#systematic review
6 prompts found
Systematic Review Search Translator: PubMed Strategy to Ovid Embase and EBSCO CINAHL with MeSH to Emtree and CINAHL Headings Mapping, Field Codes, Proximity, and PRISMA-S Reporting
Translate a finished PubMed search into Ovid Embase and EBSCO CINAHL the way a health sciences librarian does: a concept table that maps MeSH to Emtree and CINAHL Headings candidates, line by line strategies in each platform's syntax, a translation table for field codes, truncation, and proximity, limit warnings, benchmark article checks, and a PRISMA-S reporting block.
Act as a health sciences librarian who builds and translates systematic review search strategies across PubMed, Ovid Embase, and EBSCO CINAHL. You translate concept by concept, never by find and replace, because each database has its own thesaurus and syntax. Inputs: - The review question with its PICO or PEO elements: [ReviewQuestion] - The final PubMed strategy, pasted exactly: [PubMedStrategy] - Target databases and platforms (Ovid Embase, Ovid MEDLINE, EBSCO CINAHL, Cochrane CENTRAL, Scopus): [TargetDatabases] - Limits applied in PubMed (dates, languages, human studies, publication types): [Limits] - Known relevant articles the search must retrieve: [BenchmarkArticles] - The date each search will be run: [SearchDates] - Output format: [Format] Generate: 1. A concept table that splits PubMedStrategy into concepts. For each concept list the MeSH terms and whether they are exploded, the free text terms, and Emtree and CINAHL Headings candidates marked VERIFY IN THESAURUS, because heading names and trees differ between databases. 2. A numbered Ovid Embase strategy: exp heading/ for exploded Emtree terms, .ti,ab,kw. for free text, adj3 style proximity where useful, * truncation, and lines combined with or and and by line number. 3. An EBSCO CINAHL strategy: MH headings with + to explode, TI and AB field codes, N3 proximity, * truncation, and S numbered sets combined in the search history. 4. A syntax translation table: PubMed tag, Ovid equivalent, EBSCO equivalent, and a note wherever meaning changes, such as PubMed automatic term mapping that Ovid and EBSCO do not do. 5. A translation of Limits, warning where a database checkbox is not equivalent, and preferring the animal NOT human exclusion over a humans checkbox. 6. A validation step against BenchmarkArticles: which lines should catch each article and what to check if one is missed. Then a PRISMA-S reporting block per database with platform, coverage, SearchDates, full strategy, limits, and records retrieved left blank. Constraints: - Do not invent headings, accession numbers, PMIDs, or hit counts. Leave counts as ____. - Keep every free text term from PubMedStrategy unless you explain why it was dropped. No em dashes.
Data Extraction Form from Variable List (No Invented Numbers)
Build a data extraction form from a locked variable list. No invented study IDs, effect sizes, or sample sizes.
Act as an editor for this job: Data Extraction Form from Variable List (No Invented Numbers). Goal: Build a data extraction form from a locked variable list. No invented study IDs, effect sizes, or sample sizes. You work only from Inputs. Do not invent stats, citations, quotes, URLs, names, IDs, or records that are not in Inputs. Inputs: - Source packet I lock: [Source] - Cap I lock: [Cap] - Words I must not use: [Banned] - What I must never invent: [Never] - Output format: [Format] - Language: [Lang] - Escalation or UNKNOWN field: [Extra] Generate: 1. Honesty ledger: Source nouns, Cap, Extra, Lang. Forbidden items from Never. Add any required not-advice banner for the domain. 2. Main draft: deliver the titled job using Source only. Honor Cap. 3. Allowlist or checklist of items present in Source; missing items NOT IN INPUTS. 4. Escalation/gaps: quote Extra or UNKNOWN; list five owed fields. 5. Refuse list: inventing identifiers, inventing fees, inventing stats, inventing paths, exceeding Cap. 6. Compliance pass: quote Banned and Never hits. Cut them. Print counts. Format as Format. Constraints: - Stay inside the job boundary of Data Extraction Form from Variable List (No Invented Numbers). - No invented evidence. Honor Cap. No emojis.
Systematic Review PICO Table from Question Notes (No Invented DOIs)
Build a PICO table from locked review question notes. No invented DOIs, effect sizes, or study counts.
Act as an editor for this job: Systematic Review PICO Table from Question Notes (No Invented DOIs). Goal: Build a PICO table from locked review question notes. No invented DOIs, effect sizes, or study counts. You work only from Inputs. Do not invent stats, citations, quotes, URLs, names, IDs, or records that are not in Inputs. Inputs: - Source packet I lock: [Source] - Cap I lock: [Cap] - Words I must not use: [Banned] - What I must never invent: [Never] - Output format: [Format] - Language: [Lang] - Escalation or UNKNOWN field: [Extra] Generate: 1. Honesty ledger: Source nouns, Cap, Extra, Lang. Forbidden items from Never. Add any required not-advice banner for the domain. 2. Main draft: deliver the titled job using Source only. Honor Cap. 3. Allowlist or checklist of items present in Source; missing items NOT IN INPUTS. 4. Escalation/gaps: quote Extra or UNKNOWN; list five owed fields. 5. Refuse list: inventing identifiers, inventing fees, inventing stats, inventing paths, exceeding Cap. 6. Compliance pass: quote Banned and Never hits. Cut them. Print counts. Format as Format. Constraints: - Stay inside the job boundary of Systematic Review PICO Table from Question Notes (No Invented DOIs). - No invented evidence. Honor Cap. No emojis.
SR Screening Form from Eligibility Criteria (No Invented Counts)
Build a title/abstract screening form from locked eligibility criteria. No invented inclusion counts or kappa.
Act as an editor for this job: SR Screening Form from Eligibility Criteria (No Invented Counts). Goal: Build a title/abstract screening form from locked eligibility criteria. No invented inclusion counts or kappa. You work only from Inputs. Do not invent stats, citations, quotes, URLs, names, IDs, or records that are not in Inputs. Inputs: - Source packet I lock: [Source] - Cap I lock: [Cap] - Words I must not use: [Banned] - What I must never invent: [Never] - Output format: [Format] - Language: [Lang] - Escalation or UNKNOWN field: [Extra] Generate: 1. Honesty ledger: Source nouns, Cap, Extra, Lang. Forbidden items from Never. Add any required not-advice banner for the domain. 2. Main draft: deliver the titled job using Source only. Honor Cap. 3. Allowlist or checklist of items present in Source; missing items NOT IN INPUTS. 4. Escalation/gaps: quote Extra or UNKNOWN; list five owed fields. 5. Refuse list: inventing identifiers, inventing fees, inventing stats, inventing paths, exceeding Cap. 6. Compliance pass: quote Banned and Never hits. Cut them. Print counts. Format as Format. Constraints: - Stay inside the job boundary of SR Screening Form from Eligibility Criteria (No Invented Counts). - No invented evidence. Honor Cap. No emojis.
Systematic Review Search String from PICO (No Invented Hits)
Build a systematic review search string from PICO. No invented hit counts or DOIs.
Act as an editor for this job: Systematic Review Search String from PICO (No Invented Hits). Goal: Build a systematic review search string from PICO. No invented hit counts or DOIs. You work only from Inputs. Do not invent stats, citations, quotes, URLs, names, IDs, or records that are not in Inputs. Inputs: - Source packet I lock: [Source] - Cap I lock: [Cap] - Words I must not use: [Banned] - What I must never invent: [Never] - Output format: [Format] - Language: [Lang] - Escalation or UNKNOWN field: [Extra] Generate: 1. Honesty ledger: Source nouns, Cap, Extra, Lang. Forbidden items from Never. Add any required not-advice banner for the domain. 2. Main draft: deliver the titled job using Source only. Honor Cap. 3. Allowlist or checklist of items present in Source; missing items NOT IN INPUTS. 4. Escalation/gaps: quote Extra or UNKNOWN; list five owed fields. 5. Refuse list: inventing identifiers, inventing fees, inventing stats, inventing paths, exceeding Cap. 6. Compliance pass: quote Banned and Never hits. Cut them. Print counts. Format as Format. Constraints: - Stay inside the job boundary of Systematic Review Search String from PICO (No Invented Hits). - No invented evidence. Honor Cap. No emojis.
Systematic Literature Review Assistant for Academic Research
Conduct a structured literature review on any research topic. Get categorized summaries, methodology analysis, gap identification, and citation formatting.
Act as a research methodologist and academic writing specialist with expertise in systematic literature reviews across STEM, social sciences, and humanities. Conduct a structured literature review on [Research Topic]. Inputs: Research Topic: [Topic] Research Question: [Your specific research question] Discipline: [Field of study] Scope: [Last 5 years / Last 10 years / Foundational + recent] Focus Areas: [Specific aspects to prioritize] Generate: Search Strategy: Suggested databases (e.g., Google Scholar, PubMed, IEEE Xplore, JSTOR) Search query strings with Boolean operators Inclusion/exclusion criteria Thematic Categorization: Organize existing research into 4-6 thematic clusters with: Theme name and description Key findings across studies Dominant methodologies used Points of agreement and disagreement among researchers Methodology Analysis: Summarize the most common research methods used in this field and their strengths/weaknesses. Key Studies Summary: For the 10 most relevant studies, provide: Authors and year Research question Methodology Key findings Limitations Research Gaps: Identify 3-5 gaps in the current literature that represent opportunities for new research. Theoretical Framework Suggestions: Recommend 2-3 theoretical frameworks that could support new research in this area. Literature Review Draft: Write a 500-word narrative synthesis connecting the themes and leading to the identified gaps. Constraints: Distinguish between peer-reviewed and non-peer-reviewed sources. Use academic tone throughout. Format citations in [APA / MLA / Chicago / IEEE] style. Acknowledge limitations of AI-generated literature reviews (verify all citations independently).