Statistical modelling of cognitive decline to improve estimation, identifying risk factors and population benefits.
Lead Research Organisation:
MRC Biostatistics Unit
Department Name: UNLISTED
Abstract
Age related cognitive decline is a major public health concern. Most statistical methods used to measure it model the average change over time. However, scientists have reached a consensus that cognitive decline is too complex to be described as an overall mean, and rather person specific models are needed to fully understand it. I will investigate the effect of missing data due to death and ill health on estimates of cognitive decline, an investigation that will produce more realistic estimates of true cognitive decline and its potential causes. Core hypotheses of two large population based studies of older individuals will be investigated. These studies are the CC75C and the MRC CFA study.
The work proposed on the models of cost effectiveness of drugs for Alzheimer's disease will combine epidemiological data and clinical trials data within a sound framework that introduces realism into policy decisions. Models of individuals' trajectories combined with cost information and outcomes from clinical trials will provide a robust framework of the true cost of treatment for dementia.
The work proposed on the models of cost effectiveness of drugs for Alzheimer's disease will combine epidemiological data and clinical trials data within a sound framework that introduces realism into policy decisions. Models of individuals' trajectories combined with cost information and outcomes from clinical trials will provide a robust framework of the true cost of treatment for dementia.
Technical Summary
Background: Longitudinal studies provide the framework to investigate age related cognitive change. This modelling is complex due to factors such as the shape of the change, study design and missing data; factors that are often ignored. Preventing and slowing cognitive change is a target for drug interventions including those aimed at individuals with Alzheimer's disease. However, these investigations also suffer from similar modelling complexities. Investigating cost-effectiveness must consider these difficulties and also difficulties in modelling treatment effect at the individual and carer level.
Aims: To explore parametric random effects and growth mixture models that will allow for the identification of potential risk factors for cognitive decline, either for all participants or class specific groups including the modelling of missing data. To improve health economic models for Alzheimer's disease drugs by modelling the epidemiological setting as well as the clinical effectiveness.
Methodology:
" Random change point models will be fitted to investigate terminal decline with missing data using selection model approach (Bayesian analysis in WinBugs)
" Growth mixture models will investigate the analysis of class specific risk factors including the potential for test re-test effects (Using Mplus).
" Extension of investigation of the time matrix for analysis (such as time in study, age and time before death).
" Complex study design issues will be investigated via the incorporation of sampling weights into the models.
" Investigation of analysis modelling of missing data (including non ignorable data) such as inverse probability weighting, multiple imputation and pattern mixture models.
" The Cambridge City over 75 Cohort study, MRC Cognitive Function and Ageing Study and simulation studies will be used to develop the methodology and produce the applied papers.
" A literature review will initially be conducted to produce all necessary evidence regarding economic models for cholinesterase inhibitors.
" A Bayesian evidence synthesis will be undertaken to include the effect of Alzheimer's disease on mortality, the severity of the disease, the effect of transfer to institutional care as well as carers and the individuals' response to treatments. Initially the cholinesterase inhibitors will be modelled, but the framework will be flexible should new treatment strategies arise.
Opportunities. Proper models will describe potential risk factors for cognitive decline that could have population impact. Cost-effectiveness models using Bayesian synthesis for Alzheimer's disease will provide results of direct clinical usage.
Aims: To explore parametric random effects and growth mixture models that will allow for the identification of potential risk factors for cognitive decline, either for all participants or class specific groups including the modelling of missing data. To improve health economic models for Alzheimer's disease drugs by modelling the epidemiological setting as well as the clinical effectiveness.
Methodology:
" Random change point models will be fitted to investigate terminal decline with missing data using selection model approach (Bayesian analysis in WinBugs)
" Growth mixture models will investigate the analysis of class specific risk factors including the potential for test re-test effects (Using Mplus).
" Extension of investigation of the time matrix for analysis (such as time in study, age and time before death).
" Complex study design issues will be investigated via the incorporation of sampling weights into the models.
" Investigation of analysis modelling of missing data (including non ignorable data) such as inverse probability weighting, multiple imputation and pattern mixture models.
" The Cambridge City over 75 Cohort study, MRC Cognitive Function and Ageing Study and simulation studies will be used to develop the methodology and produce the applied papers.
" A literature review will initially be conducted to produce all necessary evidence regarding economic models for cholinesterase inhibitors.
" A Bayesian evidence synthesis will be undertaken to include the effect of Alzheimer's disease on mortality, the severity of the disease, the effect of transfer to institutional care as well as carers and the individuals' response to treatments. Initially the cholinesterase inhibitors will be modelled, but the framework will be flexible should new treatment strategies arise.
Opportunities. Proper models will describe potential risk factors for cognitive decline that could have population impact. Cost-effectiveness models using Bayesian synthesis for Alzheimer's disease will provide results of direct clinical usage.
Organisations
- MRC Biostatistics Unit (Lead Research Organisation)
- University College London (Collaboration)
- Albert Einstein College of Medicine (Collaboration)
- Stavanger University Hospital (Collaboration)
- LONDON METROPOLITAN UNIVERSITY (Collaboration)
- University of Victoria (Collaboration)
- UNIVERSITY OF CAMBRIDGE (Collaboration)
- UNIVERSITY OF EXETER (Collaboration)
People |
ORCID iD |
Graciela Terrera (Principal Investigator) |
Publications
Muniz-Terrera G
(2009)
Education and trajectories of cognitive decline over 9 years in very old people: methods and risk analysis.
in Age and ageing
Muniz Terrera G
(2008)
A comparison of parametric models for the investigation of the shape of cognitive change in the older population
in BMC Neurology
Muniz-Terrera G
(2011)
Are terminal decline and its potential indicators detectable in population studies of the oldest old?
in International journal of geriatric psychiatry
Matthews FE
(2010)
Who will be eligible? An investigation of the dementia population eligible for cholinesterase treatment following the change in NICE guidance.
in International journal of geriatric psychiatry
Terrera GM
(2010)
One size fits all? Why we need more sophisticated analytical methods in the explanation of trajectories of cognition in older age and their potential risk factors.
in International psychogeriatrics
Muniz Terrera G
(2011)
Random change point models: investigating cognitive decline in the presence of missing data
in Journal of Applied Statistics
Aarsland D
(2011)
Nonlinear decline of mini-mental state examination in Parkinson's disease.
in Movement disorders : official journal of the Movement Disorder Society
Piccinin AM
(2011)
An evaluation of analytical approaches for understanding change in cognition in the context of aging and health.
in The journals of gerontology. Series B, Psychological sciences and social sciences
Piccinin AM
(2011)
Terminal decline from within- and between-person perspectives, accounting for incident dementia.
in The journals of gerontology. Series B, Psychological sciences and social sciences
Description | University of Victoria, Canada/IALSA |
Amount | £1,000 (GBP) |
Organisation | Integrative Analysis of Longitudinal Studies on Aging (IALSA) |
Sector | Academic/University |
Country | Global |
Start | 06/2010 |
End | 07/2010 |
Description | University of Victoria, Canada/IALSA |
Amount | £1,000 (GBP) |
Organisation | Integrative Analysis of Longitudinal Studies on Aging (IALSA) |
Sector | Academic/University |
Country | Global |
Start | 05/2010 |
End | 06/2010 |
Title | Random change point methods |
Description | Identification of individual level change points |
Type Of Material | Data analysis technique |
Year Produced | 2010 |
Provided To Others? | Yes |
Impact | PMID: 21337356 |
URL | http://europepmc.org/abstract/MED/21337356 |
Title | Change points |
Description | I have developed statistical methods for estimation of change points representing the onset of accelerated decline. Previously, these were assumed to be common to all individuals, i have relaxed this assumption permitting the estimation of individual change points |
Type Of Material | Data analysis technique |
Year Produced | 2013 |
Provided To Others? | Yes |
Impact | The model developed is much more realistic than previous ones |
URL | http://www.homepages.ucl.ac.uk/~ucakadl/ |
Description | Analysis of associations between Vitamin D and cognitive decline |
Organisation | University of Exeter |
Department | School of Psychology |
Country | United Kingdom |
Sector | Academic/University |
PI Contribution | Developed research methods |
Collaborator Contribution | One paper published in the Archives of Internal Medicine (2010) |
Impact | PMID: 20625021 |
Start Year | 2008 |
Description | Analysis of longitudinal data for Parkinsons disease patients |
Organisation | Stavanger University Hospital |
Country | Norway |
Sector | Hospitals |
PI Contribution | Developed statistical methodology and contributted to manuscript |
Collaborator Contribution | One published paper "Non-linear cognitive decline in Parkinson disease" (Journal of Movement Disorders, 2010) |
Impact | PMID: 20960482 |
Start Year | 2010 |
Description | Association of neuropathology and cognition |
Organisation | University of Cambridge |
Department | Cambridge Institute of Public Health |
Country | United Kingdom |
Sector | Academic/University |
PI Contribution | Methodological developments. Co-supervision of MPhil thesis at the University of Cambridge |
Collaborator Contribution | One submitted/under review paper at the Lancet Neurology and one paper in preparation |
Impact | Publications submitted and under review: Neuropathological profile of different cognitive states before death in a non-demented population-based sample. Submitted to Lancet Neurology. July 2011 One paper in preparation |
Start Year | 2009 |
Description | CC75C |
Organisation | University of Cambridge |
Department | Cambridge Institute of Public Health |
Country | United Kingdom |
Sector | Academic/University |
PI Contribution | Data analysis |
Collaborator Contribution | Data provision, joint papers |
Impact | PMID: PMID: 18485192; PMID: 19252209; 21480375 Publications submitted and under review: - Investigating terminal decline: results from a UK population-based study of ageing. Submitted to Psychology and Ageing- September 2011 - Education associated with a delayed onset of terminal decline. Submitted to Age and Ageing. September 2011 |
Description | Change point |
Organisation | University of Cambridge |
Department | MRC Biostatistics Unit |
Country | United Kingdom |
Sector | Academic/University |
PI Contribution | Research and data analysis |
Collaborator Contribution | Research collaboration |
Impact | DOI: 10.1080/02664760903563668 Two papers in preparation and one presentation held at the ISCB 2011 (August) |
Start Year | 2010 |
Description | Collaboration on longitudinal models of blood pressure |
Organisation | University College London |
Department | MRC Unit for Lifelong Health and Ageing |
Country | United Kingdom |
Sector | Academic/University |
PI Contribution | Methodological improvement of blood pressure models |
Collaborator Contribution | Two papers submitted/under revision and three in preparation |
Impact | Publications submitted and under review: - Analysing cognitive test data: distributions and non-parametric random effects. Submitted to Statistical Methods in Medical Research. August 2011 - A latent-class semi-parametric change point model for cognitive ability in older age. Submitted to Lifetime and Computational data Analysis. October 2011. Three papers in preparation |
Start Year | 2008 |
Description | Collaboration on longitudinal models of cognition |
Organisation | London Metropolitan University |
Department | Department of Mathematics and Statistics |
Country | United Kingdom |
Sector | Academic/University |
PI Contribution | Developed methodology research |
Collaborator Contribution | One published paper ("Proceeding of the 25th workshop of the International Society of statistical models"), one submitted/under review and one in preparation. |
Impact | Publications: - Modelling random effects using GAMLSS. G. Muniz, A. van den Hout, M. Stasinopoulos, and R. Rigby. Proceedings of the International Workshop of Statistical Modelling, (2010) - A latent-class semi-parametric change point model for cognitive ability in older age. A. van den Hout, G. Muniz, F. Matthews. Proceedings of the International Workshop of Statistical Modelling, (2011). |
Start Year | 2009 |
Description | Delirium |
Organisation | University of Cambridge |
Department | Cambridge Institute of Public Health |
Country | United Kingdom |
Sector | Academic/University |
PI Contribution | Data analysis |
Collaborator Contribution | Project proposal |
Impact | Paper submited and under revision: Delirium increases risk of dementia but not through Alzheimer-type, infarcts or Lewy body pathology: a population-based cohort study. Submitted to BMJ. October 2011 |
Start Year | 2010 |
Description | Improvement of statistical models of cognitive data |
Organisation | University of Cambridge |
Department | MRC Biostatistics Unit |
Country | United Kingdom |
Sector | Academic/University |
PI Contribution | Developed research methods |
Collaborator Contribution | One accepted paper "Smooth random change points", to appear in the Statistics in Medicine (2010) |
Impact | PMID: 21337356 |
Start Year | 2008 |
Description | Investigation of cognitive change in a American network of longitudinal studies of ageing |
Organisation | University of Victoria |
Country | Australia |
Sector | Academic/University |
PI Contribution | Statistical input |
Collaborator Contribution | Discussed models and written 2 publications (submitted and under review) (2009) Discussed models and written 3 publications (submitted and under review) and 1 publication under preparation (2010) Collaboration with a post doc (Annie Robbittaille) on models for the investigation of moderating effects in cognitive outcomes. (2010-2011) |
Impact | PMID: 21743051; PMID: 21389088 Publications submitted and under review: - Investigation of the association between change in memory scores and death. Submitted to Geropsych. July 2011. - Bivariate longitudinal modeling of cognitive aging: Relationship between processing speed and visual spatial ability. Submitted to Geropsych. July 2011. |
Start Year | 2008 |
Description | Investigation on effect of study design on longitudinal model parameters. |
Organisation | Albert Einstein College of Medicine |
Country | United States |
Sector | Academic/University |
PI Contribution | data analysis |
Collaborator Contribution | provided the data for the analysis |
Impact | Papers in preparation |
Start Year | 2010 |
Description | Cambridge Science Festival |
Form Of Engagement Activity | Participation in an activity, workshop or similar |
Part Of Official Scheme? | Yes |
Geographic Reach | Regional |
Primary Audience | Public/other audiences |
Results and Impact | Participated in and helped managing the Unit's display for Cambridge Science Festival (2009) Assisted in attending the public (2011) Raised profile for the work of the Unit in the local schools community |
Year(s) Of Engagement Activity | 2007,2008,2009,2011 |
Description | IPH Open Day |
Form Of Engagement Activity | A talk or presentation |
Part Of Official Scheme? | No |
Geographic Reach | Local |
Primary Audience | Professional Practitioners |
Results and Impact | 100 people attended the presentation on cognitive decline in old age Health professionals asked me to assist them in fitting similar models |
Year(s) Of Engagement Activity | 2009,2010 |
Description | MPlus UK users meeting |
Form Of Engagement Activity | A talk or presentation |
Part Of Official Scheme? | No |
Geographic Reach | Local |
Primary Audience | Professional Practitioners |
Results and Impact | 70 people attended the presentation on terminal decline in cognitive outcomes Invitation to speak at the RSS (2011) |
Year(s) Of Engagement Activity | 2009,2011 |