Healthcare
Claims line items
CPT/ICD-10-coded claim line items.
Schema
The canonical field set, printed as it ships.
4 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.
claims_line_items_v1FHIR · Claim.item- fields
- 4
- required
- 2
- validated
- 2
- hints
- 12
| Canonical column | Type | Required | Validators | Header hints the cascade matches |
|---|---|---|---|---|
cpt_code | string | yes | cpt_code | cptprocedure |
icd10_code | string | — | icd10_code | icdicd-10diagnose |
amount | number | yes | — | betragmontantimporteamount |
service_date | date | — | — | leistungsdatumdate du servicefecha del servicio |
Read the same definition as JSON at GET /v1/templates/claims_line_items_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.
- 4 canonical fields
- 2 required
- 2 validated
- 12 header hints
- Healthcare pack
Try it
A real file, a real call, one template id.
8 rows, real CPT + ICD-10 codes. Fully synthetic — safe to share, commit, and run in CI.
curl -X POST https://api.adaptivmapr.com/v1/uploads \
-H "Authorization: Bearer $ADAPTIVMAPR_API_KEY" \
-F "file=@claims_line_items_sample.csv" \
-F "template=claims_line_items_v1"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.adaptivmapr.match_headers({
template_id: "claims_line_items_v1",
headers: ["cpt_code", "icd10_code", "amount", "service_date"]
})Committed rows can be emitted as FHIR Claim.item resources — a healthcare-vertical feature on a vertical-agnostic engine.
Ready when you are
Put claims line items 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.