[DC-3793] Update self_reported_population to self_reported_category

all-of-us · nishanthpp93 · Jun 28, 2024 · Jun 24, 2024 · Jun 24, 2024 · 36acdd4f43318f283c9cc10bd75d3362443c5098
commit 36acdd4f43318f283c9cc10bd75d3362443c5098
diff --git a/data_steward/analytics/cdr_ops/cross_ct_rt/output_prod_publish_qc.py b/data_steward/analytics/cdr_ops/cross_ct_rt/output_prod_publish_qc.py
@@ -91,9 +91,9 @@
 # 3. sex_at_birth_source_value
 # 4. state_of_residence_concept_id
 # 5. state_of_residence_source_value
-# 6. self_reported_population_concept_id
-# 7. self_reported_population_source_value
-# 8. self_reported_population_source_concept_id<br>
+# 6. self_reported_category_concept_id
+# 7. self_reported_category_source_value
+# 8. self_reported_category_source_concept_id<br>
 #
 #
 # Investigate any failed output.
@@ -119,12 +119,12 @@
   ,COUNTIF((p.sex_at_birth_source_value IS NULL AND pe.sex_at_birth_source_value IS NOT NULL)
       OR (p.sex_at_birth_source_value IS NOT NULL AND pe.sex_at_birth_source_value IS NULL)) as ne_nulls_sex_at_birth_source_value
 -- check self reported population columns --
-  ,COUNTIF((p.self_reported_population_concept_id IS NULL AND pe.self_reported_population_concept_id IS NOT NULL)
-      OR (p.self_reported_population_concept_id IS NOT NULL AND pe.self_reported_population_concept_id IS NULL)) as ne_nulls_self_reported_population_concept_id
-  ,COUNTIF((p.self_reported_population_source_value IS NULL AND pe.self_reported_population_source_value IS NOT NULL)
-      OR (p.self_reported_population_source_value IS NOT NULL AND pe.self_reported_population_source_value IS NULL)) as ne_nulls_self_reported_population_source_value
-  ,COUNTIF((p.self_reported_population_source_concept_id IS NULL AND pe.self_reported_population_source_concept_id IS NOT NULL)
-      OR (p.self_reported_population_source_concept_id IS NOT NULL AND pe.self_reported_population_source_concept_id IS NULL)) as ne_nulls_self_reported_population_source_concept_id
+  ,COUNTIF((p.self_reported_category_concept_id IS NULL AND pe.self_reported_category_concept_id IS NOT NULL)
+      OR (p.self_reported_category_concept_id IS NOT NULL AND pe.self_reported_category_concept_id IS NULL)) as ne_nulls_self_reported_category_concept_id
+  ,COUNTIF((p.self_reported_category_source_value IS NULL AND pe.self_reported_category_source_value IS NOT NULL)
+      OR (p.self_reported_category_source_value IS NOT NULL AND pe.self_reported_category_source_value IS NULL)) as ne_nulls_self_reported_category_source_value
+  ,COUNTIF((p.self_reported_category_source_concept_id IS NULL AND pe.self_reported_category_source_concept_id IS NOT NULL)
+      OR (p.self_reported_category_source_concept_id IS NOT NULL AND pe.self_reported_category_source_concept_id IS NULL)) as ne_nulls_self_reported_category_source_concept_id
 FROM `{{dest_project_id}}.{{dest_dataset_id}}.person` p
 JOIN `{{dest_project_id}}.{{dest_dataset_id}}.person_ext` pe
 USING (person_id)
@@ -241,9 +241,9 @@
 UNION ALL 
 
 SELECT
-'nulls_self_reported_population_concept_id_check' AS check
+'nulls_self_reported_category_concept_id_check' AS check
 ,CASE
-    WHEN c.ne_nulls_self_reported_population_concept_id > 0
+    WHEN c.ne_nulls_self_reported_category_concept_id > 0
       THEN 'FAILED'
       ELSE 'passed'
       END AS result
@@ -252,9 +252,9 @@
 UNION ALL
 
 SELECT
-'self_reported_population_source_value_check' AS check
+'self_reported_category_source_value_check' AS check
 ,CASE
-    WHEN c.ne_nulls_self_reported_population_source_value > 0
+    WHEN c.ne_nulls_self_reported_category_source_value > 0
       THEN 'FAILED'
       ELSE 'passed'
       END AS result
@@ -263,9 +263,9 @@
 UNION ALL 
 
 SELECT
-'null_self_reported_population_source_concept_id_check' AS check
+'null_self_reported_category_source_concept_id_check' AS check
 ,CASE
-    WHEN c.ne_nulls_self_reported_population_source_concept_id > 0
+    WHEN c.ne_nulls_self_reported_category_source_concept_id > 0
       THEN 'FAILED'
       ELSE 'passed'
       END AS result
@@ -285,9 +285,9 @@
 # 3. sex_at_birth_source_value
 # 4. state_of_residence_concept_id
 # 5. state_of_residence_source_value
-# 6. self_reported_population_concept_id
-# 7. self_reported_population_source_value
-# 8. self_reported_population_source_concept_id<br>
+# 6. self_reported_category_concept_id
+# 7. self_reported_category_source_value
+# 8. self_reported_category_source_concept_id<br>
 #
 # Investigate any failed output.
 
@@ -312,12 +312,12 @@
     ,COUNTIF((p.sex_at_birth_source_value IS NULL AND pe.sex_at_birth_source_value IS NOT NULL)
         OR(p.sex_at_birth_source_value IS NOT NULL AND pe.sex_at_birth_source_value IS NULL)) AS ne_nulls_sex_at_birth_source_value
 -- check self reported population columns --
-  ,COUNTIF((p.self_reported_population_concept_id IS NULL AND pe.self_reported_population_concept_id IS NOT NULL)
-      OR (p.self_reported_population_concept_id IS NOT NULL AND pe.self_reported_population_concept_id IS NULL)) as ne_nulls_self_reported_population_concept_id
-  ,COUNTIF((p.self_reported_population_source_value IS NULL AND pe.self_reported_population_source_value IS NOT NULL)
-      OR (p.self_reported_population_source_value IS NOT NULL AND pe.self_reported_population_source_value IS NULL)) as ne_nulls_self_reported_population_source_value
-  ,COUNTIF((p.self_reported_population_source_concept_id IS NULL AND pe.self_reported_population_source_concept_id IS NOT NULL)
-      OR (p.self_reported_population_source_concept_id IS NOT NULL AND pe.self_reported_population_source_concept_id IS NULL)) as ne_nulls_self_reported_population_source_concept_id
+  ,COUNTIF((p.self_reported_category_concept_id IS NULL AND pe.self_reported_category_concept_id IS NOT NULL)
+      OR (p.self_reported_category_concept_id IS NOT NULL AND pe.self_reported_category_concept_id IS NULL)) as ne_nulls_self_reported_category_concept_id
+  ,COUNTIF((p.self_reported_category_source_value IS NULL AND pe.self_reported_category_source_value IS NOT NULL)
+      OR (p.self_reported_category_source_value IS NOT NULL AND pe.self_reported_category_source_value IS NULL)) as ne_nulls_self_reported_category_source_value
+  ,COUNTIF((p.self_reported_category_source_concept_id IS NULL AND pe.self_reported_category_source_concept_id IS NOT NULL)
+      OR (p.self_reported_category_source_concept_id IS NOT NULL AND pe.self_reported_category_source_concept_id IS NULL)) as ne_nulls_self_reported_category_source_concept_id
 FROM `{{dest_project_id}}.{{dest_dataset_id}}.person` p
 JOIN `{{src_project_id}}.{{src_dataset_id}}.person_ext` pe
 USING(person_id))
@@ -436,9 +436,9 @@
 UNION ALL 
 
 SELECT
-'nulls_self_reported_population_concept_id_check' AS check
+'nulls_self_reported_category_concept_id_check' AS check
 ,CASE
-    WHEN c.ne_nulls_self_reported_population_concept_id > 0
+    WHEN c.ne_nulls_self_reported_category_concept_id > 0
       THEN 'FAILED'
       ELSE 'passed'
       END AS result
@@ -447,9 +447,9 @@
 UNION ALL
 
 SELECT
-'self_reported_population_source_value_check' AS check
+'self_reported_category_source_value_check' AS check
 ,CASE
-    WHEN c.ne_nulls_self_reported_population_source_value > 0
+    WHEN c.ne_nulls_self_reported_category_source_value > 0
       THEN 'FAILED'
       ELSE 'passed'
       END AS result
@@ -458,9 +458,9 @@
 UNION ALL 
 
 SELECT
-'null_self_reported_population_source_concept_id_check' AS check
+'null_self_reported_category_source_concept_id_check' AS check
 ,CASE
-    WHEN c.ne_nulls_self_reported_population_source_concept_id > 0
+    WHEN c.ne_nulls_self_reported_category_source_concept_id > 0
       THEN 'FAILED'
       ELSE 'passed'
       END AS result
@@ -623,4 +623,4 @@
     Investigation needed.
 '''
 render_message(df, success_msg, failure_msg)
-# -
+# -
diff --git a/data_steward/analytics/cdr_ops/rt_cdr_qc/cdr_deid_base_qa_report1.py b/data_steward/analytics/cdr_ops/rt_cdr_qc/cdr_deid_base_qa_report1.py
@@ -20,6 +20,7 @@
 from utils import auth
 from gcloud.bq import BigQueryClient
 from analytics.cdr_ops.notebook_utils import execute, IMPERSONATION_SCOPES
+
 pd.options.display.max_rows = 120
 
 # + tags=["parameters"]
@@ -77,7 +78,6 @@
     AND value_as_concept_id = 45883720)
 """)
 
-
 q = query.render(project_id=project_id, deid_base_cdr=deid_base_cdr)
 result = execute(client, q)
 
@@ -394,7 +394,7 @@
 df1
 
 # Query 2.5 "Race Ethnicity: person_ext self reported population DC-3787"
-# Verify that the person_ext self_reported_population fields are populated correctly. 
+# Verify that the person_ext self_reported_category fields are populated correctly. 
 
 # has to be deid_base
 query = JINJA_ENV.from_string("""
@@ -409,35 +409,35 @@
         ORDER BY person_id, value_source_concept_id)
       GROUP BY 1))
 
-SELECT DISTINCT races, c_races, race_source_value, ethnicity_source_value,  race_source_concept_id, race_concept_id, self_reported_population_source_value,  self_reported_population_source_concept_id, self_reported_population_concept_id
+SELECT DISTINCT races, c_races, race_source_value, ethnicity_source_value,  race_source_concept_id, race_concept_id, self_reported_category_source_value,  self_reported_category_source_concept_id, self_reported_category_concept_id
 FROM obs
 LEFT JOIN `{{project_id}}.{{deid_base_cdr}}.person`
 USING (person_id)
 LEFT JOIN `{{project_id}}.{{deid_base_cdr}}.person_ext`
 USING (person_id)
 WHERE 
 -- check srp column multi pop --
-  (REGEXP_CONTAINS(obs.c_races,  r'\|')  AND self_reported_population_source_value != 'WhatRaceEthnicity_GeneralizedMultPopulations' )
+  (REGEXP_CONTAINS(obs.c_races,  r'\|')  AND self_reported_category_source_value != 'WhatRaceEthnicity_GeneralizedMultPopulations' )
 -- check srp column single pop not hispanic--
-  OR (NOT (REGEXP_CONTAINS(obs.c_races,  r'\|') )) AND (race_source_value != self_reported_population_source_value AND (race_source_value = 'AoUDRC_NoneIndicated' AND self_reported_population_source_value != 'WhatRaceEthnicity_Hispanic'))
+  OR (NOT (REGEXP_CONTAINS(obs.c_races,  r'\|') )) AND (race_source_value != self_reported_category_source_value AND (race_source_value = 'AoUDRC_NoneIndicated' AND self_reported_category_source_value != 'WhatRaceEthnicity_Hispanic'))
 -- check srp column single pop hispanic--
-  OR (race_source_value = 'AoUDRC_NoneIndicated' AND self_reported_population_source_value != 'WhatRaceEthnicity_Hispanic')
+  OR (race_source_value = 'AoUDRC_NoneIndicated' AND self_reported_category_source_value != 'WhatRaceEthnicity_Hispanic')
 -- check only expected srpsv exist --
-  OR (self_reported_population_source_value NOT IN ('WhatRaceEthnicity_GeneralizedMultPopulations','WhatRaceEthnicity_GeneralizedPopulation', 'WhatRaceEthnicity_Black','WhatRaceEthnicity_White','WhatRaceEthnicity_Asian' ,'WhatRaceEthnicity_Hispanic','PMI_PreferNotToAnswer', 'PMI_Skip', 'WhatRaceEthnicity_RaceEthnicityNoneOfThese','WhatRaceEthnicity_AIAN',
+  OR (self_reported_category_source_value NOT IN ('WhatRaceEthnicity_GeneralizedMultPopulations','WhatRaceEthnicity_GeneralizedPopulation', 'WhatRaceEthnicity_Black','WhatRaceEthnicity_White','WhatRaceEthnicity_Asian' ,'WhatRaceEthnicity_Hispanic','PMI_PreferNotToAnswer', 'PMI_Skip', 'WhatRaceEthnicity_RaceEthnicityNoneOfThese','WhatRaceEthnicity_AIAN',
 'WhatRaceEthnicity_MENA','WhatRaceEthnicity_NHPI'))
 -- check for expected concept_ids per srpsv --
-  OR (self_reported_population_source_value = 'WhatRaceEthnicity_GeneralizedMultPopulations' AND (self_reported_population_concept_id != 2000000008 OR self_reported_population_source_concept_id != 2000000008))
-  OR (self_reported_population_source_value = 'WhatRaceEthnicity_GeneralizedPopulation' AND (self_reported_population_concept_id != 2000000001 OR self_reported_population_source_concept_id != 2000000001))
-  OR (self_reported_population_source_value = 'WhatRaceEthnicity_Black' AND (self_reported_population_concept_id != 8516 OR self_reported_population_source_concept_id != 1586143))
-  OR (self_reported_population_source_value = 'WhatRaceEthnicity_White' AND (self_reported_population_concept_id != 8527 OR self_reported_population_source_concept_id != 1586146))
-  OR (self_reported_population_source_value = 'WhatRaceEthnicity_Asian' AND (self_reported_population_concept_id != 8515 OR self_reported_population_source_concept_id != 1586142))
-  OR (self_reported_population_source_value = 'WhatRaceEthnicity_Hispanic' AND (self_reported_population_concept_id != 1586147 OR self_reported_population_source_concept_id != 1586147))
-  OR (self_reported_population_source_value = 'PMI_PreferNotToAnswer' AND (self_reported_population_concept_id != 1177221 OR self_reported_population_source_concept_id != 903079))
-  OR (self_reported_population_source_value = 'PMI_Skip' AND (self_reported_population_concept_id != 903096 OR self_reported_population_source_concept_id != 903096))
-  OR (self_reported_population_source_value = 'WhatRaceEthnicity_RaceEthnicityNoneOfThese' AND (self_reported_population_concept_id != 45882607 OR self_reported_population_source_concept_id != 1586148))
-  OR (self_reported_population_source_value = 'WhatRaceEthnicity_AIAN' AND (self_reported_population_concept_id != 8657 OR self_reported_population_source_concept_id != 1586141)) -- ct only --
-  OR (self_reported_population_source_value = 'WhatRaceEthnicity_MENA' AND (self_reported_population_concept_id != 38003615 OR self_reported_population_source_concept_id != 1586144)) -- ct only --
-  OR (self_reported_population_source_value = 'WhatRaceEthnicity_NHPI' AND (self_reported_population_concept_id != 8557 OR self_reported_population_source_concept_id != 1586145)) -- ct only --
+  OR (self_reported_category_source_value = 'WhatRaceEthnicity_GeneralizedMultPopulations' AND (self_reported_category_concept_id != 2000000008 OR self_reported_category_source_concept_id != 2000000008))
+  OR (self_reported_category_source_value = 'WhatRaceEthnicity_GeneralizedPopulation' AND (self_reported_category_concept_id != 2000000001 OR self_reported_category_source_concept_id != 2000000001))
+  OR (self_reported_category_source_value = 'WhatRaceEthnicity_Black' AND (self_reported_category_concept_id != 8516 OR self_reported_category_source_concept_id != 1586143))
+  OR (self_reported_category_source_value = 'WhatRaceEthnicity_White' AND (self_reported_category_concept_id != 8527 OR self_reported_category_source_concept_id != 1586146))
+  OR (self_reported_category_source_value = 'WhatRaceEthnicity_Asian' AND (self_reported_category_concept_id != 8515 OR self_reported_category_source_concept_id != 1586142))
+  OR (self_reported_category_source_value = 'WhatRaceEthnicity_Hispanic' AND (self_reported_category_concept_id != 1586147 OR self_reported_category_source_concept_id != 1586147))
+  OR (self_reported_category_source_value = 'PMI_PreferNotToAnswer' AND (self_reported_category_concept_id != 1177221 OR self_reported_category_source_concept_id != 903079))
+  OR (self_reported_category_source_value = 'PMI_Skip' AND (self_reported_category_concept_id != 903096 OR self_reported_category_source_concept_id != 903096))
+  OR (self_reported_category_source_value = 'WhatRaceEthnicity_RaceEthnicityNoneOfThese' AND (self_reported_category_concept_id != 45882607 OR self_reported_category_source_concept_id != 1586148))
+  OR (self_reported_category_source_value = 'WhatRaceEthnicity_AIAN' AND (self_reported_category_concept_id != 8657 OR self_reported_category_source_concept_id != 1586141)) -- ct only --
+  OR (self_reported_category_source_value = 'WhatRaceEthnicity_MENA' AND (self_reported_category_concept_id != 38003615 OR self_reported_category_source_concept_id != 1586144)) -- ct only --
+  OR (self_reported_category_source_value = 'WhatRaceEthnicity_NHPI' AND (self_reported_category_concept_id != 8557 OR self_reported_category_source_concept_id != 1586145)) -- ct only --
 ORDER BY 1,2
 
 """)
@@ -669,13 +669,13 @@
         'query': 'Query 4.0 date not shifited',
         'result': 'PASS'
     },
-                   ignore_index=True)
+        ignore_index=True)
 else:
     df = df.append({
         'query': 'Query 4.0 date not shifited',
         'result': 'Failure'
     },
-                   ignore_index=True)
+        ignore_index=True)
 df1
 
 # ##  Query 5.0 [DC-1051] Verify that "PPI Drop Duplicates" Rule is excluded COPE responses
@@ -795,6 +795,7 @@
         ignore_index=True)
 df1
 
+
 # # Summary_deid_base_validation
 
 
@@ -806,5 +807,3 @@ def highlight_cells(val):
 
 df.style.applymap(highlight_cells).set_properties(**{'text-align': 'left'})
 # -
-
-
diff --git a/data_steward/analytics/cdr_ops/rt_cdr_qc/cdr_deid_clean_qa_report1.py b/data_steward/analytics/cdr_ops/rt_cdr_qc/cdr_deid_clean_qa_report1.py
@@ -22,6 +22,7 @@
 from utils import auth
 from gcloud.bq import BigQueryClient
 from analytics.cdr_ops.notebook_utils import execute, IMPERSONATION_SCOPES
+
 pd.options.display.max_rows = 120
 
 # + papermill={"duration": 0.023643, "end_time": "2021-02-02T22:30:31.880820", "exception": false, "start_time": "2021-02-02T22:30:31.857177", "status": "completed"} tags=["parameters"]
@@ -62,13 +63,13 @@
         'query': 'Query1 observation',
         'result': 'PASS'
     },
-                   ignore_index=True)
+                             ignore_index=True)
 else:
-    summary = summary.append({
-        'query': 'Query1 observation',
-        'result': 'Failure'
-    },
-                   ignore_index=True)
+    summary = summary.append(
+        {
+            'query': 'Query1 observation',
+            'result': 'Failure'
+        }, ignore_index=True)
 result.T
 
 # + [markdown] papermill={"duration": 0.023633, "end_time": "2021-02-02T22:30:36.860798", "exception": false, "start_time": "2021-02-02T22:30:36.837165", "status": "completed"} tags=[]
@@ -95,13 +96,13 @@
         'query': 'Query2 condition',
         'result': 'PASS'
     },
-                   ignore_index=True)
+                             ignore_index=True)
 else:
     summary = summary.append({
         'query': 'Query2 condition',
         'result': 'Failure'
     },
-                   ignore_index=True)
+                             ignore_index=True)
 result.T
 
 # # 3  Verify that in procedure_occurrence table if procedure_occurrence_source_concept_id AND the procedure_occurrence_concept_id both of those fields are null OR zero, the row should be removed.
@@ -123,13 +124,13 @@
         'query': 'Query3 procedure',
         'result': 'PASS'
     },
-                   ignore_index=True)
+                             ignore_index=True)
 else:
     summary = summary.append({
         'query': 'Query3 procedure',
         'result': 'Failure'
     },
-                   ignore_index=True)
+                             ignore_index=True)
 result.T
 
 # + [markdown] papermill={"duration": 0.023649, "end_time": "2021-02-02T22:30:39.115495", "exception": false, "start_time": "2021-02-02T22:30:39.091846", "status": "completed"} tags=[]
@@ -152,16 +153,15 @@
         'query': 'Query4 visit',
         'result': 'PASS'
     },
-                   ignore_index=True)
+                             ignore_index=True)
 else:
     summary = summary.append({
         'query': 'Query4 visit',
         'result': 'Failure'
     },
-                   ignore_index=True)
+                             ignore_index=True)
 result.T
 
-
 # + [markdown] papermill={"duration": 0.023649, "end_time": "2021-02-02T22:30:39.115495", "exception": false, "start_time": "2021-02-02T22:30:39.091846", "status": "completed"} tags=[]
 # # 5 Verify that in drug_exposure table if drug_exposure_source_concept_id AND the drug_exposure_concept_id both of those fields are null OR zero, the row should be removed.
 
@@ -182,13 +182,14 @@
         'query': 'Query5 drug_exposure',
         'result': 'PASS'
     },
-                   ignore_index=True)
+                             ignore_index=True)
 else:
-    summary = summary.append({
-        'query': 'Query5 drug_exposure',
-        'result': 'Failure'
-    },
-                   ignore_index=True)
+    summary = summary.append(
+        {
+            'query': 'Query5 drug_exposure',
+            'result': 'Failure'
+        },
+        ignore_index=True)
 result.T
 
 # + [markdown] papermill={"duration": 0.023649, "end_time": "2021-02-02T22:30:39.115495", "exception": false, "start_time": "2021-02-02T22:30:39.091846", "status": "completed"} tags=[]
@@ -211,13 +212,13 @@
         'query': 'Query6 device',
         'result': 'PASS'
     },
-                   ignore_index=True)
+                             ignore_index=True)
 else:
     summary = summary.append({
         'query': 'Query6 device',
         'result': 'Failure'
     },
-                   ignore_index=True)
+                             ignore_index=True)
 result.T
 
 # + [markdown] papermill={"duration": 0.023649, "end_time": "2021-02-02T22:30:39.115495", "exception": false, "start_time": "2021-02-02T22:30:39.091846", "status": "completed"} tags=[]
@@ -240,13 +241,14 @@
         'query': 'Query7 measurement',
         'result': 'PASS'
     },
-                   ignore_index=True)
+                             ignore_index=True)
 else:
-    summary = summary.append({
-        'query': 'Query7, measurement',
-        'result': 'Failure'
-    },
-                   ignore_index=True)
+    summary = summary.append(
+        {
+            'query': 'Query7, measurement',
+            'result': 'Failure'
+        },
+        ignore_index=True)
 result.T
 # -
 
@@ -287,8 +289,8 @@
 result
 # -
 
-Query9 "Race Ethnicity: person_ext self reported population DC-3789"
-Verify that the person_ext self_reported_population fields are populated correctly. 
+# Query9 "Race Ethnicity: person_ext self reported population DC-3789"
+# Verify that the person_ext self_reported_category fields are populated correctly.
 
 # has to be deid_clean
 query = JINJA_ENV.from_string("""
@@ -303,35 +305,35 @@
         ORDER BY person_id, value_source_concept_id)
       GROUP BY 1))
 
-SELECT DISTINCT races, c_races, race_source_value, ethnicity_source_value,  race_source_concept_id, race_concept_id, self_reported_population_source_value,  self_reported_population_source_concept_id, self_reported_population_concept_id
+SELECT DISTINCT races, c_races, race_source_value, ethnicity_source_value,  race_source_concept_id, race_concept_id, self_reported_category_source_value,  self_reported_category_source_concept_id, self_reported_category_concept_id
 FROM obs
 LEFT JOIN `{{project_id}}.{{deid_clean_cdr}}.person`
 USING (person_id)
 LEFT JOIN `{{project_id}}.{{deid_clean_cdr}}.person_ext`
 USING (person_id)
 WHERE 
 -- check srp column multi pop --
-  (REGEXP_CONTAINS(obs.c_races,  r'\|')  AND self_reported_population_source_value != 'WhatRaceEthnicity_GeneralizedMultPopulations' )
+  (REGEXP_CONTAINS(obs.c_races,  r'\|')  AND self_reported_category_source_value != 'WhatRaceEthnicity_GeneralizedMultPopulations' )
 -- check srp column single pop not hispanic--
-  OR (NOT (REGEXP_CONTAINS(obs.c_races,  r'\|') )) AND (race_source_value != self_reported_population_source_value AND (race_source_value = 'AoUDRC_NoneIndicated' AND self_reported_population_source_value != 'WhatRaceEthnicity_Hispanic'))
+  OR (NOT (REGEXP_CONTAINS(obs.c_races,  r'\|') )) AND (race_source_value != self_reported_category_source_value AND (race_source_value = 'AoUDRC_NoneIndicated' AND self_reported_category_source_value != 'WhatRaceEthnicity_Hispanic'))
 -- check srp column single pop hispanic--
-  OR (race_source_value = 'AoUDRC_NoneIndicated' AND self_reported_population_source_value != 'WhatRaceEthnicity_Hispanic')
+  OR (race_source_value = 'AoUDRC_NoneIndicated' AND self_reported_category_source_value != 'WhatRaceEthnicity_Hispanic')
 -- check only expected srpsv exist --
-  OR (self_reported_population_source_value NOT IN ('WhatRaceEthnicity_GeneralizedMultPopulations','WhatRaceEthnicity_GeneralizedPopulation', 'WhatRaceEthnicity_Black','WhatRaceEthnicity_White','WhatRaceEthnicity_Asian' ,'WhatRaceEthnicity_Hispanic','PMI_PreferNotToAnswer', 'PMI_Skip', 'WhatRaceEthnicity_RaceEthnicityNoneOfThese','WhatRaceEthnicity_AIAN',
+  OR (self_reported_category_source_value NOT IN ('WhatRaceEthnicity_GeneralizedMultPopulations','WhatRaceEthnicity_GeneralizedPopulation', 'WhatRaceEthnicity_Black','WhatRaceEthnicity_White','WhatRaceEthnicity_Asian' ,'WhatRaceEthnicity_Hispanic','PMI_PreferNotToAnswer', 'PMI_Skip', 'WhatRaceEthnicity_RaceEthnicityNoneOfThese','WhatRaceEthnicity_AIAN',
 'WhatRaceEthnicity_MENA','WhatRaceEthnicity_NHPI'))
 -- check for expected concept_ids per srpsv --
-  OR (self_reported_population_source_value = 'WhatRaceEthnicity_GeneralizedMultPopulations' AND (self_reported_population_concept_id != 2000000008 OR self_reported_population_source_concept_id != 2000000008))
-  OR (self_reported_population_source_value = 'WhatRaceEthnicity_GeneralizedPopulation' AND (self_reported_population_concept_id != 2000000001 OR self_reported_population_source_concept_id != 2000000001))
-  OR (self_reported_population_source_value = 'WhatRaceEthnicity_Black' AND (self_reported_population_concept_id != 8516 OR self_reported_population_source_concept_id != 1586143))
-  OR (self_reported_population_source_value = 'WhatRaceEthnicity_White' AND (self_reported_population_concept_id != 8527 OR self_reported_population_source_concept_id != 1586146))
-  OR (self_reported_population_source_value = 'WhatRaceEthnicity_Asian' AND (self_reported_population_concept_id != 8515 OR self_reported_population_source_concept_id != 1586142))
-  OR (self_reported_population_source_value = 'WhatRaceEthnicity_Hispanic' AND (self_reported_population_concept_id != 1586147 OR self_reported_population_source_concept_id != 1586147))
-  OR (self_reported_population_source_value = 'PMI_PreferNotToAnswer' AND (self_reported_population_concept_id != 1177221 OR self_reported_population_source_concept_id != 903079))
-  OR (self_reported_population_source_value = 'PMI_Skip' AND (self_reported_population_concept_id != 903096 OR self_reported_population_source_concept_id != 903096))
-  OR (self_reported_population_source_value = 'WhatRaceEthnicity_RaceEthnicityNoneOfThese' AND (self_reported_population_concept_id != 45882607 OR self_reported_population_source_concept_id != 1586148))
-  OR (self_reported_population_source_value = 'WhatRaceEthnicity_AIAN' AND (self_reported_population_concept_id != 8657 OR self_reported_population_source_concept_id != 1586141)) -- ct only --
-  OR (self_reported_population_source_value = 'WhatRaceEthnicity_MENA' AND (self_reported_population_concept_id != 38003615 OR self_reported_population_source_concept_id != 1586144)) -- ct only --
-  OR (self_reported_population_source_value = 'WhatRaceEthnicity_NHPI' AND (self_reported_population_concept_id != 8557 OR self_reported_population_source_concept_id != 1586145)) -- ct only --
+  OR (self_reported_category_source_value = 'WhatRaceEthnicity_GeneralizedMultPopulations' AND (self_reported_category_concept_id != 2000000008 OR self_reported_category_source_concept_id != 2000000008))
+  OR (self_reported_category_source_value = 'WhatRaceEthnicity_GeneralizedPopulation' AND (self_reported_category_concept_id != 2000000001 OR self_reported_category_source_concept_id != 2000000001))
+  OR (self_reported_category_source_value = 'WhatRaceEthnicity_Black' AND (self_reported_category_concept_id != 8516 OR self_reported_category_source_concept_id != 1586143))
+  OR (self_reported_category_source_value = 'WhatRaceEthnicity_White' AND (self_reported_category_concept_id != 8527 OR self_reported_category_source_concept_id != 1586146))
+  OR (self_reported_category_source_value = 'WhatRaceEthnicity_Asian' AND (self_reported_category_concept_id != 8515 OR self_reported_category_source_concept_id != 1586142))
+  OR (self_reported_category_source_value = 'WhatRaceEthnicity_Hispanic' AND (self_reported_category_concept_id != 1586147 OR self_reported_category_source_concept_id != 1586147))
+  OR (self_reported_category_source_value = 'PMI_PreferNotToAnswer' AND (self_reported_category_concept_id != 1177221 OR self_reported_category_source_concept_id != 903079))
+  OR (self_reported_category_source_value = 'PMI_Skip' AND (self_reported_category_concept_id != 903096 OR self_reported_category_source_concept_id != 903096))
+  OR (self_reported_category_source_value = 'WhatRaceEthnicity_RaceEthnicityNoneOfThese' AND (self_reported_category_concept_id != 45882607 OR self_reported_category_source_concept_id != 1586148))
+  OR (self_reported_category_source_value = 'WhatRaceEthnicity_AIAN' AND (self_reported_category_concept_id != 8657 OR self_reported_category_source_concept_id != 1586141)) -- ct only --
+  OR (self_reported_category_source_value = 'WhatRaceEthnicity_MENA' AND (self_reported_category_concept_id != 38003615 OR self_reported_category_source_concept_id != 1586144)) -- ct only --
+  OR (self_reported_category_source_value = 'WhatRaceEthnicity_NHPI' AND (self_reported_category_concept_id != 8557 OR self_reported_category_source_concept_id != 1586145)) -- ct only --
 ORDER BY 1,2
 
 """)

diff --git a/data_steward/cdr_cleaner/cleaning_rules/create_person_ext_table.py b/data_steward/cdr_cleaner/cleaning_rules/create_person_ext_table.py
@@ -16,9 +16,9 @@
 sex_at_birth_source_concept_id: value_source_concept_id in observation where observation_source_concept_id = 1585845
 sex_at_birth_source_value: concept_code in the concept table where joining from observation where 
 observation_source_concept_id = 1585845
-self_reported_population_concept_id: value_as_concept_id in observation where observation_source_concept_id = 1586140
-self_reported_population_source_concept_id: value_source_concept_id in observation where observation_source_concept_id = 1586140
-self_reported_population_source_value: concept_code in the concept table where joining from observation where
+self_reported_category_concept_id: value_as_concept_id in observation where observation_source_concept_id = 1586140
+self_reported_category_source_concept_id: value_source_concept_id in observation where observation_source_concept_id = 1586140
+self_reported_category_source_value: concept_code in the concept table where joining from observation where
 observation_source_concept_id = 1586140
 """
 import logging
@@ -40,9 +40,9 @@
   t.sex_at_birth_concept_id = COALESCE(os.value_as_concept_id, 0),
   t.sex_at_birth_source_concept_id = COALESCE(os.value_source_concept_id, 0),
   t.sex_at_birth_source_value = COALESCE(sc.concept_code, 'No matching concept'),
-  t.self_reported_population_concept_id = COALESCE(srp.value_as_concept_id, 0),
-  t.self_reported_population_source_concept_id = COALESCE(srp.value_source_concept_id, 0),
-  t.self_reported_population_source_value = COALESCE(srp.value_source_value, 'No matching concept')
+  t.self_reported_category_concept_id = COALESCE(srp.value_as_concept_id, 0),
+  t.self_reported_category_source_concept_id = COALESCE(srp.value_source_concept_id, 0),
+  t.self_reported_category_source_value = COALESCE(srp.value_source_value, 'No matching concept')
 FROM
   `{{project}}.{{dataset}}.person` p
 LEFT JOIN

diff --git a/data_steward/resource_files/schemas/extension_tables/person_ext.json b/data_steward/resource_files/schemas/extension_tables/person_ext.json
@@ -43,19 +43,19 @@
     },
     {
         "type": "integer",
-        "name": "self_reported_population_concept_id",
+        "name": "self_reported_category_concept_id",
         "mode": "nullable",
         "description": "[All of Us OMOP extension] A foreign key to the participant's self-reported population concept."
     },
     {
         "type": "integer",
-        "name": "self_reported_population_source_concept_id",
+        "name": "self_reported_category_source_concept_id",
         "mode": "nullable",
         "description": "[All of Us OMOP extension] A foreign key to the participant's self-reported population source concept."
     },
     {
         "type": "string",
-        "name": "self_reported_population_source_value",
+        "name": "self_reported_category_source_value",
         "mode": "nullable",
         "description": "[All of Us OMOP extension] The source code for the participant's self reported population."
     }

diff --git a/data_steward/tools/recreate_person.py b/data_steward/tools/recreate_person.py
@@ -22,11 +22,11 @@
     OPTIONS(description="[All of Us OMOP extension] A foreign key to the biological sex at birth source concept."),
 ADD COLUMN IF NOT EXISTS sex_at_birth_source_value STRING
     OPTIONS(description="[All of Us OMOP extension] The source code for the biological sex at birth."),
-ADD COLUMN IF NOT EXISTS self_reported_population_concept_id INT64
+ADD COLUMN IF NOT EXISTS self_reported_category_concept_id INT64
     OPTIONS(description="[All of Us OMOP extension] A foreign key to the participant's self-reported population concept."),
-ADD COLUMN IF NOT EXISTS self_reported_population_source_concept_id INT64
+ADD COLUMN IF NOT EXISTS self_reported_category_source_concept_id INT64
     OPTIONS(description="[All of Us OMOP extension] A foreign key to the participant's self-reported population source concept."),
-ADD COLUMN IF NOT EXISTS self_reported_population_source_value STRING
+ADD COLUMN IF NOT EXISTS self_reported_category_source_value STRING
     OPTIONS(description="[All of Us OMOP extension] The source code for the participant's self reported population.")
 """)
 
@@ -38,9 +38,9 @@
     sex_at_birth_concept_id = ext.sex_at_birth_concept_id,
     sex_at_birth_source_concept_id = ext.sex_at_birth_source_concept_id,
     sex_at_birth_source_value = ext.sex_at_birth_source_value,
-    self_reported_population_concept_id = ext.self_reported_population_concept_id,
-    self_reported_population_source_concept_id = ext.self_reported_population_source_concept_id,
-    self_reported_population_source_value = ext.self_reported_population_source_value
+    self_reported_category_concept_id = ext.self_reported_category_concept_id,
+    self_reported_category_source_concept_id = ext.self_reported_category_source_concept_id,
+    self_reported_category_source_value = ext.self_reported_category_source_value
 FROM
     `{{person_ext.project}}.{{person_ext.dataset_id}}.{{person_ext.table_id}}` ext
 WHERE p.person_id = ext.person_id