-
Notifications
You must be signed in to change notification settings - Fork 31
metawRite: Meta analysis update package, LSR (Living systematic review).
Systematic reviews are an approach used by public health agencies such as the World Health Organization to understand how treatments are effective and a way to approach to disease control. Systematic review the literature and often include a meta-analysis that summarizes the findings of multiple studies. It is critical that such reviews are updated rapidly as new scientific information becomes available, so the best evidence is used for the best advice. However, the current peer-reviewed journal based approach to publishing systematic reviews means that reviews can rapidly become out of date and updating is often delayed by the publication model. Living systematic reviews have been proposed as a new approach to dealing with this problem. The main concept of a living review is to enable rapid updating of systematic reviews as new research becomes available, while also ensuring a transparent process and reproducible review. Our approach to a living systematic review will implemented in an R package. Our goal is to combine in the package, the writing and analysis of the review in a seamless package that also enables versioning and updating.
The R package we propose (metawRite) will be available on CRAN to be used for anyone who want an easy and effective way to display a living systematic review available in a web-based display. This allows to reach to a wider community because it is free and one of the most used statistical software.
Three main tasks are needed to have an effective living systematic review; the ability to produce dynamic reports, availability online with an interface that enables end users to understand the data and the ability to efficiently update the review(and any meta-analysis) with new research seamless . The package we propose will cover these three task integrated in a friendly web based environment for the final user.
This package is not a new meta analysis package instead will be flexible enough to read different output models from the most used meta-analysis packages in R, organize the information and display the results in an user driven interactive dashboard. The main function of this package will display a modern web-based application for update a living systematic review.
This package combines the power of R and shiny to get a dynamic reports and up to date meta-analysis results remaining user friendly. The package has the potential to be used by a large number of groups that conduct and update systematic review such as What Works clearing house (WWC) – which reviews education interventions, Campbell Collaboration (cambell-colalboration) that includes reviews on topics such as social and criminal justice issues and many other social science topics, the Collaboration for Environment Evidence (environment-evidence) and food production and security (syreaf).
There are a lot of packages in R to do meta-analysis meta, metafor, metanet among others.
but there is not R package to do a Living Systematic Review (LSR).
Most of the meta-analysis packages focused on model fitting and visualize the results. As far as we know there is not an R package that allows to get living systematic review.
- Tidy data: a couple of functions would be expected to facilitate the data structure after fitting a meta-analysis model with the most used R packages.
-
Visualization: With the model information some interactive visualizations will be available using
ggplot2,plotlyandshinypackages. Interactive visualization is relevant in LSR because we want the user to explore the results from different updates and be able to check the information mousing over the plot. -
Report: Easy display to do an update report based on LSR proposed structure using
kntr.
The final user will get a web application using shiny with three modules or tabsets as a main result,
- Report: this first tablset will display an environment to make an interactive report using kntr. You will write your update report in the web application to be available online and the user can download the report in different formats as they need it. Also the previous reports will be available to be modified using the shiny interactive functionalities.
- Pairwise meta-analysis: In this second tabset the main results from a pairwise meta-analysis will be displayed. The user can interact in the application to self discover the main results, selecting the update results and treatments to explore. Model fit and interactive plots will be available.
- Network meta-analysis: If network meta analysis is needed this third tabset will be available. The main results from a network meta-analysis will be displayed. The user can interact in the application to self discover the main results, selecting the update results to explore. Model fit and interactive plots will be available.
Since will be the first R package to do a LSR we expect an important impact in the systematic review community. This package will facilitate and organize all the information together to have a real update for any long term meta-analysis
- Dr Heike Hofmann, Visualization, statistical computing
- Dr Annette O’Connor, meta-analysis, systematic review
- Easy: Explore the most used R packages to run meta-analysis. Select one package you consider is appropriate and run an example for a pairwise meta-analysis comparison. Summarize the main results from your model in a .Rmd file.
- Medium: Using some meta-analysis package, write a function to read data in an arm-based format and return it in contrast based format. This function should fit a pairwise meta-analysis for each pair and store the model results in a convenient way.
- Hard: Write a shiny app with the main components of a LSR. Should contain dynamic reports, an efficient way to do the updates and should be available online. This shiny should contain summary results for each meta-analysis update (pairwise and network meta-analysis if corresponds) and dynamic reports for each update.