coreSR.AIcoreSR
Usage Guide

ROBINS-I

How to assess risk of bias for non-randomised interventions

1

Set up the assessment

  1. 1Create a new ROBINS-I assessment
  2. 2Define your research question and target trial
  3. 3Specify pre-intervention confounders
  4. 4Upload the study manuscript
2

Two-phase AI analysis

  1. 1Phase 1: AI analyses the document for context, confounders, and preliminary settings
  2. 2Review and adjust the AI suggestions
  3. 3Phase 2: AI evaluates all 7 bias domains using the context from Phase 1
  4. 4Review domain-level judgments with rationales
Tip: The two-phase approach gives more accurate results than single-pass assessment.
3

Review and export

  1. 1Review each domain: Confounding, Selection, Classification, Deviations, Missing Data, Measurement, Reporting
  2. 2Override any judgment
  3. 3Generate the overall risk of bias rating
coreSR.AICoreSR

AI-powered evidence synthesis