def test_make_df_from_binary_default_outcome():
study = StudyDefinition(
population=patients.all(),
died=patients.died_from_any_cause(
return_expectations={
"date": {"earliest": "1900-01-01", "latest": "today"},
"incidence": 0.1,
}
),
)
population_size = 10000
result = study.make_df_from_expectations(population_size)
assert len(result[~pd.isnull(result.died)]) == 0.1 * population_size
# Configure the expectations framework
default_expectations={
"date": {
"earliest": "2020-01-01",
"latest": "today"
},
"rate": "universal",
},
# define the study index date
index_date=index_date,
# This line defines the study population
population=patients.satisfying(
"(NOT died) AND (registered) AND (pregnant) AND age >= 16",
died=patients.died_from_any_cause(on_or_before=index_date,
returning="binary_flag"),
registered=patients.registered_as_of(index_date),
pregnant=patients.with_these_clinical_events(
pregnant_code,
between=["index_date", "index_date + 1 month"],
returning="binary_flag",
return_expectations={"incidence": 0.6},
),
),
age=patients.age_as_of(index_date,
return_expectations={
"rate": "universal",
"int": {
"distribution": "population_ages"
}
}),
},
"rate": "uniform",
},
index_date=index_date,
# This line defines the study population
population=patients.satisfying(
"""
(sex = 'F' OR sex = 'M') AND
(age >= 18 AND age < 120) AND
(NOT died) AND
(registered)
""",
registered=patients.registered_as_of(index_date),
died=patients.died_from_any_cause(
on_or_before=index_date,
returning="binary_flag",
),
),
age=patients.age_as_of(
index_date,
return_expectations={
"int": {
"distribution": "population_ages"
},
"incidence": 1
},
),
sex=patients.sex(return_expectations={
"category": {
"ratios": {
"M": 0.49,
covid_identification,
on_or_after="2020-03-01",
match_only_underlying_cause=True,
return_expectations={
"date": {
"earliest": "2020-03-01"
},
"incidence": 0.1
},
),
died_date_ons=patients.died_from_any_cause(
on_or_after="2020-03-01",
returning="date_of_death",
include_month=True,
include_day=True,
return_expectations={
"date": {
"earliest": "2020-03-01"
},
"incidence": 0.1
},
),
# COVID-19 outcomes
first_pos_test_sgss=patients.with_test_result_in_sgss(
pathogen="SARS-CoV-2",
test_result="positive",
find_first_match_in_period=True,
returning="date",
date_format="YYYY-MM-DD",
return_expectations={"date": {
"earliest": "2020-01-01"
}},
on_or_after="2020-02-01",
date_format="YYYY-MM",
),
# OUTCOMES
worms=patients.with_these_clinical_events(
worms_codes,
return_first_date_in_period=True,
include_month=True,
return_expectations={"date": {
"earliest": "2019-02-01"
}},
),
died_date_ons=patients.died_from_any_cause(
on_or_before="2020-08-01",
returning="date_of_death",
include_month=True,
include_day=True,
),
## DEMOGRAPHIC COVARIATES
# AGE
age=patients.age_as_of(
"2019-02-01",
return_expectations={
"rate": "universal",
"int": {
"distribution": "population_ages"
},
},
),
"rate": "exponential_increase",
"incidence": 0.1,
},
population=patients.satisfying(
"""
registered AND
(NOT died) AND
(sex = 'F' OR sex='M') AND
(age != 'missing')
""",
registered=patients.registered_as_of(
"index_date",
return_expectations={"incidence": 0.9},
),
died=patients.died_from_any_cause(
on_or_before="index_date",
returning="binary_flag",
return_expectations={"incidence": 0.1}),
),
age=patients.age_as_of(
"index_date",
return_expectations={
"rate": "universal",
"int": {
"distribution": "population_ages"
},
},
),
age_band=patients.categorised_as(
{
"0-4": "age >= 0 AND age < 5",
"5-9": "age >= 5 AND age < 10",
),
died_ons_covid_flag_underlying=patients.
with_these_codes_on_death_certificate(
covid_codelist,
on_or_after="2020-02-01",
match_only_underlying_cause=True,
return_expectations={"date": {
"earliest": "2020-02-01"
}},
),
died_date_ons=patients.died_from_any_cause(
on_or_after="2020-02-01",
returning="date_of_death",
include_month=True,
include_day=True,
return_expectations={
"date": {
"earliest": "2020-02-01"
},
"rate": "exponential_increase"
},
),
first_tested_for_covid=patients.with_test_result_in_sgss(
pathogen="SARS-CoV-2",
test_result="any",
on_or_after="2020-02-01",
find_first_match_in_period=True,
returning="date",
date_format="YYYY-MM-DD",
return_expectations={
"date": {
"earliest": "2020-02-01"
"earliest": from_date
}},
),
died_ons_covid_underlying=patients.with_these_codes_on_death_certificate(
codes_covid_death,
returning="binary_flag",
on_or_after=from_date,
match_only_underlying_cause=True,
return_expectations={"date": {
"earliest": "2020-03-01"
}},
),
died_ons=patients.died_from_any_cause(
returning="binary_flag",
on_or_after=from_date,
return_expectations={"date": {
"earliest": from_date
}},
),
died_ons_noncovid=patients.satisfying(
"""(NOT died_ons_covid) AND died_ons""",
return_expectations={"incidence": 0.15},
),
death_category=patients.categorised_as(
{
"alive": "NOT died_ons",
"covid-death": "died_ons_covid",
"non-covid-death": "died_ons_noncovid",
"unknown": "DEFAULT",
},
return_expectations={
),
ketoacidosis=patients.satisfying(
"ketoacidosis_hospital OR ketoacidosis_ons",
ketoacidosis_hospital=patients.admitted_to_hospital(
with_these_diagnoses=ketoacidosis_codes,
between=["index_date", "last_day_of_month(index_date)"],
return_expectations={"incidence": 0.05},
),
ketoacidosis_ons=patients.with_these_codes_on_death_certificate(
ketoacidosis_codes,
between=["index_date", "last_day_of_month(index_date)"],
return_expectations={"incidence": 0.05},
),
),
died=patients.died_from_any_cause(
between=["index_date", "last_day_of_month(index_date)"],
return_expectations={"incidence": 0.1},
),
)
measures = [
Measure(
id="died_rate",
numerator="died",
denominator="population",
group_by=["covid_hospitalisation"],
),
Measure(
id="DVT_rate",
numerator="DVT",
denominator="population",
group_by=["covid_hospitalisation"],
AND
NOT has_died
"""),
has_follow_up=patients.registered_with_one_practice_between(
start_date="2019-12-01",
end_date=campaign_start,
return_expectations={"incidence": 0.90},
),
registered=patients.registered_as_of(
campaign_start, # day before vaccination campaign starts - discuss with team if this should be "today"
return_expectations={"incidence": 0.98},
),
has_died=patients.died_from_any_cause(
on_or_before=campaign_start,
returning="binary_flag",
return_expectations={"incidence": 0.05},
),
# Demographic information
# CAREHOME STATUS
care_home_type=patients.care_home_status_as_of(
campaign_start,
categorised_as={
"PC": """
IsPotentialCareHome
AND LocationDoesNotRequireNursing='Y'
AND LocationRequiresNursing='N'
""",
"PN": """
