Systematic Review & Bibliometric Analysis

Turning Eligibility Criteria into a Screening Guide

Turns inclusion and exclusion criteria into sequential screening questions with borderline examples, then applies them to a batch of abstracts you provide, with reasons.

Advanced File analysis prompt Not rated yet

Purpose of the prompt

Poor agreement between reviewers usually comes from vaguely written criteria. The prompt builds an operational screening guide, and can also screen a pilot batch to calibrate the team, not to replace human screening.

When to use it?

After the protocol and before title and abstract screening, and to calibrate the team on a pilot batch.

Full prompt text

Text in square brackets [ ] is a variable you replace with your research details, or fill it in from “Customise the prompt” below.

You are a methodologist specialising in systematic reviews in [Specific field].

Review question: [Review question]

Inclusion criteria:
[Inclusion criteria]

Exclusion criteria:
[Exclusion criteria]

Required:
Part one: the screening guide
1. Turn the criteria into yes/no/unclear questions in a logical order (the quickest reason for exclusion first).
2. For each question: a clear inclusion example, a clear exclusion example, and a borderline case with the suggested decision.
3. A standard list of exclusion reasons for the full-text stage (for the PRISMA report).

Part two (if I provide abstracts): pilot screening
[Abstracts for pilot screening]
For each abstract: the decision (include/exclude/unclear), the question that settled it, and a short quote that justifies it.

Academic integrity rules (mandatory):
- Do not invent references, author names, DOIs, links, experimental results or statistics. Where a source is needed, write [source needed].
- Do not claim to have read a study or file whose text I have not given you.
- Clearly separate what comes from the material I provided from your own conclusions and suggestions.
- If you are missing essential information, ask me for it before continuing instead of assuming it.
- Pilot screening is for calibration only; the final decision belongs to two human reviewers.

Write the answer in [Answer language].

Customise the prompt

Fill in only what suits you. The line of an empty optional field is removed from the final text, and empty required fields stay in brackets for you to complete later.

Optional; if left empty, only the guide is built.

Preview of the customised prompt

You are a methodologist specialising in systematic reviews in [Specific field].

Review question: [Review question]

Inclusion criteria:
[Inclusion criteria]

Exclusion criteria:
[Exclusion criteria]

Required:
Part one: the screening guide
1. Turn the criteria into yes/no/unclear questions in a logical order (the quickest reason for exclusion first).
2. For each question: a clear inclusion example, a clear exclusion example, and a borderline case with the suggested decision.
3. A standard list of exclusion reasons for the full-text stage (for the PRISMA report).

Part two (if I provide abstracts): pilot screening
[Abstracts for pilot screening]
For each abstract: the decision (include/exclude/unclear), the question that settled it, and a short quote that justifies it.

Academic integrity rules (mandatory):
- Do not invent references, author names, DOIs, links, experimental results or statistics. Where a source is needed, write [source needed].
- Do not claim to have read a study or file whose text I have not given you.
- Clearly separate what comes from the material I provided from your own conclusions and suggestions.
- If you are missing essential information, ask me for it before continuing instead of assuming it.
- Pilot screening is for calibration only; the final decision belongs to two human reviewers.

Write the answer in [Answer language].

Variables you can customise

[Specific field]
Required
[Review question]
Required
[Inclusion criteria]
Required
[Exclusion criteria]
Required
[Abstracts for pilot screening]
Optional
[Answer language]
Optional, choose from: Arabic, English, Arabic with English terms in parentheses, default value: Arabic with English terms in parentheses

Usage example

Example input

A question on the effectiveness of mobile apps in controlling type 2 diabetes, with PICO criteria and 15 abstracts.

Expected output

A screening guide with sequential questions and borderline examples, a list of exclusion reasons, and justified pilot screening decisions.

How to use it

  • Upload the guide to Rayyan or Covidence as instructions for the team.
  • Calculate the agreement between reviewers (Cohen's kappa) after the pilot batch.

Tips for better results

  • Reword the question that produces many "unclear" answers.

Limitations and warnings

  • Using models for final screening is not accepted by many journals without human verification and disclosure.

Suggested tools for using this prompt

Tools from the directory of research and academic publishing tools that are actually linked to this prompt's task, with the reason each tool is suggested.

Rayyan

Tool: Primary Free with usage limits

An AI-supported platform for managing systematic reviews: screening studies, removing duplicates and extracting data.

Research function: Organising the stages of a systematic review and screening titles and abstracts with the help of AI predictions.

Why it is suggested: For blinded collaborative screening and recording exclusion reasons.

Covidence

Tool: Primary Paid with a free trial

A web platform for running systematic reviews: importing studies, dual screening, data extraction and quality assessment.

Research function: Managing every step of a systematic review, from import to the PRISMA diagram.

Why it is suggested: To manage both screening stages and resolve disagreements between reviewers.

ASReview

Tool: Supporting Free

Open-source software that uses active learning to speed up title and abstract screening in systematic reviews.

Research function: Ranking records by how likely they are to be relevant while you screen, so the reviewer reaches the important studies sooner.

Why it is suggested: An open-source tool that uses active learning to rank records by likely relevance during screening.

In research workflows

Ratings

Not rated yet
Rate this prompt

One rating per visitor per prompt; submitting again updates your earlier rating. Comments appear after review.

Similar prompts