Abstract and full-text screening
A decision and a reason on every paper, for |
In the product
The evidence
Screens titles, abstracts, and PDFs. Finds more relevant papers than one human reviewer.
Abstract screening
Abstractus
Manual
Full-text screening
Median recall
12 public datasets · 3,514 papers
screenings done in the time a researcher does one
Time to screen a review
Human comparison: Gartlehner et al., 2020 (single reviewers missed 13%). Abstract screening methods on the benchmark results post.
What you get
Include or exclude on every abstract and PDF, with a written reason. Share the review when you need to.
Upload RIS, NBIB, or CSV. Set your criteria. Get include or exclude on every record.
Upload up to 1,000 PDFs that passed abstract screening.
Each include or exclude comes with a written reason.
Invite by email as viewer, commenter, or editor. Talk through the review in the Run log. Organizations can keep sharing off, inside the org, or open to anyone.
Search
Abstractus writes the search, then runs it across papers and patents.
Free. Turn a research question into search strings, with MeSH, Emtree, and a live hit count.
One question, every database, one deduplicated set. The exact query sits next to each result.
We search these for you
Research Databases
· 6 databases
Searched at once, merged and deduplicated, abstracts ready to screen.
Patents and trademarks
· 3 registers
USPTO patents, plus EPO worldwide patents from about 100 authorities.
We write the search string, you run it
Every major review database
· 14 databases
Each database has its own syntax: controlled vocabulary, field tags, proximity, and truncation. Get one wrong and the results change.
How it works
Abstracts first, then PDFs. Months of reading in minutes.
Question, inclusion, and exclusion criteria. Search Assist writes the search strings.
RIS, NBIB, or CSV. Duplicates removed before screening.
Include or exclude on each paper, with a written reason.
Upload the PDFs that passed.
Sort, filter, and read the reason. Share by email. Discuss it in the Run log.
Decisions, reasons, and PRISMA counts as CSV.
From the blog
Benchmarks, methodology, and notes on evidence synthesis. Our numbers are written up so you can check them.
13 August 2026
Screening is the biggest part of a review, but it is not the only part. Recent updates: Search Assist, deduplication, and collaboration next.
Read the post
1 August 2026
On a public benchmark of 57,177 abstracts, our screening reaches a median recall of 95% and cuts the manual screening workload by 84%.
Read the post
25 July 2026
We are starting a blog about systematic reviews, evidence synthesis, and the software we are building to make screening faster.
Read the post
Bring your search results and screen them today, or talk to us about seats for a department or research group.
