Skip to content
Get started

Literature screening review

Review supplied abstracts against explicit inclusion and exclusion criteria, keep evidence quotations and show reviewer disagreements before selection.

Input

Supplied publication records CSV: id,title,year,language,text R1,Workshop training comparison,2024,en,The study compares two training groups of adult participants. Allocation was not randomized. R2,Workshop training comparison,2023,en,Th…

Result

The first abstract explicitly describes two training groups, while its reviewers disagree between include and unclear. The second record has the same normalized title and lacks a comparison group in the supplied text. The draft highlight…

Screening becomes more reviewable when the protocol, source excerpt and reviewer decision remain separate. The AI evaluates each supplied record against every explicit inclusion or exclusion criterion and returns a bounded match suggestion with an exact quotation. The server independently checks supplied year and language metadata, possible duplicate titles and human reviewer coverage. Conflicts remain visible instead of being resolved by the model.

Your texts, pages and images are processed on our own servers in the EU. Trust Center

Try it now Pricing

Who it is for

Research teams, students and evidence-review groups organizing an initial screening or a review of supplied full-text excerpts. Suitable for preparing a documented human review, not for establishing study quality, completeness of a literature search or clinical conclusions.

Typical uses

  • Apply the same explicit protocol criteria to every supplied record.
  • Distinguish an exclusion-condition match from a final exclusion decision.
  • Keep two reviewers' differing decisions and notes visible alongside the model suggestions.
  • Flag out-of-range years, unsupported language tags and possible duplicate titles without removing records.

Example

Input

Supplied publication records CSV: id,title,year,language,text R1,Workshop training comparison,2024,en,The study compares two training groups of adult participants. Allocation was not randomized. R2,Workshop training comparison,2023,en,The report describes a single training group without a comparison group. Screening criteria CSV: id,kind,definition C1,include,A comparison group is described. C2,exclude,Participants are children. Supplied human reviews CSV: id,record,reviewer,decision,note V1,R1,REVIEWER1,include,Comparison group is described. V2,R1,REVIEWER2,unclear,Check whether the comparison meets the protocol. Confirm supplied definitions: Confirmed for this review Confirmed definition version: PROTOCOL-1 Quotation detail: Detailed Result order: Source order First publication year: 2020 Last publication year: 2026 Allowed supplied language tags: en Required human reviewers: Two human reviewers Duplicate-title review: Flag for review Declared supplied evidence scope: Supplied title and abstract

Result

The first abstract explicitly describes two training groups, while its reviewers disagree between include and unclear. The second record has the same normalized title and lacks a comparison group in the supplied text. The draft highlights the possible duplicate, reviewer gaps and criterion-level evidence. Neither record is automatically included or excluded.

A fixed example, shortened. Real results are AI-generated: please check them.

Price and limits

Price
usually 1–3 credits
Available with
Free, With package
Input limit
One page with up to 80,000 characters of HTML

Privacy

Processed on our own servers in the EU (Poland). Inputs and results are deleted after 7 days (Free) or 30 days (packages), or right after you see the result if you choose not to store them. Images are deleted right after processing.

In the API

Tool name: literature_screening. Create a job with POST /api/v1/jobs and fetch the result with GET /api/v1/jobs/{id}. You find your API key in your account.

curl -X POST https://do4u.eu/api/v1/jobs \
  -H "Authorization: Bearer d4u_…" -H "Content-Type: application/json" \
  -d '{"tool": "literature_screening", "url": "https://example.com/"}'

Full API documentation →

Questions and answers

Does a matching quote prove a criterion is satisfied?

No. The quotation proves only that the exact passage exists in the supplied text. The relationship between that passage and the criterion is an AI interpretation requiring human review. Missing or ambiguous evidence should remain unclear, and no unavailable full text is inferred.

How are inclusion and exclusion criteria interpreted?

For either criterion type, match means that the supplied text appears to meet that criterion's definition. An inclusion criterion marked no_match and an exclusion criterion marked match both create review flags. Neither becomes an automatic final selection.

How are reviewer conflicts handled?

The server checks distinct supplied reviewer IDs and compares their recorded include, exclude or unclear decisions. Missing reviewers, disagreements and unclear decisions produce separate findings. Reviewer labels are not verified identities, and the model cannot alter a supplied human decision.

Is my text stored?

Only as long as needed: 7 days on Free, 30 days with a package – or not at all if you choose not to store it. Processing happens on our own servers in the EU (Poland).

Can I use the result right away?

Results are AI-generated. Please read them before you publish or send them.