1. Functions | 2. Reference Model | 3. Input/Output Data |
4. Functions of AI Modules | 5. Input/output Data of AI Modules | 6. AIW, AIMs, and JSON Metadata |
1. Functions
The Back End gathers AIH Data from End Users and acts as both a brokerage gateway between the entities requesting access to the AIH Data and those providing it. The Back End grants Rights without referring to the identity of the End Users who have provided the Health Data as long as Health Data is licensed by Smart Contracts registered on the Block Chain.
The Back End implements the following functionalities:
- Securely store, de-identify and anonymise Health Data.
- Authentication and access control to Health Data.
- Receive and store licensed Health Data.
- License access to Health Data.
- Receive requests and process Health Data through the AI Framework.
- Perform Federated Learning services to update Font-Ends.
- Upload and download AIMs from the MPAI Store.
- Communicates with the Blockchain.
2. Reference Model
Figure 1 depicts the Reference Architecture of the Health Back End (AIH-HBE).
Figure 1 – Reference Model of the Health Back End (AIH-HBE) AIW
This is the flow of operation of the Health Back End (AIH-GBE) AIW Reference Model:
- A User wishing to access the Back End, provides Authentication and Access Control Parametres to Authentication and Access Control (MPAI-AAC) AIM.
- If Authentication is successful, MPAI-AAC AIM issues a Token. All the following steps of Health Back End access assume that a User holds a Token.
- User uploads AIH Data and corresponding Model Licence.
- AIH Data is received by the Data Storage and Access (AIH-DSA) and stored to the Secure Storage.
- The Model Licence is to the Blockchain as a Smart Contract.
- The Blockchain responds with an ID if the creation of the Smart Contract was successful.
- The Back End stored the Licence ID together with the AIH ID.
- A User may make a (Pseudo-)Anonymisation Request to the De-Identification and Anonymisation (AIH-DIA) AIM:
- AIH-DIA AIM retrieves AIH Data from Secure Storage.
- (Pseudo-)Anonymises AIH Data.
- Stores (Pseudo-)Anonymise AIH Data back to Secure Storage.
- A User may make a AIH Data Processing Request to the Health Data Processing (AIH-HBP) AIM by providing the AIH Data ID:
- AIF Controller may download appropriate AIMs from the MPAI Store.
- AIH-HBP
- Request an the Licence ID from the Back End.
- Sends a Confirmation Request containing the Licence ID and the intended type of Processing to the Blockchain .
- The Blockchain sends a Confirmation Response back to the AIH-HBP.
- If the Response is positive, AIH-HBP retrieves AIH Data from Secure Storage.
- In either case AIH-HBP records the Confirmation Response.
- Performs requested processing.
- Stores processed AIH Data to Secure Storage.
- Outputs processed AIH Data.
- A User may make an Audit Request to the Audit (AIH-ADT) AIM providing Audit Data to the AIH-ADT AIM
- Retrieves relevant Confirmation Responses.
- Provides Audit Response.
- When Federated Learning process begins:
- Health Back End requests the NN Model to all Health Front Ends.
- Health Front Ends provide the NN Models.
- Health Back End
- Develops and upload the new NN Model to the MPAI Store.
- Informs the Health Front Ends.
- Front Ends download the new NN Model from the MPAI Store.
3. Input/Output Data
Table 1 specifies the Input and Output Data.
Table 1 – I/O Data of Health Back End
Input | Description |
AAC Parameters | Parameters provided by User to the Authentication & Access Control AIM. |
AIH Data Access Request | User’s request to Upload or Access AIH Data. |
AIH Data Store Request | End User’s request to Upload or Access AIH Data. |
AIH Data | Health Data provided by User’s Front End. |
AIH Data MLicence | Data describing the lEnd User’s Licence terms and conditions. |
Confirmation Response | Blockchain confirmation that AIH may/may not be used. |
DIA Request | Request to de-identify and anonymised AIH Data. |
Processing Request | Request to process AIH Data. |
ARA Data | Anomaly & Risk Data |
Audit Request | Audit Request made by End User. |
Audit Data | Data required by the Audit AIM. |
NN Model | NN Model provided by Front End. |
Output | Description |
AAC Token | Token provided by Authentication & Access Control AIM if process was successful. |
Licence Request | Request to Blockchain to create or obtain Licence |
AIH Data MLicence | Licence represented according to Licence JSON Schema. |
Confirmation Request | Request to Blockchain to confirm that AIH may/may not be used. |
DIA Data | Data that has been de-identified and anonymised. |
Licence Request | Request made to Block Chain to enable AIH Data Processing. |
AIH Data | AIH Data that have been processed. |
Audit Response | Response containing Audit results. |
NN Model | NN Model provided by Federated Learning. |
NN Model Request | Request made to Front End by Back End for Federated Learning. |
4. Functions of AI Modules
Table 2 specifies the Function of the AI Modules.
Table 2 – Functions of Health Back End AI Modules
AI Module | Description |
Authentication and Access Control | Produces Token to User who have successfully passed the process. |
Data Storage and Access | Manages AIH Data upload and subsequent Access. |
Licensing and Governance | Manages licensing request to Blockchain to store and create Licence. |
De-Identification and Anonymisation | De-identifies and anonymises AIH Data. |
HBE Data Processing | Processes AIH Data |
Auditing | Enables End User to monitor the use of their AIH Data. |
Health Federated Learning | Performs Federated Learning of Front Ends’ NN Model. |
5. Input/output Data of AI Modules
Table 3 specifies the Function of the AI Modules.
Table 3 – Functions of Health Back End AI Modules
6. AIW, AIMs, and JSON Metadata
Table 4 provides the links to the AIW and AIM specifications and to the JSON syntaxes. AIMs/1 indicates that the column contains Composite AIMs and AIMs indicates that the column contains their Basic AIMs.
Table 4 – AIW, AIMs, and JSON Metadata
AIW | AIMs | Name | JSON |
AIH-HBE | Health Back End | X | |
AIH-AAC | Authentication and Access Control | X | |
AIH-DSA | Data Storage and Access | X | |
AIH-LCG | Licensing and Governance | X | |
AIH-DIA | De-Identification and Anonymisation | X | |
AIH-BDP | HBE Data Processing | X | |
AIH-ADT | Auditing | X | |
AIH-HFL | Health Federated Learning | X |