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
Contents:
This page provides a list of the FHIR artifacts defined as part of this implementation guide.
These define data models that represent the domain covered by this implementation guide in more business-friendly terms than the underlying FHIR resources.
AI Model Card |
An AI model card is a document that provides a standardized overview of an artificial intelligence model's purpose, performance, intended usage, and limitations. |
These define constraints on FHIR resources for systems conforming to this implementation guide.
AI Provenance |
An AI Provenance is a record of the use of an AI model in generating or enhancing FHIR resources. It captures the details of the AI model used, the input data, and the output generated by the AI model. |
These define constraints on FHIR data types for systems conforming to this implementation guide.
Model Card |
When the Device is described by a Model Card, this extension can be used to reference the Model Card. |
These define sets of codes used by systems conforming to this implementation guide.
Recommended provenance codes |
Subset from HL7, plus those defined here |
These define new code systems used by systems conforming to this implementation guide.
Added DocumentReference.code for AI ModelCard |
This CodeSystem contains codes for the DocumentReference.type and DocumentReference.category that indicate that the DocumentReference is a Model Card. |
Added Provenance Codes |
This CodeSystem contains codes for the provenance indications used in .meta.security and elsewhere that indicate that the AI system has been involved. |
These are example instances that show what data produced and consumed by systems conforming with this implementation guide might look like.
Appendectomy Procedure |
A Procedure resource that is created by an AI system and verified by a human. |
Blood Culture Result |
A lab result Observation resource that is created by an AI system and verified by a human. |
Bundle of AI generated resources |
A Bundle resource containing AI generated resources |
Device with Model-Card in Device.note.text |
A Device that has a Model Card. Given that it is understood that ModelCards are Markdown, this could simply go into the .note. |
Device with attached Model-Card |
A Device that has an attached Model Card. |
DiagnosticReport with Inline AI Security Labels |
This DiagnosticeReport is derived from FHIR Core R4 DiagnosticReport id f202. This use contains a DiagnosticReport with inline Artificial Intelligence asserted security labels for the conclusion and conclusionCode, as well as a ServiceRequest.
|
DocumentReference Model-Card |
An example of a Model Card DocumentReference that contains the model card in YAML and Markdown formats. using example from HuggingFace. |
Example Observation with AI Assisted security labels |
This observation is derived from FHIR Core R4 Observation id glasgow. This use contains a Glasgow Coma Scale observation with Artificial Intelligence asserted security labels for the whole Resource. Note that the example I took, I assumed was a good one for AIAST. But I am not sure that it is, especially since the outcome is not well coded, using ucum score values. Note that there is no .performer as that element can't hold a Device, and we are modeling this as being wholely authored by the AI. Thus I use the extension alternate-reference. |
Input Prompt DocumentReference lorem ipsum |
A DocumentReference that contains the input prompt provided to the AI system. – Lorem ipsum text is used as a placeholder.
|
Input Prompt DocumentReference to create a patient |
A DocumentReference that contains the input prompt provided to the AI system. – to generate a Patient resource.
|
Lab Results PDF |
A DocumentReference resource that represents a PDF document containing lab results for a patient. This is provided to an AI, which interprets and creates FHIR Resources. In the attached example the patient's name is Alton Walsh and the lab test is an HbA1C. All the FHIR resources in the bundle have been created by the AI, so they should be tagged accordingly. |
Patient an AI generated |
An example Patient resource generated by AI |
Provenance for AI created Patient resource |
A Provenance resource that captures the full AI process, including the model card, input, and output. This is a full example of how to capture the AI process in FHIR.
|
Provenance for AI with Model Card, input, and output |
A Provenance resource that captures the full AI process, including the model card, input, and output. This is a full example of how to capture the AI process in FHIR.
|
Provenance of AI Authored Procedure.followup.text |
A Provenance resource that documents the addition of followUp text in a Procedure by an AI system. |
Provenance of AI Generated Lab Results |
A Provenance resource that documents the creation of a Lab result Observation resource by an AI (device), verified by a human. The AI system is represented as a Device resource. The Input is a PDF Lab result. |
Provenance of AI authored Lab Observation |
A Provenance resource that documents the creation of a Lab result Observation resource by an AI (device), verified by a human. The AI system is represented as a Device resource. |
The AI System |
An AI system that authored a resource. TODO: Need codes in the device-type to indicate AI/LLM. TODO: Need codes to identify the device version for the parts of an AI? |