Forty protocols, one eligibility table.
Protocols are written to be complete rather than comparable. The same criterion is a bullet in one and a paragraph in the next, and the question you have is almost always across the set. Ragextract reads them once and returns the comparison, with every answer citing the section it came from so it can be checked against the protocol.
Free credits on sign-up. No card, no subscription.
| Row | Documents | Key eligibility | Primary endpoints | Dosage limit | AE reporting |
|---|---|---|---|---|---|
| Protocol A — phase II.pdf | ECOG 0–1; ≥1 prior line; no CNS metastases §4.1 | Progression-free survival at 12 months §8.1 | 400 mg daily, 200 mg on grade 3 §6.4 | SAEs within 24 hours to sponsor §9.2 | |
| Protocol B — phase III.pdfAmendment 2.pdf | ECOG 0–2; treatment-naive; CNS mets permitted if treated Am. 2, §4.1 | Overall survival §8.1 | 10 mg/kg every 3 weeks, capped at 1,200 mg §6.2 | SAEs within 24 hours; DSMB review quarterly §9.1 | |
| Protocol C — phase Ib.pdf | ECOG 0–1; adequate organ function; no prior immunotherapy §4.2 | Dose-limiting toxicity; MTD §8.1 | Escalating, 50–300 mg by cohort §6.1 | DLTs within 24 hours; all AEs at each visit §9.3 | |
| Protocol D — synopsis.pdf | ECOG 0–1; ≥2 prior lines §2 | Objective response rate §2 | Not stated | Not stated |
A table to check against, not a table to trust.
This is a reading aid for people who will read the protocol anyway. It is not a clinical decision tool, it does not screen or match patients, and no answer in it should reach a decision without someone opening the section it cites.
What it changes is where the reading goes. Every cell carries its section and a confidence score, so a reviewer starts from the eight answers that look thin instead of from page one of forty documents. The citation is not a flourish here — it is the entire basis on which the table is usable.
| Document | Dosage limit | As stated in |
|---|---|---|
| Protocol A vs Protocol B | 400 mg daily · 10 mg/kg every 3 weeks §6.4 · §6.2 | Flat dose · weight-based, capped §6 |
A protocol includes its amendments.
Eligibility is the field that moves. A protocol amended twice has an inclusion list that no longer matches the one in the original document, and a table that reads the original will report criteria that were withdrawn — with a citation, which makes it more convincing rather than less.
Bundle each protocol with its amendments, most recent first, and the bundle is the row. Order carries precedence, so the current version is what “the eligibility criteria” resolves to. A bundle holds up to fifteen documents and the first three are included in the column’s rate.
Where it fits.
A row is one study. Which document counts as the study — protocol, synopsis, published paper — is the decision to settle before writing a single column.
| The work | What a row is | Start from |
|---|---|---|
| Protocol comparison | A protocol, with its amendments | |
| Feasibility and site selection | A protocol | |
| Literature and evidence review | A published paper | |
| Regulatory submission review | A submitted document |
The preset ships in the application and its prompts are illustrative starting points, not clinical or regulatory definitions — they are meant to be edited. Clinical trial protocols works the whole thing through, including what to check before relying on any of it.
Reading is charged once.
Forty protocols is a few thousand pages, and they are read once however many times the set is later interrogated. A question that occurs to a reviewer in month three costs what it would have cost in week one.
| A 40-protocol review | Volume | Cost |
|---|---|---|
| 40 protocols, 90 pages each — read once | 3,600 pages | 3,600 credits |
| 2 typed questions asked of all 40 | 80 cells | 80 credits |
| Eligibility and endpoints, as list columns | 80 cells | 240 credits |
Start with two protocols you know well.
Upload them with their amendments, write the eligibility column, and read every citation against the section it points at. Protocols you already know are the only honest test of whether the table is worth building for the ones you do not.
Ragextract is not a clinical decision support tool and is not regulated as a medical device. Nothing on this page is medical, clinical or regulatory advice, and the preset is not a set of clinical definitions.