PRISMA 2020 & extensions

Systematic Reviews and Meta-Analyses: reviewed like a reviewer would

Q: Does the review check whether my included studies have been retracted?

Yes. Every DOI in the reference list is screened for retractions, and a retracted reference is flagged with the retraction notice so you can decide how to handle it.

Q: Which PRISMA variant applies to a scoping review or a network meta-analysis?

Scoping reviews are audited against PRISMA-ScR and network meta-analyses against PRISMA-NMA; protocols use PRISMA-P and individual-participant-data reviews use PRISMA-IPD.

Q: Can it detect references that do not exist?

References that cannot be matched in PubMed or Crossref are reported as unverified with the fields that failed to match. Unverified is not the same as fabricated, and the report says so; you check the flagged ones.

Q: Does it re-run my search?

No. It audits whether the search is reported completely enough to be reproduced, which is a PRISMA 2020 requirement, but it does not re-execute database searches.

A systematic review is only as trustworthy as its references and its search. Reference errors are common in the literature, fabricated citations are now a documented risk, and retractions inside an included-study list are invisible unless someone checks every DOI.

Start a review — $49 See a full sample review

For the manuscript you're submitting · no accept/reject verdict

What the review checks

Built around PRISMA 2020.

Completed reviews route to PRISMA 2020; protocols to PRISMA-P; scoping reviews to PRISMA-ScR; network meta-analyses to PRISMA-NMA; individual participant data reviews to PRISMA-IPD.

PRISMA 2020 audit: eligibility criteria, information sources and full search strategies, selection and data-collection processes, risk-of-bias methods, synthesis methods, certainty assessment, registration and protocol.
Every reference, including every included study, checked against PubMed and Crossref and screened for retractions by DOI, with a per-reference status table in the report.
Heterogeneity, model choice, small-study effects, and whether pooled estimates are reported with the uncertainty the methods promise.
Compliance audit against the target journal's author instructions.
Journal formatting applied to the .docx as tracked changes, included.

PRISMA 2020 guide →PRISMA-P, PRISMA-ScR, PRISMA-NMA and PRISMA-IPD extensions →

The evidence

Why this matters, in numbers.

Each figure is quoted from its primary source; the bracketed number links to the reference below. Verified 2026-09-12.

25.4%

A meta-analysis of 28 studies found 25.4% of quotations in medical journal articles were inaccurate: 11.9% major and 11.5% minor errors. [43]

55% / 18%

55% of the references ChatGPT-3.5 generated for literature reviews were fabricated, versus 18% for GPT-4; 43% and 24% of the real ones contained substantive errors. [35]

66,901 records

The Retraction Watch Database held 66,901 retraction records on 12 September 2026; 13,226 are dated 2023, of which 9,673 are Hindawi titles, followed by 6,356 in 2024 and 5,905 in 2025. [34]

85.7% methods

Reviewers found flaws in the methods of 85.7% of 42 manuscripts submitted to medical journals in Africa and Asia, and in the references of 69.0%. [13]

6.6 million

Crossref lists 6,628,652 journal articles with a 2025 publication date, up from 3,342,205 for 2015. [11]

~75%

About 75% of published articles were submitted first to the journal that published them; high-impact journals published proportionally more resubmissions. [48]

From Peer review statistics 2026, 89 verified statistics

What you get

One pass, $49.

Included

16-section review
Every reference checked against PubMed and Crossref; status per reference; retraction screening on every DOI
Audit against the target journal's author instructions
Journal formatting applied to your .docx as Word tracked changes, included

Ground rules

No accept/reject verdict.
Zero Data Retention (Anthropic); never stored or used for training.
$49 per manuscript, no subscription. Journal Brief $2.99 per paper (first free). ESL add-on $19.99.
Full 16-section sample review published.

What it cannot do

It cannot detect fabricated or falsified data, manipulated images, or anything that is not visible in the manuscript text and references. It finds the manuscript-visible problems that reviewers and editors find, before they do.

Protected by Anthropic’s Zero Data Retention

Your manuscript is never stored, logged, or used for training.

FAQ

Questions, answered.

Don't see yours? Email us — we read every one.

Does the review check whether my included studies have been retracted?+

Which PRISMA variant applies to a scoping review or a network meta-analysis?+

Can it detect references that do not exist?+

Does it re-run my search?+

Sources

Sources cited on this page

Every figure on this page is quoted from the primary source listed here. Verification dates are recorded per source.

[1]Crossref REST API, count of works of type journal-article by publication year. Query run 12 September 2026. api.crossref.org/works?filter=type:journal-article,from-pub-date:2025-01-01,until-pub-date:2025-12-31&rows=0database query (reproducible) · verified 2026-09-12
[2]Ezeala C, Nweke I, Ezeala M. Common errors in manuscripts submitted to medical science journals. Annals of medical and health sciences research 2013. doi:10.4103/2141-9248.117957 PMID 24116317.peer-reviewed article (Europe PMC / Crossref record) · verified 2026-09-12
[3]Retraction Watch Database (Crossref). CSV downloaded 12 September 2026; yearly counts computed by PeerReviewAI from the RetractionDate field, records with RetractionNature = Retraction. gitlab.com/crossref/retraction-watch-datadatabase download (reproducible; CSV on file) · verified 2026-09-12
[4]Walters WH, Wilder EI. Fabrication and errors in the bibliographic citations generated by ChatGPT. Scientific reports 2023. doi:10.1038/s41598-023-41032-5 PMID 37679503.peer-reviewed article (Europe PMC / Crossref record) · verified 2026-09-12
[5]Jergas H, Baethge C. Quotation accuracy in medical journal articles-a systematic review and meta-analysis. PeerJ 2015. doi:10.7717/peerj.1364 PMID 26528420.peer-reviewed article (Europe PMC / Crossref record) · verified 2026-09-12
[6]Calcagno V et al. Flows of research manuscripts among scientific journals reveal hidden submission patterns. Science (New York, N.Y.) 2012. doi:10.1126/science.1227833 PMID 23065906.peer-reviewed article (Europe PMC / Crossref record) · verified 2026-09-12

Submit the version a reviewer would struggle to fault.

Upload the manuscript, name the target journal, and get the review, the reference table, the checklist audit and the formatted .docx back in minutes.

Start a review — $49 Read the sample review

For the manuscript you're submitting

Other study types

Randomized trials Observational studies Case reports Early-career researchers AI peer review for the manuscript you're submitting