PeerGenius
Evidence

Measured against real peer reviews, and reported either way.

Reviews of 5 manuscripts published in The BMJ between 2021-2023, scored against the peer reviews those journals published alongside them.

8.86
AVERAGE SCORE OUT OF 10

Against a journal reviewer average of 7.86, scored blind across ten dimensions.

4 of 5
REACHED NEAR-PARITY

Scored within one point of the published journal review for the same manuscript.

64.2%
COMPLEMENTARITY

Issues raised by one reviewer and not the other, in both directions.

What this does not show

This is a preliminary analysis of 5 manuscripts, not a controlled trial. The complementarity figure of 64.2% cuts both ways: it means the AI panel and the journal reviewers each raised substantial issues the other missed. Read it as evidence that the two are complementary, not that either replaces the other.

The manuscripts

Every manuscript, its published journal review score, and the score the panel earned on the same paper. Open any review to read it in full.

ManuscriptDesignJournalPanelReview
Hippisley-Cox et al. 2022Risk Prediction Model8.39.2Open PDF
Mok et al. 2023Pharmacoepidemiology Cohort7.69.6Open PDF
Morales et al. 2022Interrupted Time Series7.88.1Open PDF
Rees et al. 2021Population-Based Cohort7.88.8Open PDF
Woolf et al. 2023Mendelian Randomisation7.88.6Open PDF

Full scoring rubric, dimension definitions, and the replication prompt are in the methodology.

See what it finds in yours.

Upload a manuscript and read the assessment before deciding anything.

Get free assessment