Meta-analysis

Following the delivery of systematic reviews by our Evidence Development Team, Costello Medical has the in-house capability to perform the statistical synthesis of the identified data, whether that be through meta-analysis or network meta-analysis. We combine scientific and statistical skills to produce and communicate complex analyses for varying purposes, such as publications, HTA submissions or value materials.

What Makes Meta-analysis at Costello Medical Different?

  • Combination of clinical and statistical knowledge. Our experience of working with clinical studies allows us to critically evaluate the studies that feed into our statistical analysis, ensuring that the analysis is robust, justifiable and clinically appropriate. The scientific skills possessed by the team also guarantee that the results of the statistical analysis are interpreted and communicated correctly and persuasively for the purposes of the project.
  • Cross-divisional collaboration. A single, multi-skilled team including members of the Evidence Development and Meta-analysis Divisions will work on both the systematic review and meta-analysis elements, ensuring that the literature review part of the project seamlessly merges with the evidence synthesis.
  • Reasonable budget. Due to the careful scoping of the projects and our understanding of the clinical inputs, we can format the data from the systematic reviews and therefore perform the statistical analysis very efficiently. We therefore believe that we offer value for money, yet high quality, evidence synthesis services that will fit your budget. We set out our fees in a clear and transparent way, so that you can see how long it takes for us to complete each step of the project.
  • High quality communication skills. Following completion of the statistical analysis, our Biostatisticians can work closely with Medical Writers from our Publications Team to write-up the analysis into a technically comprehensive, engaging and eloquent manuscript.

Please contact Lucy Eddowes for further information on meta-analysis at Costello Medical, or to request a quote.

In order to perform a network meta-analysis to inform a value dossier, we first had to complete a systematic review, which identified more than 100 studies for assessment for inclusion in the evidence synthesis. We followed a detailed feasibility assessment process to decide which studies should be included and to devise 10 different networks containing up to 37 studies in each. Each step was recorded and justified carefully, which was particularly important in a project where there are many decisions made on how to synthesise vast amounts of data. The outcomes analysed included binary and continuous variables, and the analyses were conducted in a Bayesian framework. Given the large evidence base and vast networks, we investigated the heterogeneity and inconsistency across trials both statistically (by fitting models such as unrelated mean effects models) and through qualitative assessment of the baseline characteristics and study designs.

We approached this enormous undertaking in a systematic and meticulous way, and ensured that each stage of data extraction and model coding was checked by a second Analyst. The final result was a robust assimilation of a great volume of data. From this, we advised the client on the most clinically valid interpretation of the results to support a persuasive value message, which led to the client being extremely satisfied with the resulting value dossier.

Following an extensive systematic review and feasibility assessment of 22 initial studies, we originally found only 3 that fulfilled the inclusion criteria for a meta-analysis on the outcome of interest proposed by the client. Given this lack of data, we proposed to evaluate and run meta-analyses of additional outcomes and additional time points in order to provide the client with as much valuable information as possible given the existing evidence, at no additional cost. The outcomes evaluated in the meta-analysis included binary and continuous variables, and the analysis was carried out in a frequentist framework.

The systematic literature review and meta-analysis were conducted by highly connected teams within Costello Medical. This facilitated a perfect understanding of the data available and therefore a well-founded justification for the inclusion and exclusion of studies, which was of particular importance for the client given the large number of studies that were excluded from the final analyses. The final results from the range of meta-analyses were successfully incorporated into the value story for the product.