meta-analysis

Meta-Analysis Skill

You are helping a medical researcher conduct a systematic review and meta-analysis. You support the full pipeline from protocol development to submission-ready manuscript, with specialized support for diagnostic test accuracy (DTA) meta-analyses.

Communication Rules

• Communicate with the user in their preferred language.
• All output documents, code, and checklists in English.
• Medical terminology always in English.

Reference Files

Built-in References (${CLAUDE_SKILL_DIR}/references/)

• PROSPERO template: ${CLAUDE_SKILL_DIR}/references/PROSPERO_template.md -- field-by-field guide with word limits, pitfalls checklist
• ICMJE COI guide: ${CLAUDE_SKILL_DIR}/references/icmje_coi_guide.md -- batch generation, python-docx pitfalls, form structure
• R templates: ${CLAUDE_SKILL_DIR}/references/r_templates.md
• Checklists: ${CLAUDE_SKILL_DIR}/references/checklists/
• PRISMA_DTA.md -- 27-item checklist
• QUADAS2.md -- 4 domains + signalling questions
• ROBINS_I.md -- 7 domains + pre-assessment + synthesis recommendation
• RoB2.md -- 5 domains + signalling questions + overall judgment
• PROBAST.md -- 4 domains + AI extension + validation studies
• NOS.md -- Cohort (8 items) + Case-control (8 items) + star interpretation
• JBI_Case_Series.md -- 10-item critical appraisal checklist for case series
• Phase 9 Co-author Circulation: ${CLAUDE_SKILL_DIR}/references/phase9_circulation.md -- thread continuity, attachment scope, recipient structure, 7-day window
• Phase 10 Self-Audit Recovery: ${CLAUDE_SKILL_DIR}/references/phase10_recovery.md -- trigger conditions, 12-step rebuild sprint, PROSPERO amendment, re-circulation framing
• Data integrity checklist: ${CLAUDE_SKILL_DIR}/references/data_integrity_checklist.md -- DI-1~DI-9 extraction/synthesis guardrails (prior anonymized MA projects)
• Review orchestration: ${CLAUDE_SKILL_DIR}/references/review_orchestration.md -- RO-1~RO-5 circulation discipline (extends phase9_circulation.md)
• Submission package drift: ${CLAUDE_SKILL_DIR}/references/submission_package_drift.md -- multi-journal folder hygiene, DO_NOT_EDIT_HERE gate, _build.sh pattern
• Post-submission release ops: ${CLAUDE_SKILL_DIR}/references/post_submission_release_ops.md -- Zenodo DOI gating, tag-cleanup gates, reject-retarget versioning

Built-in Templates (${CLAUDE_SKILL_DIR}/templates/)

• Extraction Form v2 (templates/extraction_form_v2.md) -- dual-extractor schema with source_page_ref, source_verbatim_quote, cohort_source, overlap_flag_reviewer1/2, sample_n_dta_pool vs sample_n_prognostic_pool columns. Required for SR-MA targeting high-impact radiology / medical AI journals.
• Supplementary 8-file Checklist (templates/supplementary_8file_checklist.md) -- S1-S8 mandatory package (PRISMA, PROSPERO, search strategy, exclusion list, extraction table, per-study x per-domain RoB, subgroup forests, sensitivity / publication bias) with a submission-gate bash check.

Meta-Analysis Types

| Type | RoB Tool | Statistical Model | Reporting Guideline | |------|----------|-------------------|-------------------| | DTA (diagnostic test accuracy) | QUADAS-2 | Bivariate / HSROC | PRISMA-DTA | | Intervention (treatment effect) | RoB 2 (RCT) / ROBINS-I (NRSI) | Random-effects (DL/REML) | PRISMA 2020 | | Prognostic (prediction model) | QUIPS / PROBAST | Random-effects | PRISMA 2020 | | Observational (prevalence/association) | NOS / JBI | Random-effects | MOOSE |

Auto-detect type from the research question or accept user specification.

Workflow Phases

Phase 1: Protocol Development

Goal: Produce a PROSPERO-ready protocol document.

1. Structure the research question:
2. DTA: PIRD (Population, Index test, Reference standard, Diagnosis)
3. Intervention: PICO (Population, Intervention, Comparator, Outcome)

1. Define eligibility criteria:
2. Study design (cross-sectional DTA, cohort, RCT, etc.)
3. Population characteristics
4. Index test / intervention specifics
5. Comparator / reference standard
6. Outcome measures (Se/Sp for DTA; effect size for intervention)
7. Exclusion criteria with justification

1. Plan the search:
2. Minimum 3 databases: PubMed, Embase, and Cochrane CENTRAL (add Scopus, Web of Science as needed)
3. Draft Boolean search strategy using PIRD/PICO components
4. Grey literature plan (conference abstracts, trial registries)
5. Language restrictions (state explicitly)
6. Date range with justification

1. Plan RoB assessment:
2. Select tool based on type (see table above)
3. State number of independent assessors (minimum 2)
4. Plan for disagreement resolution (consensus, third reviewer)

1. Plan synthesis:
2. DTA: bivariate random-effects model (Reitsma) or HSROC (Rutter & Gatsonis)
3. Intervention: random-effects (DerSimonian-Laird or REML)
4. Heterogeneity assessment plan
5. Subgroup / sensitivity analysis plan
6. Publication bias assessment plan

1. Generate PROSPERO registration document:
2. Read ${CLAUDE_SKILL_DIR}/references/PROSPERO_template.md for field-by-field guidance
3. Generate all fields with word counts (stay within limits per field)
4. Structure: title, review question, PICO, searches, data collection, outcomes, synthesis, subgroups, stage, affiliation
5. For mixed designs (comparative + single-arm): explicitly address comparator for both arms
6. For RoB: map tool to study design (NOS for comparative, JBI for case series → select "Other" in form)
7. Output: Markdown + DOCX (via pandoc) for copy-paste into PROSPERO web form
8. Append Common Pitfalls Checklist (HTML entities, word limits, stage constraint)
9. Save to project 7_Submission/ or equivalent directory

Phase 2: Search Strategy

Goal: Develop and validate reproducible search strategies.

1. Build search blocks from PIRD/PICO:
2. Population block (MeSH + free text)
3. Index test / Intervention block
4. Comparator / Reference standard block (optional)
5. Study design filter (if applicable)

1. Combine with Boolean operators:
2. Within blocks: OR
3. Between blocks: AND

1. Execute search per database using /search-lit:
2. PubMed: MeSH + free text
3. Embase: Emtree + free text
4. Additional databases as specified in protocol

1. Report search per PRISMA-S (Rethlefsen et al. 2021, PMID:33499930):

Save search strategies as a structured document, one section per database, with date of search, number of results, and any limits applied.

1. Merge and deduplicate: Combine all database results into a single spreadsheet.

Deduplicate by DOI first, then PMID. Save raw counts for PRISMA flow.

Phase 3: Screening & Selection

Goal: Systematic title/abstract and full-text screening with two independent reviewers.

3a. Round 1 — Initial Title/Abstract Screening (single reviewer)

1. Define exclusion codes from protocol (e.g., E1=Not target population, E2=Not intervention, E3=Ineligible type, E4=Non-human, E5=Duplicate).
2. For each record, screen title+abstract against eligibility criteria.
3. Mark each record as INCLUDE / EXCLUDE / MAYBE with reason code.
4. Output: round1_{date}.tsv with color-coded decisions.

3b. Round 2 — Dual Independent Title/Abstract Screening

1. A second independent reviewer (or AI as a documented second-pass tool with human verification) re-screens all R1 records.
2. Compute Cohen's kappa at title/abstract stage; report in Methods.
3. Tag each record's round2_tag as INCLUDE / EXCLUDE / MAYBE based on R1+R2 agreement (MAYBE = disagreement OR either reviewer flagged uncertain).
4. Output: round2_{date}.tsv (adds round2_tag, round2_reason columns).

3c. Round 3 — Adjudication of Disagreements (first reviewer)

1. Build R3 sheet: all MAYBE records first, followed by INCLUDE records (which receive a brief