Clinical evidence & market access

The templates in this pack

One line-of-therapy / pathway recommendation from a clinical guideline (NCCN/ESMO/NICE/ASCO). Maps to drug-database.clinical_guidelines.

Try in Workbench Full template page

Schema

The canonical field set, printed as it ships.

12 fields with multilingual hints (DE / FR / IT / EN / ES) and field-level validators. Any source column that resolves to one of these is mapped by the cascade — most of them on the deterministic layers, with no LLM call.

clinical_guideline_v1

fields: 12
required: 4
validated: 1
hints: 62

Canonical column	Type	Required	Validators	Header hints the cascade matches
`source`	enumnccnesmoniceascoescother	yes	—	guidelineissuing bodysocietyorganisation
`org`	string	—	—	organizationissuing organizationpanelcommittee
`title`	string	yes	—	guideline titledocument titlepathwayclinical practice guideline
`indication`	string	yes	—	indicationconditiondiseasetumour typecancer typediagnosissetting
`efo_id`	string	—	—	efomondodoidontology iddisease code
`atc_code`	string	—	`atc_code`	atcdrug class code
`line_of_therapy`	enum1L2L3L4L+maintenanceadjuvantneoadjuvantconsolidation+2	—	—	line of therapyfirst-linefirst linesecond-linesecond linemaintenanceadjuvantneoadjuvant1L2L
`recommendation`	string	yes	—	recommendationrecommendedpreferred regimenother recommendedwe recommendshould be offered
`evidence_level`	string	—	—	categoryevidence levelgradelevel of evidencestrength of recommendationnccn categoryesmo-mcbsgrade
`url`	string	—	—	urllinkreferencedoi
`version`	string	—	—	versioneditionyearv.
`published_date`	date	—	—	publisheddateeffective datelast updatedrevision date

Read the same definition as JSON at GET /v1/templates/clinical_guideline_v1. A hint match resolves on layer 2 — no LLM call, no token spend, just the flat per-map fee. Hover a validator id to see what it checks.

12 canonical fields
4 required
1 validated
62 header hints
Clinical evidence & market access pack

Try it

A real file, a real call, one template id.

POST the file with the template id. The cascade resolves most columns for free on the deterministic layers; only the leftovers reach the metered LLM.

bash

curl -X POST https://api.adaptivmapr.com/v1/uploads \
  -H "Authorization: Bearer $ADAPTIVMAPR_API_KEY" \
  -F "template=clinical_guideline_v1"

→ upload created · mappings ready · confirm before commit

This is a medium-risk template. Its mappings response comes back with requires_hitl: true so you can gate your own commit. Schema-only mode — headers plus at most three sample rows, each clamped to 80 characters — is a data-minimization mode. Full-data routes the metered layer-5 call in-region under a BAA at a 20% uplift, and stays locked until the workspace accepts the BAA/NDA in-app.

mcp

adaptivmapr.match_headers({
  template_id: "clinical_guideline_v1",
  headers: ["source", "org", "title", "indication"]
})

schema-only · headers and ≤3 clamped rows only

Put clinical guideline recommendation in production — without shipping raw records.

Schema-only mapping leaves only headers and a handful of clamped samples. Add full-data when you need row-level AI, routed in-region under a BAA.

Full template page See pricing