Back to Details

evidence-synthesis

Compare original and translation side by side

🇺🇸

Original

English
🇨🇳

Translation

Chinese

Evidence Synthesis

证据合成

Rapid evidence assessment without shortcuts that collapse confidence. Every finding carries a source and a confidence grade. Gaps are named, not hidden.
严谨开展快速证据评估，绝不因追求速度而降低可信度。每项研究结果均附带来源及可信度评级。明确指出研究空白，而非刻意隐瞒。

When to use

适用场景

Trigger for evidence review work: programme design questions, evaluation framing, policy briefs, funder questions about what works, contribution analysis needing prior-evidence assembly.
Do not trigger for news scans, stakeholder mapping, or quick factual lookups. Those are different tasks.
触发证据综述工作的场景：项目设计问题、评估框架制定、政策简报撰写、资助方关于有效措施的疑问、需要整合已有证据的贡献分析。
请勿用于新闻扫描、利益相关者映射或快速事实查询，这些属于不同任务范畴。

Required inputs

必要输入

Ask in one batch. The first two are required.
  1. Question: what Ane needs the evidence to answer, as a specific question (required)
  2. Purpose: programme design, evaluation framing, policy advocacy, donor response, academic input (required; shapes depth and format)
  3. Scope constraints: geography, population, intervention type, time range (optional; will default if missing)
  4. Sources Ane trusts or distrusts: organisations, journals, or author groups to prioritise or treat cautiously (optional)
  5. Timeline: how much time Ane has — determines whether rapid (2 hours), standard (1-2 days), or rigorous (1-2 weeks) synthesis (default: rapid)
请一次性提供以下信息，前两项为必填项：
  1. 问题：Ane需要证据解答的具体问题（必填）
  2. 用途：项目设计、评估框架制定、政策倡导、资助方响应、学术研究输入（必填；决定研究深度和格式）
  3. 范围限制：地域、人群、干预类型、时间范围（可选；若未提供则使用默认值）
  4. Ane信任或不信任的来源：优先采用或需谨慎对待的机构、期刊或作者群体（可选）
  5. 时间线：Ane可用的时间——决定采用快速（2小时）、标准（1-2天）还是严谨（1-2周）的合成方式（默认：快速）

Method

方法步骤

Step 1 — frame the question

步骤1——构建问题框架

Use the framework that fits:
  • PICO for intervention-effectiveness questions: Population, Intervention, Comparison, Outcome
  • SPIDER for qualitative or mixed-method questions: Sample, Phenomenon of Interest, Design, Evaluation, Research type
  • SPICE for service evaluation questions: Setting, Perspective, Intervention, Comparison, Evaluation
Show the frame explicitly before searching.
选用适配的框架：
  • PICO框架：适用于干预效果类问题，包含人群（Population）、干预措施（Intervention）、对照（Comparison）、结果（Outcome）
  • SPIDER框架：适用于定性或混合方法类问题，包含样本（Sample）、研究现象（Phenomenon of Interest）、研究设计（Design）、评估（Evaluation）、研究类型（Research type）
  • SPICE框架：适用于服务评估类问题，包含场景（Setting）、视角（Perspective）、干预措施（Intervention）、对照（Comparison）、评估（Evaluation）
在开展搜索前，需明确展示所使用的框架。

Step 2 — define inclusion and exclusion criteria

步骤2——确定纳入与排除标准

For rapid synthesis: minimum criteria are population, intervention or phenomenon, outcome, timeframe (default last 10 years), language, study type.
State each criterion. Explain any exclusion decision that would surprise a peer reviewer.
对于快速合成：最低标准需涵盖人群、干预措施或研究现象、结果、时间范围（默认近10年）、语言、研究类型。
明确列出每项标准。若排除决定可能会让同行评审者感到意外，需做出解释。

Step 3 — select synthesis approach

步骤3——选择合成方法

Choose one, name the choice:
  • Thematic synthesis: when findings group into recurring themes (Thomas & Harden 2008)
  • Narrative synthesis: when studies are too heterogeneous to pool but a structured summary is needed (Popay et al. 2006)
  • Realist synthesis: when the question is "what works, for whom, in what circumstances, and why" (Pawson et al. 2005)
  • Meta-analysis: only when effect sizes from comparable quantitative studies can be pooled. Usually out of scope for rapid work.
选择一种方法并明确说明：
  • 主题合成法：当研究结果可归类为重复出现的主题时使用（Thomas & Harden 2008）
  • 叙事合成法：当研究异质性过高无法合并，但需要结构化总结时使用（Popay et al. 2006）
  • 现实主义合成法：当问题为“什么措施有效、对谁有效、在何种情况下有效以及为何有效”时使用（Pawson et al. 2005）
  • 元分析：仅当可合并同类定量研究的效应量时使用。通常超出快速研究的范畴。

Step 4 — search and screen

步骤4——搜索与筛选

If Ane provides sources, use them. If not, ask where to search:
  • Grey literature: WHO, UNFPA, UNAIDS, IPPF, Cochrane, 3ie, relevant IGOs
  • Academic: PubMed, Scopus, Global Health Database, Cochrane
  • Ane's resource library: 
    3. Ane's RESURSE/
    subfolders matching the topic
Never invent citations. If a search cannot be conducted in this session, ask Ane to paste the top sources or point to the library subfolder.
若Ane提供了来源，则使用这些来源；若未提供，则询问搜索渠道：
  • 灰色文献：WHO、UNFPA、UNAIDS、IPPF、Cochrane、3ie、相关政府间组织（IGOs）
  • 学术文献：PubMed、Scopus、Global Health Database、Cochrane
  • Ane的资源库：与主题匹配的
    3. Ane's RESURSE/
    子文件夹
不得编造引用文献。若无法在本次会话中开展搜索，请让Ane粘贴核心来源或指明资源库子文件夹位置。

Step 5 — extract findings

步骤5——提取研究结果

For each source, extract:
  • Full citation (author, year, title, journal or publisher, DOI if available)
  • Setting and population
  • Intervention or phenomenon studied
  • Key finding, in the source's own framing
  • Study design and sample size
  • Confidence flags: low sample, non-random, self-report, author conflicts, funder bias
针对每个来源，提取以下信息：
  • 完整引用信息（作者、年份、标题、期刊或出版社、DOI（若有））
  • 研究场景与人群
  • 研究的干预措施或现象
  • 核心研究结果（采用来源原文表述）
  • 研究设计与样本量
  • 可信度警示：样本量小、非随机抽样、自我报告、作者利益冲突、资助方偏见

Step 6 — grade confidence

步骤6——可信度评级

For each finding or theme, grade using a GRADE-adjacent scheme:
  • High: consistent findings across multiple rigorous studies; mechanism understood
  • Moderate: consistent findings but with methodological limitations or narrow context
  • Low: few studies, or conflicting findings, or serious bias risk
  • Very low: single source or methodologically weak studies only
Explain the grade in one clause. No inflation.
针对每项研究结果或主题，采用近似GRADE的体系进行评级：
  • 高可信度：多项严谨研究得出一致结果；作用机制明确
  • 中等可信度：结果一致，但存在方法学局限性或适用范围较窄
  • 低可信度：研究数量少，或结果存在冲突，或存在严重偏倚风险
  • 极低可信度：仅单一来源或方法学薄弱的研究
用一句话解释评级理由，不得夸大评级。

Step 7 — apply the relevant lenses

步骤7——应用相关视角

For SRHR or gender-related questions, apply:
  • Feminist lens: whose voices shaped the research questions? Are women and girls subjects of the research or objects? Cornwall & Rivas (2015) framing.
  • Decolonial lens: where was the research conducted, who funded it, whose knowledge is centred? Chilisa (2020).
  • Intersectionality: does the evidence disaggregate to current standard (age, gender identity, disability, geography)? Flag when it does not.
针对SRHR或性别相关问题，应用以下视角：
  • 女性主义视角：谁的声音主导了研究问题的设定？女性和女孩是研究的主体还是客体？采用Cornwall & Rivas (2015)的框架。
  • 去殖民视角：研究在何处开展？由谁资助？以谁的知识为核心？参考Chilisa (2020)的观点。
  • 交叉性视角：证据是否按当前标准（年龄、性别认同、残疾状况、地域）进行分类？若未分类需予以标注。

Step 8 — identify gaps

步骤8——识别研究空白

Name what the evidence does not answer. Use 
⚠️ Evidence gap:
format. Distinguish:
  • Gaps in research (the study has not been done)
  • Gaps in context (research exists but not from relevant settings)
  • Gaps in population (research exists but excludes the target group)
  • Gaps in method (research exists but with weak designs only)
明确指出证据未解答的问题。采用
⚠️ 证据空白:
格式区分：
  • 研究空白（相关研究尚未开展）
  • 场景空白（已有研究但未覆盖相关场景）
  • 人群空白（已有研究但未纳入目标群体）
  • 方法空白（已有研究但仅采用薄弱的研究设计）

Output structure

输出结构

Produce an evidence brief with these sections:
  1. Question — as framed in Step 1, with the framework named
  2. Method — inclusion criteria, search approach, synthesis approach, limitations of the rapid format
  3. Key findings — organised by theme. Each finding:
    • One-sentence statement
    • Confidence grade
    • Supporting sources (author year)
  4. Lens observations — feminist, decolonial, intersectional notes
  5. Implications — what this means for the stated purpose (programme design, evaluation, etc.). Be concrete.
  6. Evidence gaps — 
    ⚠️ Evidence gap:
    entries
  7. Sources — full citations, alphabetical by first author
产出包含以下章节的证据简报：
  1. 问题——采用步骤1构建的框架，并注明所使用的框架名称
  2. 方法——纳入标准、搜索方法、合成方法、快速评估格式的局限性
  3. 核心研究结果——按主题分类。每项结果包含：
    • 一句话陈述
    • 可信度评级
    • 支持来源（作者 年份）
  4. 视角观察——女性主义、去殖民、交叉性视角的相关说明
  5. 启示——对既定用途（项目设计、评估等）的具体意义
  6. 证据空白——
    ⚠️ 证据空白:
    条目
  7. 来源——完整引用信息，按第一作者姓氏字母顺序排列

Citation requirements

引用要求

Every finding cites at least one source. Method references:
  • Thomas & Harden (2008) for thematic synthesis
  • Popay et al. (2006) for narrative synthesis
  • Pawson et al. (2005) for realist synthesis
  • GRADE Working Group for confidence grading
For SRHR-specific framings:
  • Cornwall & Rivas (2015), Chilisa (2020) for lenses
  • WHO/UNFPA (2023), UNFPA HRBAP for rights-based framing
每项研究结果至少引用一个来源。方法相关引用：
  • 主题合成法引用Thomas & Harden (2008)
  • 叙事合成法引用Popay et al. (2006)
  • 现实主义合成法引用Pawson et al. (2005)
  • 可信度评级引用GRADE Working Group
针对SRHR特定框架的引用：
  • 视角相关引用Cornwall & Rivas (2015)、Chilisa (2020)
  • 基于权利的框架引用WHO/UNFPA (2023)、UNFPA HRBAP

Writing rules

写作规则

Follow CLAUDE.md house style. In this skill specifically:
  • Never summarise a finding in language stronger than the source supports.
  • Never present contested findings as settled.
  • Never use "evidence shows" without a specific citation.
  • Flag when a finding is contested, and by whom.
遵循CLAUDE.md的规范。针对本技能：
  • 不得使用比来源表述更绝对的语言总结研究结果
  • 不得将存在争议的结果表述为定论
  • 若无具体引用，不得使用“证据表明”
  • 若研究结果存在争议，需标注争议方

Limitations

局限性

Rapid syntheses are not systematic reviews. State this limitation in the Method section. Do not invent effect sizes or pool findings across incompatible studies. If Ane needs a systematic review, route to a proper review protocol (PRISMA) rather than inflating rapid-review scope.
快速合成并非系统综述。需在方法章节说明此局限性。不得编造效应量，也不得合并不兼容研究的结果。若Ane需要系统综述，应引导其采用标准综述协议（PRISMA），而非扩大快速综述的范围。