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
Draft as of 2025-08-15 | Maturity Level: 0 |
Definitions for the ModelCard logical model.
Guidance on how to interpret the contents of this table can be foundhere
0. ModelCard | |
Definition | An AI model card is a document that provides a standardized overview of an artificial intelligence model's purpose, performance, intended usage, and limitations. |
Short | AI Model Card |
Control | 0..* |
Is Modifier | false |
Logical Model | Instances of this logical model are not marked to be the target of a Reference |
2. ModelCard.id | |
Definition | model card identifier |
Short | model card identifier |
Control | 0..1 |
Type | string |
Primitive Value | This primitive element may be present, or absent, or replaced by an extension |
Summary | true |
4. ModelCard.name | |
Definition | model card title |
Short | model card title |
Control | 0..1 |
Type | string |
Primitive Value | This primitive element may be present, or absent, or replaced by an extension |
Summary | true |
6. ModelCard.description | |
Definition | This includes the architecture, version, if it was introduced in a paper, if an original implementation is available, and the creators. Any copyright should be attributed here. General information about training procedures, parameters, and important disclaimers can also be mentioned in this section. |
Short | Basic details about the model. |
Control | 0..1 |
Type | string |
Primitive Value | This primitive element may be present, or absent, or replaced by an extension |
8. ModelCard.type | |
Definition | You can name the “type” as: 1 = Supervision/Learning Method, 2 = Machine Learning Type, 3 = Modality |
Short | model type |
Control | 0..1 |
Type | code |
Primitive Value | This primitive element may be present, or absent, or replaced by an extension |
10. ModelCard.appliedIn | |
Definition | FHIR resource where the model was used if it was AI-generated |
Short | FHIR resource where the model was used if it was AI-generated |
Control | 0..* |
Type | Reference(Resource) |
Guidance on how to interpret the contents of this table can be foundhere
0. ModelCard | |
Definition | An AI model card is a document that provides a standardized overview of an artificial intelligence model's purpose, performance, intended usage, and limitations. |
Short | AI Model Card |
Logical Model | Instances of this logical model are not marked to be the target of a Reference |
2. ModelCard.id | |
Definition | model card identifier |
Short | model card identifier |
Control | 0..1 |
Type | string |
Primitive Value | This primitive element may be present, or absent, or replaced by an extension |
4. ModelCard.name | |
Definition | model card title |
Short | model card title |
Control | 0..1 |
Type | string |
Primitive Value | This primitive element may be present, or absent, or replaced by an extension |
6. ModelCard.description | |
Definition | This includes the architecture, version, if it was introduced in a paper, if an original implementation is available, and the creators. Any copyright should be attributed here. General information about training procedures, parameters, and important disclaimers can also be mentioned in this section. |
Short | Basic details about the model. |
Control | 0..1 |
Type | string |
Primitive Value | This primitive element may be present, or absent, or replaced by an extension |
8. ModelCard.type | |
Definition | You can name the “type” as: 1 = Supervision/Learning Method, 2 = Machine Learning Type, 3 = Modality |
Short | model type |
Control | 0..1 |
Type | code |
Primitive Value | This primitive element may be present, or absent, or replaced by an extension |
10. ModelCard.appliedIn | |
Definition | FHIR resource where the model was used if it was AI-generated |
Short | FHIR resource where the model was used if it was AI-generated |
Control | 0..* |
Type | Reference(Resource) |
Guidance on how to interpret the contents of this table can be foundhere
0. ModelCard | |
Definition | An AI model card is a document that provides a standardized overview of an artificial intelligence model's purpose, performance, intended usage, and limitations. |
Short | AI Model Card |
Control | 0..* |
Is Modifier | false |
Logical Model | Instances of this logical model are not marked to be the target of a Reference |
2. ModelCard.id | |
Definition | model card identifier |
Short | model card identifier |
Control | 0..1 |
Type | string |
Primitive Value | This primitive element may be present, or absent, or replaced by an extension |
Summary | true |
4. ModelCard.name | |
Definition | model card title |
Short | model card title |
Control | 0..1 |
Type | string |
Primitive Value | This primitive element may be present, or absent, or replaced by an extension |
Summary | true |
6. ModelCard.description | |
Definition | This includes the architecture, version, if it was introduced in a paper, if an original implementation is available, and the creators. Any copyright should be attributed here. General information about training procedures, parameters, and important disclaimers can also be mentioned in this section. |
Short | Basic details about the model. |
Control | 0..1 |
Type | string |
Primitive Value | This primitive element may be present, or absent, or replaced by an extension |
8. ModelCard.type | |
Definition | You can name the “type” as: 1 = Supervision/Learning Method, 2 = Machine Learning Type, 3 = Modality |
Short | model type |
Control | 0..1 |
Type | code |
Primitive Value | This primitive element may be present, or absent, or replaced by an extension |
10. ModelCard.appliedIn | |
Definition | FHIR resource where the model was used if it was AI-generated |
Short | FHIR resource where the model was used if it was AI-generated |
Control | 0..* |
Type | Reference(Resource) |