Design a PRISMA systematic review search strategy

Produces a PRISMA-style search strategy: databases with justifications, database-specific search strings, eligibility criteria, a screening process and a blank flow diagram.

PLPromptByte Library@promptbytePublished Jul 27

TextResearch #literature search #prisma #research #systematic review

Version 1 of 1 · published Jul 27, 2026Version 1 · only version

Example output

See all results

Google · Gemini 3.1 Pro 3.1 (Preview)PLPromptByte Library Version 1

Prompt

Version 1 · 2 variables · 1 required

Fill in the values below — the customized prompt updates as you type. marks a required value.

Research topic{{research_topic}}

The review question, ideally already in PICO-ish shape, e.g. "digital CBT for insomnia in adults".

Databases(optional){{databases}}

Name the databases you have access to, or leave the default and let the model propose and justify a set. Default: the databases most appropriate for this field

Fill in Research topic to copy the customized prompt.

Resultsfor version 1

All models Gemini 3.1 Pro1

Version 1 · only version

Gemini 3.1 Pro result by PromptByte Library
Google · Gemini 3.1 Pro 3.1 (Preview)PLPromptByte Library (@promptbyte)Version 1Published Jul 27
Compare
1. Databases - MEDLINE (Ovid) - core clinical trials of behavioural sleep interventions. - Embase - broader European trial coverage and conference abstracts. - PsycINFO - CBT-I trials indexed by psychological rather than medical terms. - CENTRAL - trial registry records and Cochrane-indexed RCTs. - Web of Science - citation chaining from included studies. - Grey literature: ClinicalTrials.gov, ISRCTN, plus reference lists of included trials. 2. Search string (MEDLINE/Ovid syntax) 1. exp Sleep Initiation and Maintenance Disorders/ 2. (insomnia or sleeplessness or "sleep disturbance").ti,ab.…
Community submittedFull output
Settings: Unknown
Open result

Showing all 1 public result on version 1.

Usage notes

This writes a protocol, not results. Everything it produces is a starting draft that you then run, count and correct — which is why the prompt forbids it from reporting hit numbers or naming studies it has not retrieved.

Before you run anything, check each controlled-vocabulary term against the database's own thesaurus. MeSH and Emtree headings drift, models half-remember them, and one wrong heading silently removes a chunk of the literature. Run the free-text half and the controlled half separately at first so you can see what each contributes.

Use it early, when you are scoping: it is a fast way to see whether your question is answerable, whether your eligibility criteria are actually operational, and where the grey literature sits. Then register the finished protocol (PROSPERO for health topics) before screening, so your criteria are fixed in advance rather than after you have seen the results.

A librarian still beats this for anything you intend to publish. Treat the output as the draft you take to that conversation.

Attribution: adapted from https://github.com/BevalZ/awesome-prompt-for-academic by BevalZ, licensed MIT. Source file: https://github.com/BevalZ/awesome-prompt-for-academic/blob/main/Prompts/EN/general.md

Models represented

Output2,051 characters

1. Databases - MEDLINE (Ovid) - core clinical trials of behavioural sleep interventions. - Embase - broader European trial coverage and conference abstracts. - PsycINFO - CBT-I trials indexed by psychological rather than medical terms. - CENTRAL - trial registry records and Cochrane-indexed RCTs. - Web of Science - citation chaining from included studies. - Grey literature: ClinicalTrials.gov, ISRCTN, plus reference lists of included trials. 2. Search string (MEDLINE/Ovid syntax) 1. exp Sleep Initiation and Maintenance Disorders/ 2. (insomnia or sleeplessness or "sleep disturbance").ti,ab. 3. 1 or 2 4. exp Cognitive Behavioral Therapy/ 5. (CBT-I or "cognitive behavioural therapy" or "cognitive behavioral therapy").ti,ab. 6. 4 or 5 7. (digital or online or internet or app or smartphone or web-based or eHealth or mHealth).ti,ab. 8. 3 and 6 and 7 9. limit 8 to (english language and adult) Translate lines 1 and 4 to Emtree for Embase and APA thesaurus terms for PsycINFO; keep free-text lines identical so the strings stay comparable. Verify both headings against the current thesaurus before running. 3. Eligibility criteria - Population: adults 18+ meeting insomnia criteria; exclude paediatric samples. - Intervention: digitally delivered CBT-I with at least two core components. - Comparator: waitlist, treatment as usual, or face-to-face CBT-I. - Outcomes: primary, Insomnia Severity Index; secondary, sleep-diary efficiency. - Design: randomised controlled trials only. - Dates and language: from database inception; English only, noted as a limitation. 4. Screening Two reviewers screen titles and abstracts independently, then full texts; disagreements go to a third reviewer. De-duplicate before screening and record the number removed. 5. PRISMA flow diagram (fill in your own counts) Records identified: databases (n = __), registers (n = __) Duplicates removed (n = __) Records screened (n = __) -> excluded (n = __) Full texts assessed (n = __) -> excluded, with reasons (n = __) Studies included in synthesis (n = __)

Design a PRISMA systematic review search strategy

Example output

Prompt

Resultsfor version 1

Something wrong with this prompt?

Plan a point-by-point response to manuscript reviewers

Turn study findings into a research-poster content plan

Map conflicting terminology across research disciplines

Audit in-text citations against the reference list

Create a repeatable observational data-collection protocol

Draft a qualitative codebook from anonymized excerpts

Discussion 0

Example output

Prompt

Resultsfor version 1

Something wrong with this prompt?

Related prompts

Plan a point-by-point response to manuscript reviewers

Turn study findings into a research-poster content plan

Map conflicting terminology across research disciplines

Audit in-text citations against the reference list

Create a repeatable observational data-collection protocol

Draft a qualitative codebook from anonymized excerpts

Discussion 0