Refactor code and description columns

ci_testing/models/encounter.sql

@@ -12,7 +12,9 @@ cast(null as {{ dbt.type_string() }} ) as encounter_id
 , cast(null as {{ dbt.type_string() }} ) as discharge_disposition_code
 , cast(null as {{ dbt.type_string() }} ) as discharge_disposition_description
 , cast(null as {{ dbt.type_string() }} ) as attending_provider_id
-, cast(null as {{ dbt.type_string() }} ) as facility_npi
+, cast(null as {{ dbt.type_string() }} ) as attending_provider_name
+, cast(null as {{ dbt.type_string() }} ) as facility_id
+, cast(null as {{ dbt.type_string() }} ) as facility_name
 , cast(null as {{ dbt.type_string() }} ) as primary_diagnosis_code_type
 , cast(null as {{ dbt.type_string() }} ) as primary_diagnosis_code
 , cast(null as {{ dbt.type_string() }} ) as primary_diagnosis_description

dbt_project.yml

@@ -182,7 +182,7 @@ seeds:
           +post-hook: "{{ load_seed('tuva-public-resources/versioned_value_sets/0.8.7','cms_hcc_payment_hcc_count_factors.csv',compression=true,null_marker=true) }}"
       data_quality:
         data_quality__test_catalog:
-          +post-hook: "{{ load_seed('tuva-public-resources/versioned_value_sets/0.8.7','data_quality_test_catalog.csv',compression=true,null_marker=true) }}"
+          +post-hook: "{{ load_seed('tuva-public-resources/versioned_value_sets/0.9.0','data_quality_test_catalog.csv',compression=true,null_marker=true) }}"
       ed_classification:
         ed_classification__categories:
           +post-hook: "{{ load_seed('tuva-public-resources/versioned_value_sets/0.8.7','ed_classification_categories.csv',compression=true,null_marker=true) }}"

integration_tests/dbt_project.yml

@@ -8,7 +8,7 @@ vars:
   error_empty_seeds: true
   ## Use this variable to run the project with synthetic data loaded as seeds
   # otherwise set to false and set the input vars below
-  use_synthetic_data: true
+  use_synthetic_data: false
 
   ## Update these vars to use your own data as input, do not comment out
   # enabled logic has been added to the sources config

integration_tests/docs_generate/models/_models.yml

@@ -7,6 +7,7 @@ models:
       database: tuva
       schema: input_layer
       tags: input_layer
+      materialized: table
     description: > 
       The eligibility table includes information about a patient's health 
       insurance coverage and demographics (note: we use the word patient as a 
@@ -98,6 +99,7 @@ models:
       database: tuva
       schema: input_layer
       tags: input_layer
+      materialized: table
     description: > 
       The medical_claim table contains information on healthcare services and 
       supplies provided to patients, billed by providers, and paid for by health 
@@ -696,6 +698,7 @@ models:
       database: tuva
       schema: input_layer
       tags: input_layer
+      materialized: table
     description: >
       The pharmacy_claim table includes information about retail and specialty 
       drug prescriptions that have been filled by a patient, billed by a 
@@ -772,6 +775,7 @@ models:
       database: tuva
       schema: input_layer
       tags: input_layer
+      materialized: table
     description: >
       The condition table contains information related to medical conditions 
       patients have, including problems, admitting diagnosis codes, and billable 
@@ -851,6 +855,7 @@ models:
       database: tuva
       schema: input_layer
       tags: input_layer
+      materialized: table
     description: >
       The encounter table contains information about patients visits (i.e. 
       encounters).  This includes acute inpatient, emergency department, office 
@@ -898,10 +903,13 @@ models:
         meta:
           terminology: https://github.com/tuva-health/the_tuva_project/blob/main/seeds/terminology/terminology__provider.csv
           terminology_note: "**Note: this terminology set is too large to be loaded as a seed and is instead loaded from public cloud storage for supported adapters."
-      - name: facility_npi
+      - name: facility_id
+        description: >
+          Facility identifier for the encounter (typically represents the facility where services were performed).  Can
+          be an NPI or source code.
+      - name: facility_name
         description: >
-          Facility NPI for the encounter (typically represents the facility 
-          where services were performed).
+          Facility name for the encounter (typically represents the facility where services were performed).
         meta:
           terminology: https://github.com/tuva-health/the_tuva_project/blob/main/seeds/terminology/terminology__provider.csv
           terminology_note: "**Note: this terminology set is too large to be loaded as a seed and is instead loaded from public cloud storage for supported adapters."
@@ -957,6 +965,7 @@ models:
       database: tuva
       schema: input_layer
       tags: input_layer
+      materialized: table
     description: >
       The lab result table contains information about lab test results, 
       including the LOINC code and description, units, reference range, and 
@@ -1052,6 +1061,7 @@ models:
       database: tuva
       schema: input_layer
       tags: input_layer
+      materialized: table
     description: >
       The location table contains information on practice and facility locations 
       where patients receive medical care.
@@ -1167,6 +1177,7 @@ models:
       database: tuva
       schema: input_layer
       tags: input_layer
+      materialized: table
     description: >
       The observation table contains information on measurements other than lab 
       tests e.g. blood pressure, height, and weight.
@@ -1226,6 +1237,7 @@ models:
       database: tuva
       schema: input_layer
       tags: input_layer
+      materialized: table
     description: >
       The patient table contains demographic and geographic information on 
       patients.
@@ -1282,6 +1294,7 @@ models:
       database: tuva
       schema: input_layer
       tags: input_layer
+      materialized: table
     description: >
       The practitioner table contains information on the providers in the 
       dataset e.g. physicians, physicians assistants, etc.
@@ -1321,6 +1334,7 @@ models:
       database: tuva
       schema: input_layer
       tags: input_layer
+      materialized: table
     description: >
       The procedure table contains information on procedures that were performed 
       on patients in the dataset.

integration_tests/docs_generate/models/encounter.sql

@@ -12,7 +12,9 @@ select
     , cast(null as {{ dbt.type_string() }} ) as discharge_disposition_code
     , cast(null as {{ dbt.type_string() }} ) as discharge_disposition_description
     , cast(null as {{ dbt.type_string() }} ) as attending_provider_id
-    , cast(null as {{ dbt.type_string() }} ) as facility_npi
+    , cast(null as {{ dbt.type_string() }} ) as attending_provider_name
+    , cast(null as {{ dbt.type_string() }} ) as facility_id
+    , cast(null as {{ dbt.type_string() }} ) as facility_name
     , cast(null as {{ dbt.type_string() }} ) as primary_diagnosis_code_type
     , cast(null as {{ dbt.type_string() }} ) as primary_diagnosis_code
     , cast(null as {{ dbt.type_string() }} ) as primary_diagnosis_description

integration_tests/docs_generate/models/medical_claim.sql

@@ -141,6 +141,7 @@ select
     , procedure_date_24
     , procedure_date_25
     , data_source
+    , in_network_flag
     , file_name
     , ingest_datetime
 from {{ ref('medical_claim_seed') }}

integration_tests/docs_generate/models/pharmacy_claim.sql

@@ -19,6 +19,7 @@ select
     , copayment_amount
     , deductible_amount
     , data_source
+    , in_network_flag
     , file_name
     , ingest_datetime
 from {{ ref('pharmacy_claim_seed') }}

integration_tests/models/encounter.sql

@@ -21,7 +21,9 @@ cast(null as {{ dbt.type_string() }} ) as encounter_id
 , cast(null as {{ dbt.type_string() }} ) as discharge_disposition_code
 , cast(null as {{ dbt.type_string() }} ) as discharge_disposition_description
 , cast(null as {{ dbt.type_string() }} ) as attending_provider_id
-, cast(null as {{ dbt.type_string() }} ) as facility_npi
+, cast(null as {{ dbt.type_string() }} ) as attending_provider_name
+, cast(null as {{ dbt.type_string() }} ) as facility_id
+, cast(null as {{ dbt.type_string() }} ) as facility_name
 , cast(null as {{ dbt.type_string() }} ) as primary_diagnosis_code_type
 , cast(null as {{ dbt.type_string() }} ) as primary_diagnosis_code
 , cast(null as {{ dbt.type_string() }} ) as primary_diagnosis_description

models/ahrq_measures/pqi/final/ahrq_measures__pqi_summary.sql

@@ -8,7 +8,7 @@ select p.pqi_number
  , e.encounter_id
  , e.data_source
  , e.patient_id
- , e.facility_npi
+ , e.facility_id
  , e.ms_drg_code
  , e.ms_drg_description
  , e.encounter_start_date
@@ -17,7 +17,7 @@ select p.pqi_number
  , e.paid_amount
  , '{{ var('tuva_last_run')}}' as tuva_last_run
 from {{ref('ahrq_measures__pqi_num_long')}} p 
-inner join {{ref('ahrq_measures__stg_pqi_inpatient_encounter')}} e on p.encounter_id = e.encounter_id
-and
-p.data_source = e.data_source
+inner join {{ref('ahrq_measures__stg_pqi_inpatient_encounter')}} e
+    on p.encounter_id = e.encounter_id
+    and p.data_source = e.data_source
 inner join {{ ref('pqi__measures') }} m on cast(p.pqi_number as {{ dbt.type_string() }})  = m.pqi_number

models/ahrq_measures/pqi/staging/ahrq_measures__stg_pqi_inpatient_encounter.sql

@@ -13,7 +13,7 @@ select
   , length_of_stay
   , primary_diagnosis_code
   , patient_id
-  , facility_npi
+  , facility_id
   , paid_amount
   , {{ date_part('YEAR', 'encounter_start_date') }} as year_number
 from 

models/claims_preprocessing/acute_inpatient/final/acute_inpatient__summary.sql

@@ -19,7 +19,7 @@ inner join {{ ref('acute_inpatient__encounter_start_and_end_dates') }} b
         b.encounter_id
         , first.diagnosis_code_1
         , first.diagnosis_code_type
-        , first.facility_npi as facility_npi
+        , first.facility_id as facility_id
         , first.ms_drg_code as ms_drg_code
         , first.apr_drg_code as apr_drg_code
         , first.admit_source_code as admit_source_code
@@ -44,7 +44,7 @@ inner join {{ ref('acute_inpatient__encounter_start_and_end_dates') }} b
         b.encounter_id
         , first.diagnosis_code_1
         , first.diagnosis_code_type
-        , first.facility_npi
+        , first.facility_id
         , first.ms_drg_code
         , first.apr_drg_code
         , first.admit_source_code
@@ -75,17 +75,16 @@ group by 1
     from {{ ref('acute_inpatient__stg_eligibility') }}
     )
 
-, provider as (
+, facility as (
     select
         a.encounter_id
-        , max(a.facility_npi) as facility_npi
-        , b.provider_first_name
-        , b.provider_last_name
-        , count(distinct facility_npi) as npi_count
+        , max(a.facility_id) as facility_id
+        , b.provider_organization_name
+        , count(distinct facility_id) as npi_count
     from {{ ref('acute_inpatient__institutional_encounter_id') }} a
     left join {{ ref('terminology__provider') }} b
-    on a.facility_npi = b.npi
-    group by 1,3,4
+    on a.facility_id = b.npi
+    group by 1,3
 )
 
 select
@@ -99,9 +98,8 @@ select
 , c.diagnosis_code_type as primary_diagnosis_code_type
 , c.diagnosis_code_1 as primary_diagnosis_code
 , coalesce(icd10cm.long_description, icd9cm.long_description) as primary_diagnosis_description
-, f.facility_npi
-, f.provider_first_name
-, f.provider_last_name
+, f.facility_id as facility_id
+, f.provider_organization_name as facility_name
 , c.ms_drg_code
 , j.ms_drg_description
 , j.medical_surgical
@@ -130,7 +128,7 @@ left join professional_claim_details d
   on a.encounter_id = d.encounter_id
 left join patient e
   on a.patient_id = e.patient_id
-left join provider f
+left join facility f
   on a.encounter_id = f.encounter_id
 left join {{ ref('terminology__discharge_disposition') }} g
   on c.discharge_disposition_code = g.discharge_disposition_code

models/claims_preprocessing/acute_inpatient/intermediate/acute_inpatient__data_quality_summary.sql

@@ -206,18 +206,18 @@ from {{ ref('acute_inpatient__institutional_claims') }}
 ),
 
 
-facility_npi_not_unique as (
+facility_id_not_unique as (
 select
-  '22 facility_npi_not_unique' as field,
-  sum(facility_npi_not_unique) as total_count
+  '22 facility_id_not_unique' as field,
+  sum(facility_id_not_unique) as total_count
 from {{ ref('acute_inpatient__institutional_claims') }}
 ),
 
 
-facility_npi_missing as (
+facility_id_missing as (
 select
-  '23 facility_npi_missing' as field,
-  sum(facility_npi_missing) as total_count
+  '23 facility_id_missing' as field,
+  sum(facility_id_missing) as total_count
 from {{ ref('acute_inpatient__institutional_claims') }}
 ),
 
@@ -378,12 +378,12 @@ from discharge_disposition_code_missing
 union all
 
 select *
-from facility_npi_not_unique
+from facility_id_not_unique
 
 union all
 
 select *
-from facility_npi_missing
+from facility_id_missing
 
 union all
 

models/claims_preprocessing/acute_inpatient/intermediate/acute_inpatient__first_claim_values.sql

@@ -1,34 +1,35 @@
-{{ config(
-     enabled = var('claims_preprocessing_enabled',var('claims_enabled',var('tuva_marts_enabled',False))) | as_bool
-   )
-}}
-
-with first_claim_values as(
-    select distinct
-        e.encounter_id
-        , coalesce(claim_start_date, admission_date) as claim_start
-        , diagnosis_code_1
-        , diagnosis_code_type
-        , admit_source_code
-        , admit_type_code
-        , facility_npi
-        , ms_drg_code
-        , apr_drg_code
-    from {{ ref('acute_inpatient__encounter_id')}} e
-    inner join {{ ref('acute_inpatient__stg_medical_claim') }} m
-        on e.claim_id = m.claim_id
-    where claim_type = 'institutional'
-)
-
-select
-    encounter_id
-    , claim_start
-    , diagnosis_code_1
-    , diagnosis_code_type
-    , admit_source_code
-    , admit_type_code
-    , facility_npi
-    , ms_drg_code
-    , apr_drg_code
-    , row_number() over (partition by encounter_id order by claim_start) as claim_row
-from first_claim_values
+{{ config(
+     enabled = var('claims_preprocessing_enabled',var('claims_enabled',var('tuva_marts_enabled',False)))
+ | as_bool
+   )
+}}
+
+with first_claim_values as(
+    select distinct
+        e.encounter_id
+        , coalesce(claim_start_date, admission_date) as claim_start
+        , diagnosis_code_1
+        , diagnosis_code_type
+        , admit_source_code
+        , admit_type_code
+        , facility_id
+        , ms_drg_code
+        , apr_drg_code
+    from {{ ref('acute_inpatient__encounter_id')}} e
+    inner join {{ ref('acute_inpatient__stg_medical_claim') }} m
+        on e.claim_id = m.claim_id
+    where claim_type = 'institutional'
+)
+
+select
+    encounter_id
+    , claim_start
+    , diagnosis_code_1
+    , diagnosis_code_type
+    , admit_source_code
+    , admit_type_code
+    , facility_id
+    , ms_drg_code
+    , apr_drg_code
+    , row_number() over (partition by encounter_id order by claim_start) as claim_row
+from first_claim_values