data. A novel four-step approach utilising derivative information on the disease progression, standard non-linear mixed effects models, and a Bayesian approach are examined. The four-step approach and the Bayesian approach provide similar outcomes in terms of disease progression, but the latter deals with sparse data, commonly seen in AD progression, more effectively through the introduction of informative priors. The standard non-linear mixed effects model approach is shown to be inefficient for this purpose.

AB - Different methodologies for constructing and quantifying the underlying long-term trajectories for Alzheimer's disease (AD) markers are developed and compared using real world and simulated data. A novel four-step approach utilising derivative information on the disease progression, standard non-linear mixed effects models, and a Bayesian approach are examined. The four-step approach and the Bayesian approach provide similar outcomes in terms of disease progression, but the latter deals with sparse data, commonly seen in AD progression, more effectively through the introduction of informative priors. The standard non-linear mixed effects model approach is shown to be inefficient for this purpose.

KW - Alzheimer's disease

KW - Sigmoidal curves

KW - Longitudinal trajectories

KW - Bayesian

KW - Propensity scores

KW - Five-paramater logistic function

KW - Frequentist

KW - ADNI and AIBL

U2 - 10.4225/23/5ae2793b66b60

DO - 10.4225/23/5ae2793b66b60

M3 - Doctoral Thesis

ER -