There are more than 7000 diseases with low incidence rates (rare diseases), of which 75% affect children, and 30% of rare disease patients die before they reach 5 years old[1]. In trials investigating novel treatments for rare diseases, it is often not possible to recruit sample sizes resulting from traditional power calculations. Regulatory guidance advises that alternative approaches to statistical analysis of such trials are suitable to improve the interpretability of trial results[2]. There are advantages to the Bayesian approach for communicating results of small trials, and in their design, utilising (suitably down-weighted) data from previous trials in the same disease, trials from related non-rare diseases, or expert knowledge. The prior used can be highly influential on the results of a Bayesian analysis; therefore it is critical that the historical data and expert knowledge are used carefully and judiciously.
This project will investigate expert knowledge, via comprehensive elicitation processes, for Bayesian design and analysis of trials in rare diseases. It will conduct a systematic review of approaches to Bayesian design of trials in rare diseases, and appropriate elicitation of expert knowledge within these approaches. The project will consider analysis of trials where data is available from previous trials or non-rare related populations or diseases (e.g. adults in a paediatric trial). Options for incorporating this information in the prior include the power prior and a Bayesian meta-analysis. In both cases, expert knowledge is required to specify parameters indicating the relevance of the data to the trial in the rare population. The project will consider approaches to incorporating data, and develop methods, building on the SHeffield ELicitation Framework (SHELF) and the IDEA protocol, to elicit parameters.
The project will consider specifying a prior when no previous data are available. In this case, the prior for the Bayesian design is formed from expert knowledge. The aim is to develop a robust, defensible and systematic elicitation method, for a set of trial designs in rare diseases, informed by the systematic review. A challenge will be in aggregation of the judgements of experts into a single prior representing the accumulated knowledge and uncertainty of the group. The project will consider approaches to assess the influence of the prior on the analysis in rare disease trials, such as via assessment of prior-data conflict. The methods developed will be applied retrospectively to published results in the MYPAN trial2, as well as to OACS, a current basket randomised controlled trial. The latter is a precision medicine trial looking at the efficacy of Obeticholic acid compared to placebo for treating cognitive dysfunction in different diseases. Several Bayesian approaches have been proposed, but require specification of priors for parameters that are difficult to interpret, resulting in challenging elicitation.
The project will hosted by Newcastle University (NU) and will also include supervision from the University of Cambridge (UoC).
· Biostatistics Research Group (NU): NW, Senior Statistician (Biostatistics) and JW, Professor of Biostatistics, have extensive expertise in the design, conduct and analysis of clinical trials from early to late phase.
· School of Mathematics, Statistics & Physics (NU): KW, Senior Lecturer in Statistics, specialises in methodological developments in Bayesian analysis and expert knowledge elicitation.
· MRC Biostatistics Unit (UoC): HZ, CRUK Research Fellow in Statistical Methodology, specialises in prior specification in Bayesian analysis, particularly for robust borrowing of information.
The student would also have the opportunity to receive training in public and patient involvement and present their research to the OACS PPI group.
HOW TO APPLY
You are applying for a PhD studentship from the MRC TMRP DTP. A list of potential projects and the application form is available online at:
http://www.methodologyhubs.mrc.ac.uk/about/tmrp-doctoral-training-partnership/
Please complete the form fully. Incomplete forms will not be considered. CVs will not be accepted for this scheme.
Please apply giving details for your first choice project. You can provide details of up to two other TMRP DTP projects you may be interested in at section B of the application form.
Before making an application, applicants should contact the project supervisor to find out more about the project and to discuss their interests in the research before 09 January 2023.
The deadline for applications is 4pm (GMT) 16 January 2023. Late applications will not be considered.
Completed application forms must be returned to: [Email Address Removed]
Informal enquiries may be made to Dr Nina Wilson - [Email Address Removed]
Continue with Facebook
