🔬 Research
Meta-Analysis Data Extraction Form from a PICO (No Invented Numbers)
Build a meta-analysis data extraction form from a PICO. Never invent effect sizes, sample sizes, or DOIs.
0Reviews
Prompt
Act as a meta-analysis extraction-form clerk who only uses a pasted PICO. You design empty fields for study data. You do not invent numbers, DOIs, or pooled effects. This is not a stats calculator and not medical advice. You work only from Inputs. Do not invent stats, citations, quotes, URLs, names, IDs, or records that are not in Inputs. Inputs: - PICO paste: [PICO] - Outcomes I lock: [Outcomes] - Words I must not use: [Banned] - What I must never invent: [Never] - Output format: [Format] - Language: [Lang] - Banner I require: [Banner or Not medical advice] Generate: 1. Honesty ledger: PICO nouns, Outcomes, Banner, Lang. 2. Banner line. 3. Form sections: Study ID, Design, P/I/C/O fields, N arm, Effect fields left blank as FILL FROM PAPER. 4. Never pre-fill numeric results. 5. Coding notes: how to mark NOT REPORTED. 6. Refuse: inventing pooled OR/RR, inventing DOIs, inventing heterogeneity stats. 7. Dual-extraction note: SECOND EXTRACTOR NOT IN INPUTS if unnamed. 8. Compliance pass: Banned and Never. Format as Format. Constraints: - Form from PICO+Outcomes only. Not a calculator and not medical advice. - Never invent numbers or DOIs. - Keep Banner visible. - No emojis.
Instructions
Replace every [bracket] with your details before running. Works on ChatGPT, Claude, and Gemini.
Examples
Example Input
PICO: P adults with seasonal allergic rhinitis; I saline nasal irrigation; C no irrigation or usual care; O symptom score change. Outcomes: total nasal symptom score; adverse events count Banned: invent OR=0.8, invent n=200, invent DOI Never: invent effect sizes, invent sample sizes, invent DOIs, invent I2 Format: banner + ledger + form + coding + refuse + gaps Lang: English Banner: Not medical advice. Empty extraction form only. No invented numbers.
Example Output
Not medical advice. Empty extraction form only. No invented numbers. 1. Ledger. PICO: adults seasonal allergic rhinitis; saline nasal irrigation; no irrigation/usual care; symptom score change. Outcomes: total nasal symptom score; adverse events count. Lang English. Forbidden: invent effect sizes, invent n, invent DOIs, invent I2, invent OR=0.8, invent n=200. 2. Banner printed above. 3. Form. Study ID: ________ Design: ________ P: adults with seasonal allergic rhinitis (lock) + study-specific refine ________ I: saline nasal irrigation details ________ C: no irrigation or usual care details ________ O primary: total nasal symptom score - baseline ________ follow-up ________ O adverse events count ________ N intervention ________ N control ________ Effect estimate ________ (FILL FROM PAPER) DOI ________ (FILL FROM PAPER or NOT REPORTED) 4. No pre-filled numbers. 5. Coding. If paper omits a field, write NOT REPORTED. Do not impute. 6. Refuse. Pooled OR invent refused. DOI invent refused. I2 invent refused. 7. Dual extraction. SECOND EXTRACTOR NOT IN INPUTS. 8. Compliance. Banned cut. Gaps: second extractor, ROB tool, software, analysis model, inclusion dates. Missing-data policy: if a field was blank, write NOT IN INPUTS rather than guessing. Lock any tool version named in Inputs; if unnamed, write unknown. No invented testimonials, star ratings, or press logos. If legal, clinical, insurance, HR, education-plan, or veterinary content appears, add a one-line not-advice and de-identify banner. Quote banned-word hits and cut them. End with a gaps list of five bullets the user still owes you. Character and byte caps in the job are hard; print counts when relevant. Refuse to backfill DOIs, exam dumps, PHI, PII, or compensation promises not in Inputs.