AI Transparency on FHIR
0.1.0 - ci-build International flag

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

: Provenance for AI created Patient resource - XML Representation

Raw xml | Download


<Provenance xmlns="http://hl7.org/fhir">
  <id value="AI-generated-patient-resource"/>
  <text>
    <status value="generated"/>
    <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 (use: usual, ))</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 = ---
language:
- en
license:
- bsd-3-clause
annotations_creators:
- crowdsourced
- expert-generated
language_creators:
- found
multilinguality:
- monolingual
size_categories:
- n&lt;1K
task_categories:
- image-segmentation
task_ids:
- semantic-segmentation
pretty_name: Sample Segmentation
---

# Dataset Card for Sample Segmentation

This is a sample dataset card for a semantic segmentation dataset.</a></td></tr></table></div>
  </text>
  <contained>
    <DocumentReference>
      <id value="Input-Prompt-create-patient"/>
      <status value="current"/>
      <type>
        <coding>
          <system
                  value="http://hl7.org/fhir/uv/aitransparency/CodeSystem/AImodelCardCS"/>
          <code value="AIInputPrompt"/>
          <display value="AI Input Prompt"/>
        </coding>
      </type>
      <category>
        <coding>
          <system
                  value="http://hl7.org/fhir/uv/aitransparency/CodeSystem/AImodelCardCS"/>
          <code value="AIInputPrompt"/>
          <display value="AI Input Prompt"/>
        </coding>
      </category>
      <description
                   value="System Prompt

You 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.

Requirements:

- Generate valid JSON that conforms to FHIR R4 Patient resource structure
- Ensure compliance with US Core Patient Profile (US Core 6.1.0)
- Include all required US Core elements when data is available
- Use appropriate FHIR data types and value sets
- Generate a unique resource ID using UUID format
- Apply proper FHIR coding systems and terminologies
- Handle missing data appropriately (omit optional fields when data unavailable)
- Use standard US address formatting
- Apply proper date formatting (YYYY-MM-DD)
- Include appropriate extensions when necessary for US Core compliance

US Core 6.1.0 Patient Profile Requirements:

- Must include: identifier, name, gender, birthDate
- Should include: address, telecom, race, ethnicity when available
- Use US Core extensions for race and ethnicity
- Follow US postal address conventions
- Use appropriate terminologies (e.g., HL7 AdministrativeGender, OMB race categories)

Data Mapping Guidelines:

- Extract patient name and structure as HumanName with family/given components
- Map gender terms to FHIR AdministrativeGender codes (male, female, other, unknown)
- Convert birth dates to FHIR date format
- Structure addresses using Address data type with appropriate use codes
- Map race/ethnicity information using US Core extensions with appropriate OMB codes
- Generate medical record number as primary identifier when not provided
- Include meta.profile reference to US Core Patient profile

Output Format:

- Provide only the valid FHIR JSON resource without additional commentary or explanation.

User Prompt

- Convert the following patient information into a FHIR Patient resource conformant with US Core 6.1.0:

`Jane Doe is a white female born on November 15, 1950. She lives at 123 Main Street, Anytown, Michigan, zipcode 12345.`"/>
      <content>
        <attachment>
          <contentType value="text/plain"/>
          <data
                value="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"/>
        </attachment>
      </content>
    </DocumentReference>
  </contained>
  <target>🔗 
    <reference value="Patient/a1b2c3d4-e5f6-7890-abcd-ef1234567890"/>
  </target>
  <occurredDateTime value="2025-06-18T00:00:00Z"/>
  <recorded value="2025-06-18T00:00:00Z"/>
  <policy
          value="http://example.org/policies/ai-authorized-patient-generation"/>
  <reason>
    <coding>
      <system value="http://terminology.hl7.org/CodeSystem/v3-ActReason"/>
      <code value="HOPERAT"/>
    </coding>
  </reason>
  <agent>
    <type>
      <coding>
        <system
                value="http://terminology.hl7.org/CodeSystem/provenance-participant-type"/>
        <code value="verifier"/>
        <display value="Verifier"/>
      </coding>
    </type>
    <who>
      <reference value="http://example.org/fhir/Practitioner/pract"/>
    </who>
  </agent>
  <agent>
    <type>
      <coding>
        <system
                value="http://terminology.hl7.org/CodeSystem/provenance-participant-type"/>
        <code value="author"/>
        <display value="Author"/>
      </coding>
    </type>
    <who>🔗 
      <reference value="Device/Note-ModelCard"/>
    </who>
  </agent>
  <entity>
    <role value="quotation"/>
    <what>
      <reference value="#Input-Prompt-create-patient"/>
    </what>
    <agent>
      <type>
        <coding>
          <system
                  value="http://terminology.hl7.org/CodeSystem/provenance-participant-type"/>
          <code value="author"/>
          <display value="Author"/>
        </coding>
      </type>
      <who>
        <reference value="http://example.org/fhir/Practitioner/pract"/>
      </who>
    </agent>
  </entity>
</Provenance>