adding condition_concept_codes feature

edsteva/probes/biology/biology.py

@@ -102,7 +102,7 @@ def compute_process(
             ("GLIMS_ANABIO", "ANABIO_ITM", "Mapped from"),
             ("ANABIO_ITM", "LOINC_ITM", "Maps to"),
         ],
-        concept_codes: Union[bool, List[str]] = None,
+        measurement_concept_codes: Union[bool, List[str]] = None,
         concepts_sets: Union[str, Dict[str, str]] = {
             "Leucocytes": "A0174|K3232|H6740|E4358|C9784|C8824|E6953",
             "Plaquettes": "E4812|C0326|A1636|A0230|H6751|A1598|G7728|G7727|G7833|A2538|A2539|J4463",
@@ -147,7 +147,7 @@ def compute_process(
             **EXAMPLE**: `[("ANALYSES_LABORATOIRE", "GLIMS_ANABIO", "Maps to")]`
         concepts_sets: Union[str, Dict[str, str]] , optional
             **EXAMPLE**: `{"Créatinine": "E3180|G1974|J1002|A7813|A0094|G1975|J1172|G7834|F9409|F9410|C0697|H4038|F2621", "Leucocytes": r"A0174|K3232|H6740|E4358|C9784|C8824|E6953"}`
-        concept_codes: Union[bool, List[str]], optional
+        measurement_concept_codes: Union[bool, List[str]], optional
             **EXAMPLE**: ['E3180', 'G1974', 'J1002', 'A7813', 'A0094', 'G1975', 'J1172', 'G7834', 'F9409', 'F9410', 'C0697', 'H4038']`
         care_site_ids : List[int], optional
             **EXAMPLE**: `[8312056386, 8312027648]`
@@ -180,7 +180,7 @@ def compute_process(
         """
         if not concepts_sets and "concepts_set" in self._index:
             self._index.remove("concepts_set")
-        if not concept_codes:
+        if not measurement_concept_codes:
             for terminology in self._standard_terminologies:
                 if "{}_concept_code".format(terminology) in self._index:
                     self._index.remove("{}_concept_code".format(terminology))
@@ -219,7 +219,7 @@ def compute_process(
             care_site_ids=care_site_ids,
             care_site_short_names=care_site_short_names,
             care_site_specialties=care_site_specialties,
-            concept_codes=concept_codes,
+            measurement_concept_codes=measurement_concept_codes,
             care_sites_sets=care_sites_sets,
             specialties_sets=specialties_sets,
             concepts_sets=concepts_sets,

edsteva/probes/biology/completeness_predictors/per_measurement.py

@@ -34,7 +34,7 @@ def compute_completeness_predictor_per_measurement(
     care_site_ids: List[int],
     care_site_short_names: List[str],
     care_site_specialties: Union[bool, List[str]],
-    concept_codes: Union[bool, List[str]],
+    measurement_concept_codes: Union[bool, List[str]],
     care_sites_sets: Union[str, Dict[str, str]],
     specialties_sets: Union[str, Dict[str, str]],
     concepts_sets: Union[str, Dict[str, str]],
@@ -96,7 +96,7 @@ def compute_completeness_predictor_per_measurement(
     measurement = prepare_measurement(
         data=data,
         biology_relationship=biology_relationship,
-        concept_codes=concept_codes,
+        measurement_concept_codes=measurement_concept_codes,
         concepts_sets=concepts_sets,
         start_date=start_date,
         end_date=end_date,

edsteva/probes/biology/completeness_predictors/per_visit.py

@@ -33,7 +33,7 @@ def compute_completeness_predictor_per_visit(
     care_site_ids: List[int],
     care_site_short_names: List[str],
     care_site_specialties: Union[bool, List[str]],
-    concept_codes: Union[bool, List[str]],
+    measurement_concept_codes: Union[bool, List[str]],
     care_sites_sets: Union[str, Dict[str, str]],
     specialties_sets: Union[str, Dict[str, str]],
     concepts_sets: Union[str, Dict[str, str]],
@@ -130,7 +130,7 @@ def compute_completeness_predictor_per_visit(
     measurement = prepare_measurement(
         data=data,
         biology_relationship=biology_relationship,
-        concept_codes=concept_codes,
+        measurement_concept_codes=measurement_concept_codes,
         concepts_sets=concepts_sets,
         root_terminology=root_terminology,
         standard_terminologies=standard_terminologies,

edsteva/probes/condition/completeness_predictors/per_condition.py

@@ -37,6 +37,7 @@ def compute_completeness_predictor_per_condition(
     specialties_sets: Union[str, Dict[str, str]],
     diag_types: Union[bool, str, Dict[str, str]],
     condition_types: Union[bool, str, Dict[str, str]],
+    condition_concept_codes: Union[bool, List[str]],
     source_systems: Union[bool, List[str]],
     length_of_stays: List[float],
     age_ranges: List[int],
@@ -96,6 +97,7 @@ def compute_completeness_predictor_per_condition(
         source_systems=source_systems,
         diag_types=diag_types,
         condition_types=condition_types,
+        condition_concept_codes=condition_concept_codes,
         start_date=start_date,
         end_date=end_date,
     )

edsteva/probes/condition/completeness_predictors/per_visit.py

@@ -37,6 +37,7 @@ def compute_completeness_predictor_per_visit(
     specialties_sets: Union[str, Dict[str, str]],
     diag_types: Union[bool, str, Dict[str, str]],
     condition_types: Union[bool, str, Dict[str, str]],
+    condition_concept_codes: Union[bool, List[str]],
     source_systems: Union[bool, List[str]],
     length_of_stays: List[float],
     age_ranges: List[int],

edsteva/probes/condition/condition.py

@@ -57,6 +57,7 @@ def __init__(
             "age_range",
             "drg_source",
             "gender_source_value",
+            "condition_source_value",
         ]
         super().__init__(
             completeness_predictor=completeness_predictor,
@@ -71,6 +72,7 @@ def compute_process(
         extra_data: Data = None,
         diag_types: Union[bool, str, Dict[str, str]] = None,
         condition_types: Union[bool, str, Dict[str, str]] = None,
+        condition_concept_codes: Union[str, List[str]] = None,
         source_systems: Union[bool, List[str]] = ["ORBIS"],
         care_site_ids: List[int] = None,
         care_site_short_names: List[str] = None,
@@ -103,6 +105,8 @@ def compute_process(
             **EXAMPLE**: `{"All": ".*"}` or `{"All": ".*", "DP\DR": "DP|DR"}` or `"DP"`
         condition_types: Union[bool, str, Dict[str, str]], optional
             **EXAMPLE**: `{"All": ".*"}` or `{"All": ".*", "Pulmonary_embolism": "I26"}`
+        condition_concept_codes: Union[bool, List[str]], optional
+            **EXAMPLE**: ['E3180', 'G1974', 'J1002', 'A7813', 'A0094', 'G1975', 'J1172', 'G7834', 'F9409', 'F9410', 'C0697', 'H4038']`
         source_systems: Union[bool, List[str]], optional
             **EXAMPLE**: `["AREM", "ORBIS"]`
         care_site_ids : List[int], optional
@@ -136,6 +140,8 @@ def compute_process(
             self._index.remove("diag_type")
         if not condition_types and "condition_type" in self._index:
             self._index.remove("condition_type")
+        if not condition_concept_codes and "condition_source_value" in self._index:
+            self._index.remove("condition_source_value")
         if not source_systems and "source_system" in self._index:
             self._index.remove("source_system")
         if not care_site_levels and "care_site_level" in self._index:
@@ -177,6 +183,7 @@ def compute_process(
             provenance_sources=provenance_sources,
             length_of_stays=length_of_stays,
             condition_types=condition_types,
+            condition_concept_codes=condition_concept_codes,
             source_systems=source_systems,
             stay_sources=stay_sources,
             drg_sources=drg_sources,

edsteva/probes/utils/prepare_df.py

@@ -124,7 +124,7 @@ def prepare_visit_occurrence(
 def prepare_measurement(
     data: Data,
     biology_relationship: pd.DataFrame,
-    concept_codes: Union[bool, List[str]],
+    measurement_concept_codes: Union[bool, List[str]],
     concepts_sets: Union[str, Dict[str, str]],
     root_terminology: str,
     standard_terminologies: List[str],
@@ -180,13 +180,13 @@ def prepare_measurement(
             end_date=end_date,
         )
 
-    if concept_codes and isinstance(concept_codes, list):
+    if measurement_concept_codes and isinstance(measurement_concept_codes, list):
         measurement_by_terminology = []
         for standard_terminology in standard_terminologies:
             measurement_by_terminology.append(
                 measurement[
                     measurement["{}_concept_code".format(standard_terminology)].isin(
-                        concept_codes
+                        measurement_concept_codes
                     )
                 ]
             )
@@ -215,6 +215,7 @@ def prepare_condition_occurrence(
     source_systems: Union[bool, List[str]],
     diag_types: Union[bool, str, Dict[str, str]],
     condition_types: Union[bool, str, Dict[str, str]],
+    condition_concept_code: Union[bool, List[str]] = None,
     start_date: datetime = None,
     end_date: datetime = None,
 ):
@@ -278,16 +279,17 @@ def prepare_condition_occurrence(
             target_col="diag_type",
         )
 
-    # Filter conditions
-    condition_occurrence = condition_occurrence.rename(
-        columns={"condition_source_value": "condition_type"}
-    )
+    if condition_concept_code and isinstance(condition_concept_code, list):
+        condition_occurrence = condition_occurrence[
+            condition_occurrence.condition_source_value.isin(condition_concept_code)
+        ]
+
     if condition_types and isinstance(condition_types, (dict, str)):
         condition_occurrence = filter_table_by_type(
             table=condition_occurrence,
             table_name="condition_occurrence",
             type_groups=condition_types,
-            source_col="condition_type",
+            source_col="condition_source_value",
             target_col="condition_type",
         )