English homeMethodsRobotReviewer Systematic Review Guide: Automated Risk-of-Bias Assessment, RCT Study Quality, and Rayyan/Covidence Workfl
Method Guide
RobotReviewer Systematic Review Guide: Automated Risk-of-Bias Assessment, RCT Study Quality, and Rayyan/Covidence Workfl
How to use RobotReviewer for RCT quality appraisal, risk-of-bias prompts, and systematic review workflows with human review.
Before using this in research
The goal is not to adopt another tool. The goal is to reduce verified research time without weakening the evidence trail.
Best for
Biomedical, medical, and academic researchers conducting systematic reviews of randomized controlled trials, especially teams that need structured support for study quality appraisal, risk-of-bias assessment, and reviewer workflow coordination.
First step
Start by defining the review question, eligibility criteria, outcomes, and risk-of-bias framework. Then identify which RCT full texts or abstracts will be assessed with RobotReviewer and which decisions must be checked by human reviewers.
A safer workflow
1
Use Rayyan, Covidence, or ASReview for citation screening, deduplication, and reviewer assignment according to your review protocol.
2Apply RobotReviewer to relevant RCT records to generate risk-of-bias prompts and study quality signals that can help focus reviewer attention.
3Have trained reviewers compare RobotReviewer outputs against the trial report, protocol details when available, and the chosen risk-of-bias criteria.
4Record final human judgments, disagreements, and reasons for decisions in the main review platform or extraction sheet, keeping automated outputs as supporting information rather than definitive conclusions.
Watch-outs
Do not treat automated risk-of-bias suggestions as final assessments; they require human verification against the full study report.
Check whether each included study is actually an RCT and whether the available text contains enough detail for appraisal.
Keep platform roles clear: screening and workflow management belong in tools such as Rayyan, Covidence, or ASReview, while RobotReviewer is used to support quality and bias assessment.
Evidence checks
Confirm that randomization, allocation concealment, blinding, attrition, selective reporting, and other relevant domains are judged using the review protocol's criteria.
Compare automated prompts with the exact methods and results reported in the publication, supplement, registry entry, or protocol when available.
Document how automated outputs were used, how human reviewers resolved conflicts, and which evidence supported each final risk-of-bias judgment.
Need the complete current version?
Open the full detail page
This English version is a curated decision page. The full current detail page remains available while the English library is being expanded.