def test_recursive_definitions_produce_errors():
with pytest.raises(ValueError):
StudyDefinition(
population=patients.all(),
this=patients.satisfying("that = 1"),
that=patients.satisfying("this = 1"),
)
def test_patients_categorised_as():
session = make_session()
session.add_all(
[
Patient(
Sex="M",
CodedEvents=[
CodedEvent(CTV3Code="foo1", ConsultationDate="2000-01-01")
],
),
Patient(
Sex="F",
CodedEvents=[
CodedEvent(CTV3Code="foo2", ConsultationDate="2000-01-01"),
CodedEvent(CTV3Code="bar1", ConsultationDate="2000-01-01"),
],
),
Patient(
Sex="M",
CodedEvents=[
CodedEvent(CTV3Code="foo2", ConsultationDate="2000-01-01")
],
),
Patient(
Sex="F",
CodedEvents=[
CodedEvent(CTV3Code="foo3", ConsultationDate="2000-01-01")
],
),
]
)
session.commit()
foo_codes = codelist([("foo1", "A"), ("foo2", "B"), ("foo3", "C")], "ctv3")
bar_codes = codelist(["bar1"], "ctv3")
study = StudyDefinition(
population=patients.all(),
category=patients.categorised_as(
{
"W": "foo_category = 'B' AND female_with_bar",
"X": "sex = 'F' AND (foo_category = 'B' OR foo_category = 'C')",
"Y": "sex = 'M' AND foo_category = 'A'",
"Z": "DEFAULT",
},
sex=patients.sex(),
foo_category=patients.with_these_clinical_events(
foo_codes, returning="category", find_last_match_in_period=True
),
female_with_bar=patients.satisfying(
"has_bar AND sex = 'F'",
has_bar=patients.with_these_clinical_events(bar_codes),
),
),
)
results = study.to_dicts()
assert [x["category"] for x in results] == ["Y", "W", "Z", "X"]
# Assert that internal columns do not appear
assert "foo_category" not in results[0].keys()
assert "female_with_bar" not in results[0].keys()
assert "has_bar" not in results[0].keys()
def test_column_name_clashes_produce_errors():
with pytest.raises(ValueError):
StudyDefinition(
population=patients.all(),
age=patients.age_as_of("2020-01-01"),
status=patients.satisfying(
"age > 70 AND sex = 'M'",
sex=patients.sex(),
age=patients.age_as_of("2010-01-01"),
),
)
def test_patients_satisfying_with_hidden_columns():
condition_code = "ASTHMA"
condition_code2 = "COPD"
session = make_session()
patient_1 = Patient(DateOfBirth="1940-01-01", Sex="M")
patient_2 = Patient(DateOfBirth="1940-01-01", Sex="F")
patient_3 = Patient(DateOfBirth="1990-01-01", Sex="M")
patient_4 = Patient(DateOfBirth="1940-01-01", Sex="F")
patient_4.CodedEvents.append(
CodedEvent(CTV3Code=condition_code, ConsultationDate="2010-01-01")
)
patient_5 = Patient(DateOfBirth="1940-01-01", Sex="F")
patient_5.CodedEvents.append(
CodedEvent(CTV3Code=condition_code, ConsultationDate="2010-01-01")
)
patient_5.CodedEvents.append(
CodedEvent(CTV3Code=condition_code2, ConsultationDate="2010-01-01")
)
session.add_all([patient_1, patient_2, patient_3, patient_4, patient_5])
session.commit()
study = StudyDefinition(
population=patients.all(),
sex=patients.sex(),
age=patients.age_as_of("2020-01-01"),
at_risk=patients.satisfying(
"""
(age > 70 AND sex = "M")
OR
(has_asthma AND NOT copd)
""",
has_asthma=patients.with_these_clinical_events(
codelist([condition_code], "ctv3")
),
copd=patients.with_these_clinical_events(
codelist([condition_code2], "ctv3")
),
),
)
results = study.to_dicts()
assert [i["at_risk"] for i in results] == ["1", "0", "0", "1", "0"]
assert "has_asthma" not in results[0].keys()
def test_make_df_from_expectations_with_satisfying():
study = StudyDefinition(
population=patients.all(),
has_condition=patients.satisfying(
"condition_a OR condition_b",
condition_a=patients.with_these_clinical_events(
codelist(["A", "B", "C"], system="ctv3")),
condition_b=patients.with_these_clinical_events(
codelist(["X", "Y", "Z"], system="ctv3")),
return_expectations={
"date": {
"earliest": "2001-01-01",
"latest": "2020-03-01"
},
"incidence": 0.95,
},
),
)
population_size = 10000
result = study.make_df_from_expectations(population_size)
assert result.columns == ["has_condition"]
def test_patients_satisfying():
condition_code = "ASTHMA"
session = make_session()
patient_1 = Patient(DateOfBirth="1940-01-01", Sex="M")
patient_2 = Patient(DateOfBirth="1940-01-01", Sex="F")
patient_3 = Patient(DateOfBirth="1990-01-01", Sex="M")
patient_4 = Patient(DateOfBirth="1940-01-01", Sex="F")
patient_4.CodedEvents.append(
CodedEvent(CTV3Code=condition_code, ConsultationDate="2010-01-01")
)
session.add_all([patient_1, patient_2, patient_3, patient_4])
session.commit()
study = StudyDefinition(
population=patients.all(),
sex=patients.sex(),
age=patients.age_as_of("2020-01-01"),
has_asthma=patients.with_these_clinical_events(
codelist([condition_code], "ctv3")
),
at_risk=patients.satisfying("(age > 70 AND sex = 'M') OR has_asthma"),
)
results = study.to_dicts()
assert [i["at_risk"] for i in results] == ["1", "0", "0", "1"]
def test_using_expression_in_population_definition():
session = make_session()
session.add_all(
[
Patient(
Sex="M",
DateOfBirth="1970-01-01",
CodedEvents=[
CodedEvent(CTV3Code="foo1", ConsultationDate="2000-01-01")
],
),
Patient(Sex="M", DateOfBirth="1975-01-01"),
Patient(
Sex="F",
DateOfBirth="1980-01-01",
CodedEvents=[
CodedEvent(CTV3Code="foo1", ConsultationDate="2000-01-01")
],
),
Patient(Sex="F", DateOfBirth="1985-01-01"),
]
)
session.commit()
study = StudyDefinition(
population=patients.satisfying(
"has_foo_code AND sex = 'M'",
has_foo_code=patients.with_these_clinical_events(
codelist(["foo1"], "ctv3")
),
sex=patients.sex(),
),
age=patients.age_as_of("2020-01-01"),
)
results = study.to_dicts()
assert results[0].keys() == {"patient_id", "age"}
assert [i["age"] for i in results] == ["50"]
"rate": "uniform",
"incidence": 0.2,
},
## STUDY POPULATION (required)
population=patients.satisfying(
"""
copd AND
(age >=35 AND age <= 110) AND
ever_smoked AND
has_follow_up AND NOT
recent_asthma AND NOT
other_respiratory AND NOT
nebules AND NOT
ltra_single
""",
has_follow_up=patients.registered_with_one_practice_between(
"2019-02-28", "2020-02-29"),
recent_asthma=patients.with_these_clinical_events(
asthma_codes,
between=["2017-02-28", "2020-02-29"],
),
#### NEBULES
nebules=patients.with_these_medications(
nebulised_med_codes,
between=["2019-02-28", "2020-02-29"],
),
),
## OUTCOMES (at least one outcome or covariate is required)
icu_date_admitted=patients.admitted_to_icu(
on_or_after="2020-03-01",
include_day=True,
asthma_codes,
between=["2017-02-28", "2020-02-29"],
return_expectations={"incidence": 0.5},
),
asthma_ever=patients.with_these_clinical_events(
asthma_ever_codes,
on_or_before="2020-02-29",
return_expectations={"incidence": 0.8},
),
age_cat=patients.satisfying(
"age >=18 AND age <= 110",
return_expectations={"incidence": 0.9},
age=patients.age_as_of(
"2020-02-29",
return_expectations={
"rate": "universal",
"int": {
"distribution": "population_ages"
},
},
),
),
has_follow_up=patients.registered_with_one_practice_between(
"2019-02-28", "2020-02-29", return_expectations={"incidence": 0.9}),
copd=patients.with_these_clinical_events(
copd_codes,
on_or_before="2020-02-29",
return_expectations={"incidence": 0.05},
),
### OTHER RESPIRATORY
other_respiratory=patients.with_these_clinical_events(
default_expectations={
"date": {"earliest": "1970-01-01", "latest": "today"},
"rate": "uniform",
"incidence": 0.05,
},
## STUDY POPULATION (required)
population=patients.all(),
copd=patients.with_these_clinical_events(
copd_codes, on_or_before="2020-02-29", return_expectations={"incidence": 0.4},
),
age_cat=patients.satisfying(
"age >=35 AND age <= 110",
return_expectations={"incidence": 0.9},
age=patients.age_as_of(
"2020-02-29",
return_expectations={
"rate": "universal",
"int": {"distribution": "population_ages"},
},
),
),
ever_smoked=patients.with_these_clinical_events(
filter_codes_by_category(clear_smoking_codes, include=["S", "E"]),
on_or_before="2020-02-29",
return_expectations={"incidence": 0.9},
),
has_follow_up=patients.registered_with_one_practice_between(
"2019-02-28", "2020-02-29", return_expectations={"incidence": 0.9},
),
recent_asthma=patients.with_these_clinical_events(
asthma_codes,
population=patients.satisfying(
"""
(
has_asthma OR
(asthma_ever AND any_asthma_med)
) AND
(age >=18 AND age <= 110) AND
has_follow_up AND NOT
copd AND NOT
other_respiratory AND NOT
nebules AND NOT
(
(lama_single OR laba_lama) AND NOT (
high_dose_ics OR
high_dose_ics_single_ing OR
high_dose_ics_multiple_ingredient OR
low_med_dose_ics_single_ingredient OR
low_med_dose_ics_multiple_ingredient OR
low_med_dose_ics OR
ics_single OR
laba_ics OR
laba_lama_ics
)
)
""",
has_asthma=patients.with_these_clinical_events(
asthma_codes,
between=["2017-02-28", "2020-02-29"],
),
has_follow_up=patients.registered_with_one_practice_between(
"2019-02-28", "2020-02-29"),
nebules=patients.with_these_medications(
nebulised_med_codes,
between=["2019-02-28", "2020-02-29"],
),
any_asthma_med=patients.satisfying("""
ltra_single OR
laba_lama_ics OR
laba_lama OR
laba_ics OR
lama_single OR
laba_single OR
sama_single OR
saba_single OR
ics_single OR
low_med_dose_ics OR
low_med_dose_ics_multiple_ingredient OR
low_med_dose_ics_single_ingredient OR
high_dose_ics_multiple_ingredient OR
high_dose_ics_single_ing OR
high_dose_ics
""")),
