The openIMIS Backend Claim AI Quality reference module.
Project description
openIMIS Backend Claim AI Quality reference module
This repository holds the files of the openIMIS Backend Claim AI Quality reference module. It is dedicated to be deployed as a module of openimis-be_py.
ORM mapping:
None
Listened Django Signals
SubmitClaimsMutation
Adds 'claim_ai_quality' key to the json_ext field on claim submissions.
If ClaimAiQualityConfig.event_based_activation is set to true AI adjudication is performed.
EvaluateByAIMutation
Adjudication is called using after_claim_ai_evaluation_validation signal.
Services
- AiQualityReportService, loading claims used for misclassification report
Reports
-
miscategorisation_report
GraphQL Queries
None
GraphQL Mutations
EvaluateByAIMutation
Used for manual AI Adjudication of selected claims through after_claim_ai_evaluation_validation signal.
gql_mutation_submit_claims_perms permission required.
Additional Endpoints
- miscategorisation_report: generating report regarding ai misclassification in PDF format
Reports
miscategorisation_report: AI Evaluation accurracy and list of misclassified claims
Configuration options (can be changed via core.ModuleConfiguration)
Rest API Configuration
rest_api_login_endpoint: Endpoint used for getting user authentication token.
Default:http://localhost:8000/api/api_fhir_r4/login/,rest_api_bundle_evaluation_endpoint: Endpoint used for sending bundle of claims for evaluation.
Default:http://localhost:8000/api/claim_ai/claim_bundle_evaluation/,rest_api_single_claim_evaluation_endpoint: Endpoint used for sending single claim for evaluation.
Default:http://localhost:8000/api/claim_ai/claim_evaluation/,wait_for_evaluation: If set toFalsesystem doesn't wait for server response and have to use other method to pull adjudication data.rest_api_user_login: Username of user used for AI Server JWT Authentication.rest_api_user_password: Username of user used for AI Server JWT Authentication.
Remaining
claim_ai_username: User dedicated to perform DB operations executed in background by Claim AI Quality module. By default it's_ClaimAIAdminadded in module migration.event_based_activation: Determines if AI evaluation should be done on claim submission (True) or using scheduled job (True). Default:False- bundle_size: number of claims in one bundle if scheduled job is used. Default:
200, accepted_category_code: Code for Items/Services positively evaluated by AI. Default:0,rejected_category_code: Code for Items/Services negatively evaluated by AI. Default:1,reason_rejected_by_ai_code: FHIR Rejection reason code for claims rejected by AI. Default:-2,date_format: date format used in FHIR response. Default:%Y-%m-%d,misclassification_report_perms: List of permissions required to get Misclassification report.
Default: [112001],evaluation_method: Method used for AI evaluation. If set torest_apiclaims are adjudicated using REST API connection. If set tointegratedthen system is usingclaim_aimodule installed on same instance as Claim AI Quality server.
Default: (empty string). - ifclaim_aimodule is installed locally it uses this module. If it's not installed REST API is used.
openIMIS Modules Dependencies
- core
- claim
- api_fhir_r4
- location
- report
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distribution
Filter files by name, interpreter, ABI, and platform.
If you're not sure about the file name format, learn more about wheel file names.
Copy a direct link to the current filters
File details
Details for the file openimis-be-claim_ai_quality-2.0.0.tar.gz.
File metadata
- Download URL: openimis-be-claim_ai_quality-2.0.0.tar.gz
- Upload date:
- Size: 54.6 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/4.0.0 CPython/3.10.4
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
0ff6ea0e9192ff98950f7dd4bf96db972feaf64aa9abf7b92b82b09758cf04b8
|
|
| MD5 |
eae0a6051c9f203e5de64baa7a92f981
|
|
| BLAKE2b-256 |
92465977485d4c8b567c9151560fc4371582a596b3ae8583f4f0c0dfdb872096
|
File details
Details for the file openimis_be_claim_ai_quality-2.0.0-py3-none-any.whl.
File metadata
- Download URL: openimis_be_claim_ai_quality-2.0.0-py3-none-any.whl
- Upload date:
- Size: 71.9 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/4.0.0 CPython/3.10.4
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
4452e4d25f00c4908b33bb3be6d9bd9bc9721343374b59ee502c302321e9d207
|
|
| MD5 |
367b22157ccf6fd61357840b58caeda8
|
|
| BLAKE2b-256 |
1a0e81b758ee0056ac4bb558ec9ded907924c68da6c209772def4efb5e0dc862
|