RobotReviewer is a Machine Learning system which automates the assessment of bias in clinical trials. RobotReviewer takes the full text of a clinical trial report, and instantly returns a completed Cochrane Risk of Bias tool, including justifications for its judgements.

We have a demo version you can try here for your own systematic reviews.

We are actively working on extending RobotReviewer so that it can extract other important data from clinical trial report

How does it work?

Our algorithms 'learn' how to assess bias from existing systematic reviews, specifically from the Cochrane Database of Systematic Reviews. RobotReviewer performs well compared to human Risk of Bias assessment; you may wish to use RobotReviewer to replace one of the two human assessors typically used for bias assessment.

Our validation study, together with a description of our methods is available in our JAMIA paper.

Citing RobotReviewer

We offer RobotReviewer free of charge, but we'd be most grateful if you would cite us if you use it. We're academics, and thrive on links and citations!

Getting RobotReviewer widely used and cited helps us obtain the funding to maintain the project and make RobotReviewer better.

It also makes your methods transparent to your readers, and not least we'd love to see where RobotReviewer is used! :)

You can cite RobotReviewer as:

Marshall IJ, Kuiper J, & Wallace BC. RobotReviewer: evaluation of a system for automatically assessing bias in clinical trials. Journal of the American Medical Informatics Association 2015. [doi:10.1093/jamia/ocv044]

A BibTeX entry for LaTeX users is:

title = {{RobotReviewer: evaluation of a system for automatically assessing bias in clinical trials}},
author = {Marshall, Iain J and Kuiper, Jo\"{e}l and Wallace, Byron C},
doi = {10.1093/jamia/ocv044},
url = {},
journal = {Journal of the American Medical Informatics Association},
year = {2015}
month = jun,
pages = {ocv044}


Want to use RobotReviewer in your systematic review creation software? You may do so free of charge in return for linking to us.

Source code and full details available at our github page.