Extract multiple FHIR resources from text

post

https://{instanceUrl}/lang2fhir/create/multi

Analyzes natural language text and extracts multiple FHIR resources, returning them as a transaction Bundle.
Automatically detects Patient, Condition, MedicationRequest, Observation, and other resource types from the text.
Resources are linked with proper references (e.g., Conditions reference the Patient).

Patient identifier handling. US Core requires Patient.identifier (a business identifier such as an MRN). When the source text contains an identifier, it is extracted with an appropriate URI system. When the source text does not contain a detectable identifier, a synthetic one is generated with system: "urn:phenoml:lang2fhir-generated-id" and a UUID value so the bundle remains FHIR-valid and US Core conformant. Callers who need a tenant-specific namespace should rewrite the synthetic system after extraction.

Recent Requests

Time	Status	User Agent
Retrieving recent requests…

Loading…

Body Params

text

string

required

Natural language text containing multiple clinical concepts to extract

version

string

Defaults to R4

FHIR version to use

provider

string

Optional FHIR provider name for provider-specific profiles

patient_reference

object

Optional reference to an existing Patient, by business identifier. If a Patient resource is extracted, this identifier is added to that Patient's identifier list (existing identifiers are kept). If no Patient is extracted, generated clinical resources are linked to this patient as a logical reference (subject.identifier) instead of the request failing, and no placeholder Patient is created. Supply the patient-level identifier (not an order or specimen identifier).

implementation_guide

string

Custom Implementation Guide name. When specified, profiles from this IG are included alongside US Core profiles during resource detection. US Core is always the base layer; custom IG profiles are additive.

detection_effort

string

enum

Defaults to standard

Detection effort. 'standard' runs detection once, 'deep' runs detection multiple times for higher recall.

Allowed:

validation_method

string

enum

Defaults to none

FHIR validation method to apply to the generated bundle. 'none' skips validation (default). 'check' runs the bundle through a FHIR structure validator and includes the results in the response. 'fix' runs validation and attempts to auto-correct errors using an LLM (up to 3 validation passes). The response includes results from each pass. Warning: 'fix' can significantly increase latency due to multiple LLM and validation round-trips.

Allowed:

resource_review

object

Opt-in, report-only faithfulness audit (honored by /lang2fhir/create/multi and /lang2fhir/document/multi). For each selected resource type an LLM checks whether selected dates and clinical code concepts are actually supported by the full source document. Resources with an unsupported field are pulled out of the returned bundle and reported under resource_review in the response.

Responses

400

Invalid request

401

Unauthorized

404

Profile not found

422

Generated FHIR resource failed validation or terminology constraints

500

Server error

Language

Credentials

Bearer

JWT

URL

Loading…

Response

Click Try It! to start a request and see the response here! Or choose an example:

application/json

200Successfully extracted FHIR resources