Home/Blog/How to Screen Paper Titles for a Systematic Review
Blog

How to Screen Paper Titles for a Systematic Review

P
promptstudio
How to Screen Paper Titles for a Systematic Review

Title screens invent abstracts. Include or exclude from the title tokens only.

The matching generator is the Title-Only Systematic Review Screener from Pasted Titles (No Invented Inclusion) prompt. Browse related cards in the PromptDig library (Browse more prompts). When a filled run survives, share the version you actually use (Share a prompt).

Lock include and exclude rules first

Screen pasted paper titles against locked include/exclude rules. Never invent inclusion, abstracts, or DOIs. Start by filling Inputs, not by asking the model to remember last week's run. If a field is blank, write NONE or NOT IN INPUTS and leave it blank through Generate. The card is built so the model cannot honestly invent a number, owner, URL, or command that you did not paste.

Paste these fields before you hit run:

Pasted titles (one per line, as numbered): [Titles]
Include rules I lock: [Include]
Exclude rules I lock: [Exclude]
Words I must not use: [Banned]
What I must never invent: [Never]
Output format: [Format]
Language: [Lang]
Banner I require: [Banner or Not medical advice]

That inventory is the honesty ledger. Anything that does not appear there is forbidden in the draft. If you catch yourself adding a nice-to-have after the run, you are no longer using the card. You are ghostwriting. Put the extra fact in Inputs and run again.

Mark TITLE TOO THIN instead of guessing

Generate is numbered on purpose. Do not skip a step because the first paragraph looked done. The early steps exist to stop later prose from smuggling claims.

Walk the Generate list in order:

  1. Honesty ledger: title count, Include rules, Exclude rules, Banner, Lang. Forbidden: inventing abstracts, DOIs, sample N.
  2. Banner line.
  3. Per-title table: ID, title quoted, decision Include/Exclude/Unclear, reason quoting only title tokens plus Include/Exclude rules.
  4. If a title lacks enough words to apply a rule, mark Unclear and write TITLE TOO THIN, not a guessed abstract.
  5. Counts: Include n, Exclude n, Unclear n. Do not add titles.
  6. Refuse: full-text screening, PRISMA flow numbers, invented years, Cochrane ID invent.
  7. Dual-reviewer note: if a second screener is not in Inputs, write SECOND SCREENER NOT IN INPUTS.
  8. Compliance pass: quote Banned and Never hits. Format as Format.

If a step asks for a version lock, quote the version from Inputs in the output. If a step asks for a refuse list, keep the refuse list in the published artifact, not in a sidebar you delete. Reviewers should see what the model was not allowed to do.

Refuse PRISMA flow numbers

Most failures are the same shape: a missing field gets a confident fill. A conversion rate appears. A Gradle task appears. A flash point appears. A caption appears on a job that asked for slide text only. Your review is to search the draft for numbers, names, and commands, then grep Inputs. No match means cut.

Honor the constraints as hard stops, not vibes:

  • Title-only screen from Titles plus Include/Exclude. Not a PRISMA assistant and not medical advice.
  • Never invent inclusion, abstracts, or DOIs.
  • Keep Banner visible.
  • No emojis.

When the card says not legal advice, not certification, not an exam dump, or not a caption engine, that sentence belongs at the top of the output. Deleting it to look more finished is how you inherit risk.

Leave the second screener blank when missing

Finish with the compliance pass the prompt already asks for. Quote the banned-word hits. Cut them. Print character counts when the job has a cap. Print word counts when the job has a budget. List gaps as gaps. Five missing facts are more useful than one smooth paragraph.

Tags on the card (title only systematic review screener, pasted titles no invented inclusion, title screen include exclude) are a reminder of the job shape, not an invitation to wander into a neighboring cluster. If you need a different surface, open a different PromptDig card rather than stretching this one.

Fill the card, then run

Replace every bracket. Run on ChatGPT, Claude, or Gemini. Read the ledger first, then the artifact. If the model invents a commit, KPI, DOI, PEL, bid, or logo, discard the run. Tighten Inputs. Run again. Share the filled card that survived, not the first draft that sounded done.