AI Transparency on FHIR, published by HL7 International / Electronic Health Records. This guide is not an authorized publication; it is the continuous build for version 0.1.0 built by the FHIR (HL7® FHIR® Standard) CI Build. This version is based on the current content of https://github.com/HL7/aitransparency-ig/ and changes regularly. See the Directory of published versions
{
"resourceType" : "Provenance",
"id" : "AI-generated-patient-resource",
"text" : {
"status" : "generated",
"div" : "<div xmlns=\"http://www.w3.org/1999/xhtml\"><p class=\"res-header-id\"><b>Generated Narrative: Provenance AI-generated-patient-resource</b></p><a name=\"AI-generated-patient-resource\"> </a><a name=\"hcAI-generated-patient-resource\"> </a><p>Provenance for <a href=\"Patient-a1b2c3d4-e5f6-7890-abcd-ef1234567890.html\">Jane Doe (official) Female, DoB: 1950-11-15 ( Medical Record Number: MRN123456789\u00a0(use:\u00a0usual,\u00a0))</a></p><p>Summary</p><table class=\"grid\"><tr><td>Occurrence</td><td>2025-06-18 00:00:00+0000</td></tr><tr><td>Recorded</td><td>2025-06-18 00:00:00+0000</td></tr><tr><td>Policy</td><td><a href=\"http://example.org/policies/ai-authorized-patient-generation\">http://example.org/policies/ai-authorized-patient-generation</a></td></tr></table><p><b>Agents</b></p><table class=\"grid\"><tr><td><b>Type</b></td><td><b>who</b></td></tr><tr><td><span title=\"Codes:{http://terminology.hl7.org/CodeSystem/provenance-participant-type verifier}\">Verifier</span></td><td><a href=\"http://example.org/fhir/Practitioner/pract\">http://example.org/fhir/Practitioner/pract</a></td></tr><tr><td><span title=\"Codes:{http://terminology.hl7.org/CodeSystem/provenance-participant-type author}\">Author</span></td><td><a href=\"Device-Note-ModelCard.html\">Device: identifier = http://example.org/ehr/client-ids#goodhealth; manufacturer = Acme Devices, Inc; type = ; contact = http://example.org; note = ---\nlanguage:\n- en\nlicense:\n- bsd-3-clause\nannotations_creators:\n- crowdsourced\n- expert-generated\nlanguage_creators:\n- found\nmultilinguality:\n- monolingual\nsize_categories:\n- n<1K\ntask_categories:\n- image-segmentation\ntask_ids:\n- semantic-segmentation\npretty_name: Sample Segmentation\n---\n\n# Dataset Card for Sample Segmentation\n\nThis is a sample dataset card for a semantic segmentation dataset.</a></td></tr></table></div>"
},
"contained" : [
{
"resourceType" : "DocumentReference",
"id" : "Input-Prompt-create-patient",
"status" : "current",
"type" : {
"coding" : [
{
"system" : "http://hl7.org/fhir/uv/aitransparency/CodeSystem/AImodelCardCS",
"code" : "AIInputPrompt",
"display" : "AI Input Prompt"
}
]
},
"category" : [
{
"coding" : [
{
"system" : "http://hl7.org/fhir/uv/aitransparency/CodeSystem/AImodelCardCS",
"code" : "AIInputPrompt",
"display" : "AI Input Prompt"
}
]
}
],
"description" : "System Prompt\n\nYou are a healthcare data specialist that converts natural language patient information into valid FHIR Patient resources. Your task is to extract relevant patient demographics and create a well-formed FHIR Patient resource that is fully conformant with FHIR US Core 6.1.0 specifications.\n\nRequirements:\n\n- Generate valid JSON that conforms to FHIR R4 Patient resource structure\n- Ensure compliance with US Core Patient Profile (US Core 6.1.0)\n- Include all required US Core elements when data is available\n- Use appropriate FHIR data types and value sets\n- Generate a unique resource ID using UUID format\n- Apply proper FHIR coding systems and terminologies\n- Handle missing data appropriately (omit optional fields when data unavailable)\n- Use standard US address formatting\n- Apply proper date formatting (YYYY-MM-DD)\n- Include appropriate extensions when necessary for US Core compliance\n\nUS Core 6.1.0 Patient Profile Requirements:\n\n- Must include: identifier, name, gender, birthDate\n- Should include: address, telecom, race, ethnicity when available\n- Use US Core extensions for race and ethnicity\n- Follow US postal address conventions\n- Use appropriate terminologies (e.g., HL7 AdministrativeGender, OMB race categories)\n\nData Mapping Guidelines:\n\n- Extract patient name and structure as HumanName with family/given components\n- Map gender terms to FHIR AdministrativeGender codes (male, female, other, unknown)\n- Convert birth dates to FHIR date format\n- Structure addresses using Address data type with appropriate use codes\n- Map race/ethnicity information using US Core extensions with appropriate OMB codes\n- Generate medical record number as primary identifier when not provided\n- Include meta.profile reference to US Core Patient profile\n\nOutput Format:\n\n- Provide only the valid FHIR JSON resource without additional commentary or explanation.\n\nUser Prompt\n\n- Convert the following patient information into a FHIR Patient resource conformant with US Core 6.1.0:\n\n`Jane Doe is a white female born on November 15, 1950. She lives at 123 Main Street, Anytown, Michigan, zipcode 12345.`",
"content" : [
{
"attachment" : {
"contentType" : "text/plain",
"data" : "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"
}
}
]
}
],
"target" : [
{
🔗 "reference" : "Patient/a1b2c3d4-e5f6-7890-abcd-ef1234567890"
}
],
"occurredDateTime" : "2025-06-18T00:00:00Z",
"recorded" : "2025-06-18T00:00:00Z",
"policy" : [
"http://example.org/policies/ai-authorized-patient-generation"
],
"reason" : [
{
"coding" : [
{
"system" : "http://terminology.hl7.org/CodeSystem/v3-ActReason",
"code" : "HOPERAT"
}
]
}
],
"agent" : [
{
"type" : {
"coding" : [
{
"system" : "http://terminology.hl7.org/CodeSystem/provenance-participant-type",
"code" : "verifier",
"display" : "Verifier"
}
]
},
"who" : {
"reference" : "http://example.org/fhir/Practitioner/pract"
}
},
{
"type" : {
"coding" : [
{
"system" : "http://terminology.hl7.org/CodeSystem/provenance-participant-type",
"code" : "author",
"display" : "Author"
}
]
},
"who" : {
🔗 "reference" : "Device/Note-ModelCard"
}
}
],
"entity" : [
{
"role" : "quotation",
"what" : {
"reference" : "#Input-Prompt-create-patient"
},
"agent" : [
{
"type" : {
"coding" : [
{
"system" : "http://terminology.hl7.org/CodeSystem/provenance-participant-type",
"code" : "author",
"display" : "Author"
}
]
},
"who" : {
"reference" : "http://example.org/fhir/Practitioner/pract"
}
}
]
}
]
}