fix v1

Author: marie

docs/csv/dwh_data/dwh_data.csv

@@ -1,13 +1,12 @@
 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," "
+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," "
+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," "
@@ -30,5 +29,5 @@ document_num,The identifier of the document grouping multiple related data recor
 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," "
+upload_id,"Identifier of the pipeline integration run, used to differentiate each batch of integrated data.",Defined at the start of the pipeline as `datetime.now().strftime("%Y%m%d%H%M%S")`. <br> For example a batch integrated on 15/09/2025 at 00:00:00 has `upload_id = 20250915000000`.,bigint(64),No,No,No," "
+update_date,Date and time of the record’s last update., ,timestamptz,No,No,No," "

docs/csv/dwh_document.csv

@@ -1,12 +1,11 @@
 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
+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_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," "
+displayed_text,The content of the document.,Convert to html,text,Yes,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
@@ -19,5 +18,5 @@ 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," "
+upload_id,"Identifier of the pipeline integration run, used to differentiate each batch of integrated data.",Defined at the start of the pipeline as `datetime.now().strftime("%Y%m%d%H%M%S")`. <br> For example a batch integrated on 15/09/2025 at 00:00:00 has `upload_id = 20250915000000`.,bigint(64),No,No,No," "
+update_date,Date and time of the record’s last update., ,timestamptz,No,No,No," "

docs/csv/dwh_patient.csv

@@ -1,23 +1,23 @@
 Field,User Guide,ETL Conventions,Datatype,Required,Primary Key,Foreign Key,FK Table
 patient_num,Unique identifier, ,bigint(64),Yes,Yes,No," "
-lastname, ,*null* in CNIL compliant warehouse,varchar(100),No,No,No," "
+lastname, ,*null* in CNIL compliant warehouse,varchar(120),No,No,No," "
 maiden_name, ,*null* in CNIL compliant warehouse,varchar(120),No,No,No," "
-firstname, ,*null* in CNIL compliant warehouse,varchar(100),No,No,No," "
+firstname, ,*null* in CNIL compliant warehouse,varchar(120),No,No,No," "
 birth_date, ,"If the precise date include day or month is not known or not allowed, January is used as the default month, and the first day of the month the default day",timestamptz,No,No,No," "
-sex,Biological sex at birth,"*F* (female), *M* (male), empty if unknown",varchar(2),No,No,No," "
+sex,Biological sex at birth,"*F* (female), *M* (male), *O* (other), empty if unknown",varchar(2),No,No,No," "
 nss,Social security number,*null* in CNIL compliant warehouse,varchar(20),No,No,No," "
-phone_number, ,*null* in CNIL compliant warehouse,varchar(1000),No,No,No," "
+phone_number, ,*null* in CNIL compliant warehouse,varchar(50),No,No,No," "
 email, ,*null* in CNIL compliant warehouse,varchar(500),No,No,No," "
 residence_address, ,*null* in CNIL compliant warehouse,varchar(1000),No,No,No," "
 residence_country, , ,varchar(100),No,No,No," "
 residence_city, , ,varchar(200),No,No,No," "
 zip_code, , ,varchar(30),No,No,No," "
 birth_country, , ,varchar(100),No,No,No," "
-birth_city, , ,varchar(100),No,No,No," "
-birth_zip_code, , ,varchar(10),No,No,No," "
+birth_city, , ,varchar(200),No,No,No," "
+birth_zip_code, , ,varchar(30),No,No,No," "
 death_code,Vital status,"*null* if alive, *d* if dead",varchar(2),No,No,No," "
 death_date,Date of death,"If the precise date include day or month is not known or not allowed, January is used as the default month, and the first day of the month the default day",timestamptz,No,No,No," "
-is_merged,Use to indicate this patient was merged in another patient,*true* if merged,boolean,No,No,No," "
+is_merged,Indicate this patient was merged in another patient,*true* if merged,boolean,No,No,No," "
 merged_into,Patient this one was merged into, ,bigint(64),No,No,Yes,dwh_patient
 max_date,The last time this patient came to the healthcare facility,Computed from the other table,date,No,No,No," "
 
@@ -26,5 +26,5 @@ instance_id,"Code of the healthcare center, see *hospital_instance* for more inf
 patient_pid,"Pseudo-identifier for the patient. Used in correspondence tables to retrieve the original patient identity if needed.",Generated as a SHA-256 hash of *id_patient_source* combined with *patient_salt*.,varchar(300),No,No,No," "
 patient_salt,Random salt used in the hash algorithm to generate patient_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., ,timestamptz,No,No,No," "
+upload_id,"Identifier of the pipeline integration run, used to differentiate each batch of integrated data.",Defined at the start of the pipeline as `datetime.now().strftime("%Y%m%d%H%M%S")`. <br> For example a batch integrated on 15/09/2025 at 00:00:00 has `upload_id = 20250915000000`.,bigint(64),No,No,No," "
+update_date,Date and time of the record’s last update., ,timestamptz,No,No,No," "

docs/csv/dwh_patient_ipphist.csv

@@ -1,10 +1,10 @@
 Field,User Guide,ETL Conventions,Datatype,Required,Primary Key,Foreign Key,FK Table
 ipphist_num,Unique identifier, ,bigint(64),Yes,Yes,No," "
 patient_num, , ,bigint(64),Yes,No,Yes,dwh_patient
-hospital_patient_id,Patient identifier in source data (IPP), ,varchar(100),`Yes`,No,No," "
+hospital_patient_id,Patient identifier in source data (IPP), ,varchar(100),Yes,No,No," "
 origin_patient_id,Use to separate real identifier from technical identifier (for instance pk in data source with no medical meaning) ,Set to *SIH* for real identifier,varchar(40),No,No,No," "
-master_patient_id,Indicate which identifier should be display to users. Each patient should have one and only one master identifier.,*true* if this identifier is the master,boolean,No,No,No," "
+master_patient_id,Indicate which identifier should be display to users. Each patient should have one and only one master identifier.,*true* if this identifier is the master,boolean,Yes,No,No," "
 instance_ipp_id,"Code of the healthcare center, see *hospital_instance* for more informations",Names accross all instance_id fields in other tables should match,varchar(40),No,No,No," "
 ipp_origin_code,Indicate source software for this record., ,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., ,timestamptz,No,No,No," "
+upload_id,"Identifier of the pipeline integration run, used to differentiate each batch of integrated data.",Defined at the start of the pipeline as `datetime.now().strftime("%Y%m%d%H%M%S")`. <br> For example a batch integrated on 15/09/2025 at 00:00:00 has `upload_id = 20250915000000`.,bigint(64),No,No,No," "
+update_date,Date and time of the record’s last update., ,timestamptz,No,No,No," "

docs/csv/dwh_patient_mvt.csv

@@ -1,16 +1,16 @@
 Field,User Guide,ETL Conventions,Datatype,Required,Primary Key,Foreign Key,FK Table
 mvt_num,Unique identifier, ,bigint(64),Yes,Yes,No," "
-patient_num, , ,bigint(64),`Yes`,No,Yes,dwh_patient
-stay_num,Use this field to link the movement record to its visit., ,bigint(64),`Yes`,No,Yes,dwh_patient_stay
+patient_num, , ,bigint(64),Yes,No,Yes,dwh_patient
+stay_num,Use this field to link the movement record to its visit., ,bigint(64),Yes,No,Yes,dwh_patient_stay
 
-entry_date,Admission date, ,timestamptz,`Yes`,No,No," "
+entry_date,Admission date, ,timestamptz,Yes,No,No," "
 out_date,Discharge date, ,timestamptz,No,No,No," "
 
-mvt_entry_mode,Indicates where a person was admitted from,"Values are not standardized yet. <br> Example values : *Transfert*, *Domicile*, *Mutation*",varchar(255),No,No,No," "
-mvt_exit_mode,Indicates where a person was discharged to,"Values are not standardized yet. <br> Example values : *Transfert*, *Domicile*, *Mutation*, *Décès*",varchar(300),No,No,No," "
+mvt_entry_mode,Indicates where a person was admitted from,"Values are not standardized yet. <br> Example values : *Transfert*, *Domicile*, *Mutation*",varchar(500),No,No,No," "
+mvt_exit_mode,Indicates where a person was discharged to,"Values are not standardized yet. <br> Example values : *Transfert*, *Domicile*, *Mutation*, *Décès*",varchar(500),No,No,No," "
 
-type_mvt,"Represents the kind of visit that took place (inpatient, outpatient, emergency, etc.)","**TODO** <br> *C* : Consultation<br> *J* : HDJ<br> *U* : Urgence<br> *H* : Hospitalisation<br> *A* : Ambulatoire<br> *S* : Séance<br> *AM* : Ambulatoire MCO<br> *AP* : Ambulatoire PSY",varchar(30),No,No,No," "
-mvt_order,Indicates the sequential order of patient movements within a visit.,"This derived field assigns a numeric ranking to each movement event, allowing reconstruction of the temporal flow of movements during a single visit (e.g., for visualization or analysis).",integer(32),No,No,No," "
+type_mvt,"Represents the kind of visit that took place (inpatient, outpatient, emergency, etc.)","*C* : Consultation<br> *J* : HDJ<br> *U* : Urgence<br> *H* : Hospitalisation<br> *A* : Ambulatoire<br> *S* : Séance<br> *AM* : Ambulatoire MCO<br> *AP* : Ambulatoire PSY<br> *E* : Externes",varchar(30),No,No,No," "
+mvt_order,Indicates the sequential order of patient movements within a visit.,"This derived field assigns a numeric ranking to each movement event based on ascending `mvt_entry_date`, allowing reconstruction of the temporal flow of movements during a single visit (e.g., for visualization or analysis).",integer(32),No,No,No," "
 
 department_num,Service of admission, ,bigint(64),No,No,Yes,dwh_thesaurus_department
 unit_num,Unit of admission, ,bigint(64),No,No,Yes,dwh_thesaurus_unit
@@ -22,5 +22,5 @@ id_mvt_source,Unique identifier in source software, ,varchar(300),No,No,No," "
 mvt_pid,"Optional pseudo-identifier for a movement. Mainly included for structural consistency; not required for standard analytical use.",Generated as a hash of *id_mvt_source* combined with *mvt_salt*.,varchar(300),No,No,No," "
 mvt_salt,Optional random salt used in the hash algorithm to generate *mvt_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., ,timestamptz,No,No,No," "
+upload_id,"Identifier of the pipeline integration run, used to differentiate each batch of integrated data.",Defined at the start of the pipeline as `datetime.now().strftime("%Y%m%d%H%M%S")`. <br> For example a batch integrated on 15/09/2025 at 00:00:00 has `upload_id = 20250915000000`.,bigint(64),No,No,No," "
+update_date,Date and time of the record’s last update., ,timestamptz,No,No,No," "

docs/csv/dwh_patient_stay.csv

@@ -1,15 +1,15 @@
 Field,User Guide,ETL Conventions,Datatype,Required,Primary Key,Foreign Key,FK Table
 stay_num,Unique identifier, ,bigint(64),Yes,Yes,No," "
-encounter_num,Encounter number,*null* in CNIL compliant warehouse,varchar(300),Yes,No,No," "
-patient_num, , ,bigint(64),`Yes`,No,Yes,dwh_patient
-entry_date,Admission date, ,timestamptz,`Yes`,No,No," "
+encounter_num,"Unique identifier of the patient visit, as recorded in the source hospital information system",*null* in CNIL compliant warehouse,varchar(300),Yes,No,No," "
+patient_num, , ,bigint(64),Yes,No,Yes,dwh_patient
+entry_date,Admission date, ,timestamptz,Yes,No,No," "
 out_date,Discharge date,*out_date* should be greater or equal than *entry_date*,timestamptz,No,No,No," "
-entry_mode,Indicates where a person was admitted from,"Values are not standardized yet.<br> Example values : *Transfert*, *Domicile*, *Mutation*",varchar(400),No,No,No," "
+entry_mode,Indicates where a person was admitted from,"Values are not standardized yet.<br> Example values : *Transfert*, *Domicile*, *Mutation*",varchar(500),No,No,No," "
 out_mode,Indicates where a person was discharged to after a visit,"Values are not standardized yet.<br> Example values : *Transfert*, *Domicile*, *Mutation*, *Décès*",varchar(500),No,No,No," "
-type_dos,"Represents the kind of visit that took place (inpatient, outpatient, emergency, etc.)","*Consultation*, *HDJ*, *HAD*, *Urgence*, *Hospitalisation*, *Ambulatoire*",varchar(10),No,No,No," "
+type_dos,"Represents the kind of visit that took place (inpatient, outpatient, emergency, etc.)","*Consultation*, *HDJ*, *HAD*, *Urgence*, *Hospitalisation*, *Ambulatoire*, *Externes*",varchar(50),No,No,No," "
 instance_stay_id,"Code of the healthcare center, see *hospital_instance* for more informations", ,varchar(40),No,No,No," "
 stay_origin_code,Indicate source software for this stay, ,varchar(300),No,No,No," "
 stay_pid,Pseudo identifier of the stay. Use in correspondence table to retrieve patient identity when needed., ,varchar(300),No,No,No," "
 stay_salt,Salt for hash algorithm, ,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., ,timestamptz,No,No,No," "
+upload_id,"Identifier of the pipeline integration run, used to differentiate each batch of integrated data.",Defined at the start of the pipeline as `datetime.now().strftime("%Y%m%d%H%M%S")`. <br> For example a batch integrated on 15/09/2025 at 00:00:00 has `upload_id = 20250915000000`.,bigint(64),No,No,No," "
+update_date,Date and time of the record’s last update., ,timestamptz,No,No,No," "

docs/csv/dwh_thesaurus_data.csv

@@ -1,13 +1,13 @@
 Field,User Guide,ETL Conventions,Datatype,Required,Primary Key,Foreign Key,FK Table
 thesaurus_data_num,Unique identifier, ,bigint(64),Yes,Yes,No," "
-thesaurus_code,"Identifier of the vocabulary or coding system (e.g. *CIM10*, *CCAM*, *ATC*).", ,varchar(30),`Yes`,No,No," "
-concept_code,"The concept code represents the identifier of the concept in the source vocabulary. Note that concept codes are not unique across vocabularies.", ,varchar(100),`Yes`,No,No," "
-concept_str,Human-readable name or label of the concept., ,varchar(2000),`Yes`,No,No," "
+thesaurus_code,"Identifier of the vocabulary or coding system (e.g. *CIM10*, *CCAM*, *ATC*).", ,varchar(30),Yes,No,No," "
+concept_code,"The concept code represents the identifier of the concept in the source vocabulary. Note that concept codes are not unique across vocabularies.", ,varchar(100),Yes,No,No," "
+concept_str,Human-readable name or label of the concept., ,varchar(2000),Yes,No,No," "
 description,Extended description or definition of the concept., ,varchar(4000),No,No,No," "
 measuring_unit,"Measurement unit for quantitative concepts (e.g., mg, mmHg).", ,varchar(50),No,No,No," "
-value_type,Type of value expected,"*numeric* : quantitative value <br> *text*: free-text value <br> *present* : presence/absence indicator <br> *liste* : enumerated values",varchar(50),`Yes`,No,No," "
+value_type,Type of value expected,"*numeric* : quantitative value <br> *text*: free-text value <br> *present* : presence/absence indicator <br> *liste* : enumerated values",varchar(50),Yes,No,No," "
 list_values,List of values when type is *liste* else *null*,"Values should be split by *;* (e.g. *principal;associé;relié*"),varchar(4000),No,No,No," "
 thesaurus_parent_num,Parent concept in the hierarchy., ,bigint(64),No,No,Yes,dwh_thesaurus_data
 count_data_used,Count of *dwh_data* associated with this concept, ,integer(32),No,No,No," "
-updated_date,Last modification of this record., ,date,Yes,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,Date and time of the record’s last update., ,timestamptz,No,No,No," "
+upload_id,"Identifier of the pipeline integration run, used to differentiate each batch of integrated data.",Defined at the start of the pipeline as `datetime.now().strftime("%Y%m%d%H%M%S")`. <br> For example a batch integrated on 15/09/2025 at 00:00:00 has `upload_id = 20250915000000`.,bigint(64),No,No,No," "