Extract PICO and GRADE

Paste your PICO extraction schema, attach a clinical trial paper, and tell Anara to extract only from that document. You get a completed PICO table with a GRADE quality assessment, every field traceable to the source text, and blanks where the paper is silent. Use it when the extraction has to stand up to audit.

Prompt

A health economics researcher extracts a PCSK9 inhibitor trial for a payer submission.

Prompt

I am extracting clinical trial data for a HEOR dossier. Attached is a single RCT paper. Apply my extraction schema below using ONLY the information in this paper. Do not use external knowledge, prior studies, or general clinical assumptions to fill any field. If a field is not reported in this paper, write "Not reported."

PICO schema:
- Population (inclusion/exclusion criteria, sample size, demographics)
- Intervention (drug, dose, regimen, duration)
- Comparator (active or placebo; dose and regimen)
- Primary outcomes (measure, result, 95% CI, p-value as reported)
- Secondary outcomes (list each with results as reported)
- Follow-up duration
- Study design and blinding
- Industry sponsorship (yes/no, which sponsor)

After the PICO table, provide a GRADE quality assessment: rate the evidence quality as high, moderate, low, or very low, and state the reason for any downgrade (risk of bias, indirectness, imprecision, inconsistency, publication bias).

At the bottom, quote the three passages from the paper that most directly support the primary outcome data.

What to add to your library

Required: the clinical trial paper, as an upload or from your library.
Required: your PICO extraction schema, pasted directly into the prompt.
Optional: one completed row from your existing table, so Anara matches your format and level of detail.

What you get

A completed PICO table drawn only from the attached paper.
A GRADE quality assessment with the reason for any downgrade.
Three quoted source passages for audit verification, and every unfilled field marked not reported rather than inferred.

Follow-ups

Rank GRADE quality across the evidence base.

Prompt

Rank the 15 RCTs in my library folder by GRADE evidence quality from high to very low. For papers rated low or very low, summarize the reasons for downgrade and note the most common limitation.

Confirm a filled cell came from the paper.

Prompt

For the "primary outcome result" cell: quote the exact sentence that reports this value. If you took it from a table or calculation, identify the table and row.

Tips

The constraint statement carries the workflow. Without it, fields can be filled from general clinical knowledge when the paper is silent.
State the fallback explicitly, so an unreported field returns "Not reported" instead of an inference.
Verify the three quoted passages against the PDF before the row enters the dossier.