coreSR.AI
Learn

ROBINS-I

Risk Of Bias In Non-randomized Studies — of Interventions

CoreSR implements the ROBINS-I tool with structured GLASS assessment. The model answers signaling questions across seven bias domains for non-randomized studies of interventions, and the tool keeps transparent rationale for every judgement.

AI Assessment Is a Starting Point

AI-generated assessments should always be reviewed and verified by a human assessor with domain expertise. The structured AI output highlights uncertainty and source-evidence gaps, but the final judgement is yours. For published systematic reviews, all RoB assessments should be conducted by at least two independent human reviewers.

How It Works

Five steps from PDF upload to a complete domain-level risk of bias assessment for non-randomized intervention studies.

1UploadPDFsFull-text papersSupplements2StudyDetailsTitle & authorsIntervention3StructuredAI ReviewGLASSSignaling Qs4DomainJudgements7 domainsSignaling Qs5Review &OverrideUser overridesExport

Step-by-Step Guide

Each step builds on the previous one. AI assessment runs automatically after you provide the study details.

Step 1

Upload Study PDFs

Upload one or more full-text PDF files for the non-randomized study you want to assess. The AI extracts text from the PDFs to inform its domain-level judgements.

You can upload multiple PDFs per study (e.g., main paper + supplementary appendix) for more complete assessment.
Step 2

Enter Study Details

Provide the study title, authors, publication year, intervention of interest, and comparator. Specify the target trial design that the non-randomized study is emulating.

Clearly defining the target trial helps the AI assess confounding and selection bias more accurately.
Step 3

Run AI Assessment

Click "Evaluate with AI" to run a structured GLASS assessment. The model answers ROBINS-I signaling questions for each domain, and the tool derives domain and overall judgements from those structured answers.

Assessment typically takes 45-90 seconds per study due to the additional domains compared to RoB 2.0.
Step 4

Review and Override

Review each domain's signaling questions, AI justifications, and judgements. You can override any answer or domain judgement. Pay special attention to the confounding domain, as it often requires expert knowledge of the clinical area.

Focus your attention on domains with low confidence or sparse source evidence.

The Seven Domains

ROBINS-I evaluates risk of bias across seven domains, each assessed through a series of signaling questions.

D1

Bias due to confounding

Is there potential for confounding of the effect of the intervention? Did the authors use an appropriate analysis method that controlled for all the important confounding domains? Were confounding domains measured validly and reliably?

D2

Bias in selection of participants into the study

Was selection of participants into the study (or into the analysis) based on participant characteristics observed after the start of intervention? Were the post-intervention variables that influenced selection likely affected by the intervention?

D3

Bias in classification of interventions

Were intervention groups clearly defined? Was the information used to define intervention groups recorded at the start of the intervention? Could classification of intervention status have been affected by knowledge of the outcome or risk of the outcome?

D4

Bias due to deviations from intended interventions

Were there deviations from the intended intervention beyond what would be expected in usual practice? Were important co-interventions balanced across intervention groups? Was the intervention implemented successfully for most participants?

D5

Bias due to missing data

Were outcome data available for all, or nearly all, participants? Were participants excluded due to missing data on intervention status? Were participants excluded due to missing data on other variables needed for the analysis?

D6

Bias in measurement of outcomes

Could the outcome measure have been influenced by knowledge of the intervention received? Were outcome assessors aware of the intervention received by study participants? Were the methods of outcome assessment comparable across intervention groups?

D7

Bias in selection of the reported result

Is the reported effect estimate likely to be selected, on the basis of the results, from multiple outcome measurements, multiple analyses, or different subgroups?

Structured AI Review Process

GLASS answers structured signaling questions, then the tool stores domain judgements with source-grounded rationale for human review.

Structured Answers

The assessment is built from signaling-question answers rather than an unstructured overall guess. Each answer includes rationale and confidence so the basis for the domain judgement is inspectable.

Uncertainty Flags

Low-confidence answers, no-information answers, and sparse source evidence remain visible in the domain details so reviewers can focus attention where the automated assessment is least certain.

Human Override

You can override any signaling question answer or domain judgement. Your decision always takes precedence over the AI. Overrides are tracked and clearly marked in exports for audit trails.

Judgement Scale

Low risk of bias

Comparable to a well-performed RCT for this domain.

Moderate risk of bias

Sound for a non-randomized study but not equivalent to a well-performed RCT.

Serious risk of bias

The study has a serious problem in this domain that substantially lowers confidence.

Critical risk of bias

The study is too problematic in this domain to provide useful evidence.

No information

Insufficient information reported to assess risk of bias for this domain.

Frequently Asked Questions

Common questions about ROBINS-I assessments in CoreSR.

What is ROBINS-I?
ROBINS-I (Risk Of Bias In Non-randomized Studies — of Interventions) is a tool developed by the Cochrane Bias Methods Group for assessing risk of bias in non-randomized studies that estimate the effect of an intervention (e.g., cohort studies, case-control studies, before-after studies). It covers seven domains and uses a structured approach with signaling questions.
When should I use ROBINS-I instead of RoB 2.0?
Use ROBINS-I for non-randomized studies of interventions (e.g., cohort studies, quasi-experimental designs). Use RoB 2.0 for randomized controlled trials. If your study randomly assigned participants to intervention groups, RoB 2.0 is appropriate. If it did not, use ROBINS-I.
When should I use ROBINS-I vs ROBINS-E?
ROBINS-I is for studies evaluating the effect of an intervention (something deliberately applied, like a treatment or policy). ROBINS-E is for studies evaluating the effect of an exposure (something participants experience or are exposed to, like a pollutant or dietary factor). The key distinction is whether the "treatment" was intentionally assigned or is an environmental/behavioural exposure.
How does confounding assessment work?
The confounding domain requires you to identify the key confounders relevant to the research question before assessing a study. The AI attempts to identify important confounders from the study context, but you should verify these against your protocol's pre-specified confounder list. Adequate control of confounding is often the most critical domain in non-randomized studies.
What is the "target trial" concept?
ROBINS-I asks assessors to consider the hypothetical pragmatic randomized trial that the non-randomized study is attempting to emulate. Defining this "target trial" helps clarify what the ideal study design would look like and where the actual study may deviate, introducing risk of bias.
How does the judgement scale differ from RoB 2.0?
ROBINS-I uses a five-point scale: Low, Moderate, Serious, Critical, and No Information. "Low" corresponds to a well-conducted RCT. "Moderate" means the study is sound for a non-randomized study but cannot be considered comparable to a well-performed RCT. "Serious" and "Critical" indicate increasing levels of bias that may substantially affect confidence in the result.
How does the AI review work?
GLASS evaluates each ROBINS-I signaling question using structured JSON output with source-grounded rationale. The application stores signaling answers, domain judgements, rationale, and confidence so a human reviewer can verify or override them.
Can I export the results?
Yes. You can export individual study assessments or the full project summary as CSV. The export includes all domain judgements, signaling question answers, AI justifications, and any user overrides.

Ready to assess?

Upload a study PDF and let AI provide a first-pass ROBINS-I risk of bias assessment.

Go to ROBINS-I

References

1. Sterne JAC, Hernán MA, Reeves BC, et al. ROBINS-I: a tool for assessing risk of bias in non-randomised studies of interventions. BMJ. 2016;355:i4919. doi:10.1136/bmj.i4919

2. ROBINS-I V2 development group. The Risk Of Bias In Non-randomized Studies — of Interventions, Version 2 (ROBINS-I V2) assessment tool. November 2025.

3. Schünemann HJ, Cuello C, Akl EA, et al. GRADE guidelines 18: How ROBINS-I and other tools to assess risk of bias in nonrandomized studies should be used. J Clin Epidemiol. 2019;111:105-114. doi:10.1016/j.jclinepi.2018.01.012

CoreSR · Evidence Synthesis Platform