Purpose of the prompt
The prompt combines the two most important stages after screening: standardised data extraction, and assessing study quality or risk of bias with a recognised tool, linking each judgement to text from the study.
When to use it?
After full-text screening is finished, and when piloting the extraction form on two or three studies.
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 an expert in systematic reviews and study quality assessment in [Specific field]. Type of included studies: [Type of studies] Outcomes I need for the synthesis: [Required outcomes] Part one: design a data extraction form with grouped fields: (study information, participants or data, intervention or model, comparator, outcomes and how they were measured, numerical results needed for pooling, funding and conflicts of interest). Specify the type and allowed values of each field. Part two: suggest the most suitable risk of bias tool for the type of studies, with justification, and list its domains. Part three (if I provide the text of a study): <study> [Text of a study to test on] </study> - Fill in the form from the text only, and write "not reported" for anything missing. - Apply the tool's domains: the judgement (low/high/some concerns or unclear) with a quote as evidence. 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. - The risk of bias judgements here are a draft; they must be made by two independent reviewers. Write the answer in [Answer language].You are an expert in systematic reviews and study quality assessment in [Specific field]. Type of included studies: [Type of studies] Outcomes I need for the synthesis: [Required outcomes] Part one: design a data extraction form with grouped fields: (study information, participants or data, intervention or model, comparator, outcomes and how they were measured, numerical results needed for pooling, funding and conflicts of interest). Specify the type and allowed values of each field. Part two: suggest the most suitable risk of bias tool for the type of studies, with justification, and list its domains. Part three (if I provide the text of a study): <study> [Text of a study to test on] </study> - Fill in the form from the text only, and write "not reported" for anything missing. - Apply the tool's domains: the judgement (low/high/some concerns or unclear) with a quote as evidence. 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. - The risk of bias judgements here are a draft; they must be made by two independent reviewers. Write the answer in [Answer language]. You are an expert in systematic reviews and study quality assessment in {{field}}. Type of included studies: {{design}} Outcomes I need for the synthesis: {{outcomes}} Part one: design a data extraction form with grouped fields: (study information, participants or data, intervention or model, comparator, outcomes and how they were measured, numerical results needed for pooling, funding and conflicts of interest). Specify the type and allowed values of each field. Part two: suggest the most suitable risk of bias tool for the type of studies, with justification, and list its domains. Part three (if I provide the text of a study): <study> {{study}} </study> - Fill in the form from the text only, and write "not reported" for anything missing. - Apply the tool's domains: the judgement (low/high/some concerns or unclear) with a quote as evidence. 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. - The risk of bias judgements here are a draft; they must be made by two independent reviewers. Write the answer in {{lang}}.
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.
Preview of the customised prompt
You are an expert in systematic reviews and study quality assessment in [Specific field]. Type of included studies: [Type of studies] Outcomes I need for the synthesis: [Required outcomes] Part one: design a data extraction form with grouped fields: (study information, participants or data, intervention or model, comparator, outcomes and how they were measured, numerical results needed for pooling, funding and conflicts of interest). Specify the type and allowed values of each field. Part two: suggest the most suitable risk of bias tool for the type of studies, with justification, and list its domains. Part three (if I provide the text of a study): <study> [Text of a study to test on] </study> - Fill in the form from the text only, and write "not reported" for anything missing. - Apply the tool's domains: the judgement (low/high/some concerns or unclear) with a quote as evidence. 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. - The risk of bias judgements here are a draft; they must be made by two independent reviewers. Write the answer in [Answer language].
Variables you can customise
- [Specific field]
- Required
- [Type of studies]
- Optional, choose from: Randomised controlled trials, Observational studies, Diagnostic accuracy studies, Prediction model or machine learning studies, Qualitative studies, Mixed, default value: Randomised controlled trials
- [Required outcomes]
- Optional
- [Text of a study to test on]
- 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
Expected output
How to use it
- Test the form on 2 to 3 studies and adjust the fields before adopting it.
- Move the form into Covidence or a shared spreadsheet.
Tips for better results
- For machine learning studies, ask for a specific check for data leakage and external validation.
Limitations and warnings
- Models can make mistakes when copying exact figures; double human extraction is essential.
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.
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: Supports extraction forms and quality assessment with independent reviewers.
An AI research assistant that searches scientific papers semantically, extracts data from them and produces research reports with sources.
Research function: Semantic search of scientific papers, summarising them and extracting information into organised tables.
Why it is suggested: For a first extraction of specific fields from papers, followed by human checking.
SciSpace
Tool: OptionalAn AI research platform: literature reviews across more than 280 million papers, chat with PDF files and a writing assistant.
Research function: Searching the literature, explaining papers, extracting data from them and helping with writing, with the sources cited.
Why it is suggested: To read the methods sections and ask clarifying questions about them.
In research workflows
Similar prompts
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.
Writing Results and Synthesis per PRISMA 2020
Writes the results section of a systematic review from your actual figures: the flow diagram, study characteristics, risk of bias and synthesis, and checks which PRISMA items are missing.
Drafting a Systematic Review Protocol (PRISMA-P)
Builds a draft systematic review protocol with the PRISMA-P items: the question in a PICO (or alternative) framework, eligibility criteria, sources, screening, extraction, risk assessment and synthesis.
بناء معادلة بحث لقواعد متعددة
أنشئ استراتيجية بحث قابلة للتكييف مع Scopus وPubMed وWeb of Science، مع مرادفات وحقول.
