# mode: review discipline: medicine title: ""

# Research brief — (review)

# 1. Research objective and scope

• Review question.
• Type. <systematic | scoping | narrative/critical>.
• Scope. <years, languages, study designs, populations, outcomes>.

# 2. Domain, mode and methodology

• Discipline: <…>. Primary mode: review. Reporting standard: <PRISMA 2020 / PRISMA-ScR / narrative with explicit protocol>.

# 3. Contribution and novelty

• <Why a new synthesis is needed; existing reviews to compare with (cite).>

# 4. Search protocol and source rules

• Databases: <PubMed, OpenAlex, Crossref, Semantic Scholar, arXiv>. Search strings: . Date of search recorded.
• Inclusion/exclusion criteria: <…>. Screening: title/abstract then full text (open-access when available); record every decision with a reason in data/screening.csv.
• Every included study added through the verification tool (DOI/PMID); target ≥ 25 verified sources.

# 5. Evidence extraction

• Data items: <design, sample, intervention/exposure, outcomes, effect sizes, risk-of-bias items>. Store in results/extraction.csv.
• Quality/risk-of-bias assessment: .

# 6. Procedure

1. Run searches; export hit counts per database (data/manifest.json describes the screening records).
2. Screen; extract; assess quality.
3. Synthesize: <narrative synthesis / vote counting / meta-analysis if ≥ k comparable studies — with heterogeneity and small-study checks>.
4. Produce the flow diagram (counts), evidence tables and summary figures.

# 7. Robustness and falsification

• Re-run searches with alternative terms; re-screen a random 10% sample for consistency; sensitivity analyses excluding low-quality studies.

# 8. Reproducibility and artifacts

• Search strings, dates, counts, screening and extraction files, synthesis scripts (code/), results/synthesis.md.

# 9. Manuscript

• AutoScholar class; methods section reproducing the protocol; evidence tables; limitations of the evidence base; 10–25 pages.

# 10. Review and revision

• Reviewer focus: search completeness, selection bias, extraction errors, overgeneralized conclusions.

# 11. Limitations, ethics, legal

• Metadata and abstracts only where full texts are paywalled; no republication of copyrighted text beyond short quotes. Medical conclusions are not clinical advice.

# 12. Acceptance criteria

• Protocol executed as written; counts reported; ≥ 25 verified sources; extraction table complete; synthesis consistent with the extracted data.