Extensions of the fragility index to non-binary data

Background to the project: The fragility index [Walsh 2014] calculates how many events would be required to change a statistically significant trial result into a non-significant result for binary data. A smaller fragility index indicates a more “fragile” trial. The index has recently gained prominence as a practical way of demonstrating how vulnerable a trial result is. In a recent study [Ridgeon 2016], the median fragility index for multicentre randomised controlled trials in critical care medicine reporting mortality was 2, and 40% (of 56 trials) had a fragility index of less than or equal to 1. This result suggests that much of the evidence we rely on is weak. The fragility index is currently not considered at the planning and design stage of a clinical trial. Furthermore it is currently only applicable to trials with a binary outcome looking to detect superiority. Developing the fragility index to allow its use within non-inferiority and equivalence trials as well as trials with ordinal or continuous outcomes would greatly help our understanding of the robustness of these trial results. Additionally the fragility index may lead to a stronger evidence base if it can be incorporated at the design stage for example adjusting the trial sample size to achieve a minimal index for results to be considered convincing to clinicians.

What the studentship will encompass: This PhD will develop methodology to allow the use of the fragility index to be extended. The student will consider how the fragility index could be incorporated at the design phase of a clinical trial and allow for its use in alternative frameworks. They will propose new indices, based on the ideas underlying the fragility index, which can be applied to ordinal scales, continuous scales and survival data, including a review of the relevant literature. They will investigate which of the new indices are more easily understood by clinicians, policy makers and patients, and make recommendations on where they should be used in the future, e.g. in Data Monitoring Committee reports. They will investigate how vulnerable a selection of recently published trials are, across a range of outcome data types.

Detail of supervision, including the roles of any named co-supervisors: Lead supervisor: Carrol Gamble (Liverpool) is Professor of Medical Statistics at the University of Liverpool, Deputy Director and Head of Statistics of the Clinical Trials Research Centre, and co-theme lead for later phase trials in the North West Hub for Trials Methodology Research. She is also Chair of the UKCRC registered CTU Statistics Operational Group.
2nd supervisor: Steff Lewis (Edinburgh) is Professor of Medical Statistics at Edinburgh University and leads the Edinburgh Clinical Trials Unit (ECTU) statistics team. She has access to a wealth of example trial datasets relevant to the project, across many clinical specialties. She has been working in trials methodology for 25 years and is an experienced PhD supervisor (including through the HTMR programme).
3rd supervisor: Marion Campbell (Aberdeen) is Professor of Health Services Research, and medical statistician, at the University of Aberdeen and an experienced trialist. She has been investigating the fragility index and its use in a cohort of UK trials. She is an experienced PhD supervisor
4th supervisor: Jonathan Cook, is Associate Professor and Fellow of St Hugh’s College
Centre for Statistics in Medicine University of Oxford and a member of the Bristol HTMR.

Detail of any planned field work / secondments / industry placement: This PhD topic could be undertake full or part-time. It would work well alongside systematic review experience and clinical trials. The successful candidate would be encouraged to gain experience within each of these areas across the Liverpool, Edinburgh, and Aberdeen. Travel to the three sites will be required.