v1

Author: marie

.github/workflows/ci.yml

@@ -0,0 +1,29 @@
+name: ci
+on:
+  push:
+    branches:
+      - master
+      - main
+permissions:
+  contents: write
+jobs:
+  deploy:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+      - name: Configure Git Credentials
+        run: |
+          git config user.name github-actions[bot]
+          git config user.email 41898282+github-actions[bot]@users.noreply.github.com
+      - uses: actions/setup-python@v5
+        with:
+          python-version: 3.x
+      - run: echo "cache_id=$(date --utc '+%V')" >> $GITHUB_ENV
+      - uses: actions/cache@v4
+        with:
+          key: mkdocs-material-${{ env.cache_id }}
+          path: ~/.cache
+          restore-keys: |
+            mkdocs-material-
+      - run: pip install mkdocs-material
+      - run: mkdocs gh-deploy --force

.gitignore

@@ -0,0 +1,5 @@
+venv
+.idea
+.DS_Store
+generate/files/*
+.env

README.md

@@ -1,2 +1,16 @@
 # codoc-data-model-docs
  Definition and DDLs for the codoc data model 
+
+## Commands
+
+* `mkdocs new [dir-name]` - Create a new project.
+* `mkdocs serve` - Start the live-reloading docs server.
+* `mkdocs build` - Build the documentation site.
+* `mkdocs -h` - Print help message and exit.
+
+## Project layout
+
+    mkdocs.yml    # The configuration file.
+    docs/
+        index.md  # The documentation homepage.
+        ...       # Other markdown pages, images and other files.

docs/assets/diagram.png

@@ -0,0 +1,34 @@
+Field,User Guide,ETL Conventions,Datatype,Required,Primary Key,Foreign Key,FK Table
+data_num,Unique identifier, ,bigint(64),Yes,Yes,No," "
+patient_num, , ,bigint(64),`Yes`,No,Yes,dwh_patient
+thesaurus_data_num,"The concept identifier associated with the data record (e.g., diagnosis, procedure, lab test).", ,bigint(64),`Yes`,No,Yes,dwh_thesaurus_data
+thesaurus_code,"The source vocabulary code corresponding to the associated concept (e.g., ICD-10, LOINC, ATC).", ,varchar(40),`Yes`,No,No," "
+
+document_date,The date the data was recorded in the source system., ,timestamptz,`Yes`,No,No," "
+start_date,"The start date of the clinical event, observation or drugs.", ,timestamptz,`Yes`,No,No," "
+end_date,"The end date of the clinical event, observation or drugs, if applicable.", ,timestamptz,No,No,No," "
+age_patient,The age of the patient at the time of the data record., ,double(53),No,No,No," "
+
+
+val_numeric,"A numeric value associated with the data record (e.g., lab result, measurement).", ,double(53),No,No,No," "
+operator,"The operator applied to the value (e.g. *<*, *>*, *=*).", ,varchar(5),No,No,No," "
+
+val_text,A textual or categorical value associated with the data record., ,varchar(10000),No,No,No," "
+
+lower_bound,"The lower boundary of a value range, if applicable.", ,double(53),No,No,No," "
+upper_bound,"The upper boundary of a value range, if applicable.", ,double(53),No,No,No," "
+
+
+instance_data_id,"Code of the healthcare center, see *hospital_instance* for more informations.", ,varchar(40),No,No,No," "
+document_origin_code,Indicate source software for this record., ,varchar(60),No,No,No," "
+id_data_source,Unique identifier in source software., ,varchar(300),No,No,No," "
+
+stay_num,The visit during which the data record was generated., ,bigint(64),No,No,Yes,dwh_patient_stay
+department_num,The service associated with the data record., ,bigint(64),No,No,Yes,dwh_thesaurus_department
+document_num,The identifier of the document grouping multiple related data records (e.g. all results from a lab report)., ,bigint(64),No,No,Yes,dwh_document
+
+data_pid,"Optional pseudo-identifier for a data. Mainly included for structural consistency; not required for standard analytical use.",Generated as a hash of *id_data_source* combined with *data_salt*.,varchar(300),No,No,No," "
+data_salt,Optional random salt used in the hash algorithm to generate *data_pid*., ,varchar(300),No,No,No," "
+
+upload_id,ETL Pipeline identifier,Defined at the start of the pipeline as `datetime.now().strftime("%Y%m%d%H%M%S")`,bigint(64),No,No,No," "
+updated_date,Last modification of this record., ,date,Yes,No,No," "

docs/assets/favicon.png

@@ -0,0 +1,10 @@
+Field,User Guide,ETL Conventions,Datatype,Required,Primary Key,Foreign Key,FK Table
+frequency,"Frequency of drug administration (e.g. once daily, twice daily)", ,integer(32),No,No,No," "
+period,The duration of the prescription or administration period., ,integer(32),No,No,No," "
+period_unit,"The unit of time for the period (e.g. days, weeks, months).", ,varchar(25),No,No,No," "
+route,"The route of drug administration (e.g. oral, intravenous).", ,varchar(50),No,No,No," "
+data_status,"The status of the prescription or data record (e.g. prescribed, administered, cancelled)", ,varchar(20),No,No,No," "
+data_unit,"The unit of measure for the drug dose (e.g. mg, mL).", ,varchar(25),No,No,No," "
+daily_details,"Additional structured details about daily drug administration (e.g. morning/evening, meal-related intake).", ,varchar(400),No,No,No," "
+drug_condition,"Indicates whether the prescription is conditional.", ,boolean,No,No,No," "
+drug_condition_reason,"The clinical reason or trigger for a conditional prescription (e.g., *if needed*, *if severe pain*)"., ,varchar(4000),No,No,No," "

docs/assets/logo.svg

@@ -0,0 +1,4 @@
+Field,User Guide,ETL Conventions,Datatype,Required,Primary Key,Foreign Key,FK Table
+activity_form,The form of activity related to the PMSI coding.,"*30* : CMP <br> *31* : Outpatient care provided by other facilities than CMP or CATTP <br> *32* : CATTP",varchar(4),No,No,No," "
+intersectoriel_number,Identifier for inter-sectorial linkage of PMSI episodes., ,varchar(6),No,No,No," "
+residency_zip_code,Patient's residency postal code as recorded in PMSI., ,integer(32),No,No,No," "

docs/csv/dwh_data/dwh_data.csv

@@ -0,0 +1,23 @@
+Field,User Guide,ETL Conventions,Datatype,Required,Primary Key,Foreign Key,FK Table
+document_num,Unique identifier, ,bigint(64),Yes,Yes,No," "
+patient_num, , ,bigint(64),`Yes`,No,Yes,dwh_patient
+title, The title of the document. , ,varchar(400),No,No,No," "
+document_date,The date the document was recorded., ,timestamptz,`Yes`,No,No," "
+document_type,"The type of the document (e.g. CR, observation, formulaire, ...)", ,varchar(100),No,No,No," "
+author,The person who created or authored the document, ,varchar(200),No,No,No," "
+displayed_text,The content of the document.,Convert to html,text,`Yes`,No,No," "
+age_patient,The age of the patient at the time the document was created., ,integer(32),No,No,No," "
+
+stay_num,The visit during which the document was created., ,bigint(64),No,No,Yes,dwh_patient_stay
+department_num,The service associated with the document. , ,bigint(64),No,No,Yes,dwh_thesaurus_department
+unit_num,The care unit associated with the document., ,bigint(64),No,No,Yes,dwh_thesaurus_unit
+
+instance_document_id,"Code of the healthcare center, see *hospital_instance* for more informations", ,varchar(40),No,No,No," "
+document_origin_code,Indicate source software for this document, ,varchar(60),No,No,No," "
+id_doc_source,Unique identifier in source software, ,varchar(300),No,No,No," "
+
+document_pid,"Optional pseudo-identifier for a document. Mainly included for structural consistency; not required for standard analytical use.",Generated as a hash of *id_doc_source* combined with *document_salt*.,varchar(300),No,No,No," "
+document_salt,Optional random salt used in the hash algorithm to generate *document_pid*., ,varchar(300),No,No,No," "
+
+upload_id,ETL Pipeline identifier,Defined at the start of the pipeline as `datetime.now().strftime("%Y%m%d%H%M%S")`,bigint(64),No,No,No," "
+update_date,Last modification of this record., ,date,No,No,No," "