Statistical Methodology for Longitudinal Studies in Clinical Research

Lead Research Organisation: University of Liverpool
Department Name: Medical Statistics and Health Evaluation

Abstract

Progression of a disease or condition as it develops over time can be monitored in many ways, which can
be collectively referred to as biomarkers. Some of these are very familiar, such as blood pressure and cholesterol levels. Others are used to convert the results of tests and examinations into numerical scores, such as the stage of a cancer or a performance index of activity. Still others are the results of psychological questionnaires used to describe intangibles like mental health or quality of life.

This proposal aims to develop statistical methods to investigate how the patterns over time in biomarkers relate to prognosis for the patient and in particular the timing of clinically significant events. For example, we all know that a high cholesterol level leads to an increased risk of a heart attack, but is the risk for someone whose cholesterol level has risen gradually over several years the same as for someone whose cholesterol has increased to the same level in a much shorter time? And what about someone whose cholesterol has stayed constant at the same high level for many years?

To answer questions like this we need to develop statistical models to describe the complex relationship between the biomarker and the clinical events. The models need to take into account errors in the measurement of the biomarker and the variability observed between people, so as to be able to detect genuine patterns in the type of data observed in practice. The models will be used to exploit biomarker data in providing accurate prognostic forecasts of clinical events, enabling identification of individuals in whom early intervention may be warranted to prevent adverse events. They will help the patient and their doctor to make the best treatment choice. The models can allow researchers to assess indirectly, but very quickly, the effect of a new drug or therapy, by examining its effect on biomarker patterns rather than waiting for the clinical event to occur.

The proposal is built around three important medical areas: epilepsy treatment, cardio-thoracic surgery and renal transplantation. The multidisciplinary research team includes clinical specialists in each medical area as well as experienced statisticians from Liverpool and Lancaster Universities. Although there are currently no plans for direct communication to the public of the high level research methodology to be developed, specific medical results will be disseminated by collaborators through relevant Patient Association groups.

Technical Summary

This proposal is for the development and application of
statistical methodology for longitudinal data which simultaneously include two components: event times and repeated measurements. Statistical methods for the proper treatment of data of this form are currently both under-developed and under-used in clinical research. An important aim of the programme is to develop user-friendly software to allow easy implementation of the methods to be developed, together with a series of workshops to provide training in the
methodology and software.

The overall research programme will be built around specific collaborative research projects in three different medical areas: epilepsy treatment; cardio-thoracic surgery; and renal transplantation. As well as providing a range of clinical problems of interest in their own right, the three areas
together provide a range of study types on which to validate the methodology developed under the proposal.

Publications

10 25 50

publication icon
Diggle P (2007) Analysis of longitudinal data with drop-out: objectives, assumptions and a proposal in Journal of the Royal Statistical Society: Series C (Applied Statistics)

publication icon
Friede T (2006) A note on testing for intervention effects on binary responses. in Methods of information in medicine

publication icon
Henderson Robin (2011) OPTIMAL DYNAMIC TREATMENT METHODS in REVSTAT-STATISTICAL JOURNAL

publication icon
Hoefield RA (2011) The use of eGFR and ACR to predict decline in renal function in people with diabetes. in Nephrology, dialysis, transplantation : official publication of the European Dialysis and Transplant Association - European Renal Association

publication icon
Johnson SL (2011) Depressive and manic symptoms are not opposite poles in bipolar disorder. in Acta psychiatrica Scandinavica

 
Description MRC Methodology Research Panel
Amount £42,004 (GBP)
Organisation Medical Research Council (MRC) 
Sector Academic/University
Country United Kingdom
Start 08/2015 
End 08/2018
 
Description Renehan A and Williamson PR (Joint PIs). Core outcome set for anal cancer studies
Amount £229,405 (GBP)
Funding ID PB-PG-1013-32064 
Organisation National Institute for Health Research 
Department Research for Patient Benefit
Sector Public
Country United Kingdom
Start 10/2015 
End 09/2017
 
Title New statistical methods 
Description Joint modelling methods. 
Type Of Material Improvements to research infrastructure 
Year Produced 2007 
Provided To Others? Yes  
Impact Contacted by researchers requesting software to implement methods. 
 
Description Longitudinal studies in renal medicine 
Organisation Salford Royal NHS Foundation Trust
Country United Kingdom 
Sector Public 
PI Contribution Development and application of statistical methods for longitudinal studies of renal function, with an initial focus on real-time prediction of renal failure from serial blood chemistry data
Collaborator Contribution Substantive knowledge of and research expertise in renal medicine, and provision of data
Impact Hoefield, R.A., Kalra, P.A., Baker, P.G., Sousa, I., Diggle, P.J., Gibson, J.M., O'Donoghue, D.J., Middleton, R.J. and New, J.P. (2011). The use of eGFR and ACR to predict decline in renal function in people with diabetes. Nephrology Dialysis Transplantation, 26, 887-892
Start Year 2010
 
Title Statistical software 
Description Shareware software to implement methods developed. 
Type Support Tool - For Fundamental Research
Current Stage Of Development Small-scale adoption
Year Development Stage Completed 2009
Development Status Under active development/distribution
Impact Request for access from researchers. 
 
Description Invited talk, France 2011 
Form Of Engagement Activity A talk or presentation
Part Of Official Scheme? No
Geographic Reach International
Primary Audience Public/other audiences
Results and Impact Around 200 participants attended the meeting from all over the world. The talk was followed by a lively discussion about methodology and related software.

Several students/researchers requested information on software and also requested advise on their projects by e-mail afterwards.
Year(s) Of Engagement Activity 2011
 
Description Invited talk, London 2011 
Form Of Engagement Activity A talk or presentation
Part Of Official Scheme? No
Geographic Reach International
Primary Audience Public/other audiences
Results and Impact 75 participants attended the meeting from a range of institutes in UK and Europe that showed the potential of using novel methodology in clinical research. The talk was followed by a lively discussion.

More information on publications and software was requested (at the discussion, and by e-mail later) by several participants for their research.
Year(s) Of Engagement Activity 2011
 
Description JoineR Workshop 2013, Newcastle RKD 
Form Of Engagement Activity Participation in an activity, workshop or similar
Part Of Official Scheme? No
Type Of Presentation Workshop Facilitator
Geographic Reach International
Primary Audience Other academic audiences (collaborators, peers etc.)
Results and Impact 13 participants. The workshop was interactive throughout where participants discuss applying the methods in their clinical data, and had hands-on experience in using the software JoineR.

The workshop has received very positive feedback. All participants considered use of joint modelling in their future research and improved their understanding of the relevance of joint modelling ideas to substantive clinical research.
Year(s) Of Engagement Activity 2013
 
Description JoineR workshop 2012 
Form Of Engagement Activity Participation in an activity, workshop or similar
Part Of Official Scheme? No
Type Of Presentation Workshop Facilitator
Geographic Reach National
Primary Audience Public/other audiences
Results and Impact A one-day training workshop was held on 13th September 2012 in Liverpool and
discussed the novel statistical method through two expository lectures and gave practical instruction in the use of the software.

Very positive feedback received.
Year(s) Of Engagement Activity 2012
 
Description Joint modelling talk, Budapest 2013 RKD 
Form Of Engagement Activity A talk or presentation
Part Of Official Scheme? No
Type Of Presentation Keynote/Invited Speaker
Geographic Reach International
Primary Audience Other academic audiences (collaborators, peers etc.)
Results and Impact 30-40 participants. The talk was followed by a lively discussion where participants discussed applying the methods in their clinical and biolomedical research.

Requests for the software JoineR.
Year(s) Of Engagement Activity 2013
 
Description Joint modelling talk, London 2013 RKD 
Form Of Engagement Activity A talk or presentation
Part Of Official Scheme? No
Type Of Presentation Keynote/Invited Speaker
Geographic Reach National
Primary Audience Other academic audiences (collaborators, peers etc.)
Results and Impact 50-60 participants. The talk was followed by a lively discussion where participants discussed applying the methods in their clinical and biolomedical research.

Several participants approached to discuss their projects involving longitudinal data and requested the software JoineR.
Year(s) Of Engagement Activity 2013
 
Description Talk, Birmimgham 2013 RKD 
Form Of Engagement Activity A talk or presentation
Part Of Official Scheme? No
Geographic Reach International
Primary Audience Other academic audiences (collaborators, peers etc.)
Results and Impact 150 participants. The talk was followed by a lively discussion.

Several participants approached to discuss their projects involving longitudinal biomarker data.
Year(s) Of Engagement Activity 2013