The following requirements were considered when updating openIMIS’s Claim adjudication process:

• the default openIMIS Claim adjudication process should be modified as less as possible

• Medical Officers should not be impacted too much by the activation of the openIMIS-AI module

Claim adjudication process

Updated Claim Status

The following state diagram from Figure 1 corresponds to the Claim fields status with the updated adjudication process.

Figure 1. Claim state diagram for the updated claim adjudication process

Updated Claim Adjudication Process

The following activity diagram proposes the updated adjudication process.

Claim-AI Quality Module

Claim-AI Quality Responsibilities

• Contribute to Claim Review Search with Medical Item/Service filter

• Listening for <<signal_mutation_module_after_mutating>> SubmitClaimsMutation

• Prepare the new checked claims for AI categorisation (not to be selected by reviewers)

• Convert openIMIS Claims to FHIR Claims and POST to Claim-AI

• Receive FHIR ClaimResponse

• Update Claim Status and ReviewStatus

• Reports claim adjudication misclassifications

Models

The following JSON extensions will be created to support the Claim AI-based Categorisation:

• claim_ai to add information on Claim

  "json_ext": {
    "claim_ai_quality": {
      "was_categorized": "boolean",
      "request_time": "datetime",
      "response_time": "datetime"
    }
  }

• claim_ai_item to add information on ClaimItem and ClaimService. This is used to store AI categorisation result to allow the misclassification report.

  "json_ext": {
    "claim_ai_quality": {
      "ai_result": "integer"
    }
  }

Because ClaimItem and ClaimService doesn’t extend the ExtendableModel, this change is also made to allow custom fields.

Claim-AI Module

Claim-AI Responsibilities

• Self containing REST API

• Accepts FHIR R4 Claim and reply with FHIR R4 ClaimResponse

• Clean the data and prepare it for the AI model

• Categorize the claim (AI model execution)