from cohortextractor import StudyDefinition, patients, codelist, codelist_from_csv
study = StudyDefinition(
default_expectations={
"date": {"earliest": "1900-01-01", "latest": "today"},
"rate": "uniform",
"incidence": 0.5,
},
population=patients.registered_with_one_practice_between(
"2019-02-01", "2020-02-01"
),
age=patients.age_as_of(
"2019-09-01",
return_expectations={
"rate": "universal",
"int": {"distribution": "population_ages"},
},
),
)
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(
other_respiratory_codes,
on_or_before="2020-02-29",
return_expectations={"incidence": 0.05},
),
nebules=patients.with_these_medications(
nebulised_med_codes,
between=["2019-02-28", "2020-02-29"],
return_expectations={"incidence": 0.05},
default_expectations={
"date": {
"earliest": "1900-01-01",
"latest": "today"
},
"rate": "uniform",
"incidence": 0.1,
},
# This line defines the study population
population=patients.satisfying(
"""
has_follow_up AND
(age >=18 AND age <= 110) AND
(sex = "M" OR sex = "F")
""",
has_follow_up=patients.registered_with_one_practice_between(
"2019-02-28", "2020-02-29")),
# Outcomes
icu_date_admitted=patients.admitted_to_icu(
on_or_after="2020-03-01",
include_day=True,
returning="date_admitted",
find_first_match_in_period=True,
return_expectations={
"date": {
"earliest": "2020-03-01"
},
"incidence": 0.1
},
),
died_ons_covid_flag_any=patients.with_these_codes_on_death_certificate(
covid_identification,
from_date = "2020-02-01"
to_date = "2021-11-28"
study = StudyDefinition(
index_date=from_date,
default_expectations={
"date": {
"earliest": "1970-01-01",
"latest": "today"
},
"rate": "uniform",
"incidence": 0.2,
},
# This line defines the study population
population=patients.registered_with_one_practice_between(
from_date, to_date),
# demographic info
# https://github.com/ebmdatalab/tpp-sql-notebook/issues/33
age=patients.age_as_of(
from_date,
return_expectations={
"rate": "universal",
"int": {
"distribution": "population_ages"
},
},
),
# https://github.com/ebmdatalab/tpp-sql-notebook/issues/46
sex=patients.sex(return_expectations={
"rate": "universal",
"category": {
)
systolic_blood_pressure_codes = codelist(["2469."], system="ctv3")
diastolic_blood_pressure_codes = codelist(["246A."], system="ctv3")
study = StudyDefinition(
index_date="2020-02-01",
# Configure the expectations framework
default_expectations={
"date": {
"earliest": "1900-01-01",
"latest": "index_date"
},
"rate": "exponential_increase",
},
# This line defines the study population
population=patients.registered_with_one_practice_between(
"index_date - 1 year", "index_date"),
# The rest of the lines define the covariates with associated GitHub issues
# https://github.com/ebmdatalab/tpp-sql-notebook/issues/33
age=patients.age_as_of(
"index_date",
return_expectations={
"rate": "universal",
"int": {
"distribution": "population_ages"
},
},
),
# https://github.com/ebmdatalab/tpp-sql-notebook/issues/46
sex=patients.sex(return_expectations={
"rate": "universal",
"category": {
from codelists import *
# STUDY DEFINITION
# Defines both the study population and points to the important covariates and outcomes
study = StudyDefinition(
default_expectations={
"date": {
"earliest": "1970-01-01",
"latest": "today"
},
"rate": "uniform",
"incidence": 0.2,
},
# STUDY POPULATION
population=patients.registered_with_one_practice_between(
"2019-11-01", "2020-02-01"),
dereg_date=patients.date_deregistered_from_all_supported_practices(
on_or_after="2020-02-01",
date_format="YYYY-MM",
),
# FOLLOW UP
has_12_m_follow_up=patients.registered_with_one_practice_between(
"2019-02-01",
"2020-01-31", ### 12 months prior to 1st Feb 2020
return_expectations={
"incidence": 0.95,
}),
# OUTCOMES
died_ons_covid_flag_any=patients.with_these_codes_on_death_certificate(
study = StudyDefinition(
default_expectations={
"date": {
"earliest": "1980-01-01",
"latest": "today"
},
"rate": "uniform",
"incidence": 0.05,
},
index_date="2019-02-01",
population=patients.satisfying(
"""
has_follow_up
AND (age >=18 AND age <= 110)
""",
has_follow_up=patients.registered_with_one_practice_between(
"index_date - 1 year", "index_date"),
age=patients.age_as_of(
"index_date",
return_expectations={
"rate": "universal",
"int": {
"distribution": "population_ages"
},
},
),
),
covid_hospitalisation=patients.categorised_as(
{
"COVID-19 positive": "covid_positive AND NOT covid_hospitalised",
"COVID-19 hospitalised": "covid_hospitalised",
"General population": "DEFAULT",
# This line defines the study population
population=patients.satisfying("""
registered = 1
AND
(covid_vacc_date
OR
(age >=70 AND age <= 110)
OR
(care_home_type))
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
# STUDY DEFINITION
# Defines both the study population and points to the important covariates and outcomes
study = StudyDefinition(
default_expectations={
"date": {
"earliest": "1970-01-01",
"latest": "today"
},
"rate": "uniform",
"incidence": 0.2,
},
# STUDY POPULATION - registered 1 year prior to November 16th 2020
population=patients.satisfying(
"one_practice AND sgss_pos_inrange",
one_practice=patients.registered_with_one_practice_between(
"2019-11-16", "2020-11-16"),
),
dereg_date=patients.date_deregistered_from_all_supported_practices(
on_or_after="2020-11-16",
date_format="YYYY-MM",
),
# OUTCOMES - ONS death dates
died_ons_covid_flag_any=patients.with_these_codes_on_death_certificate(
covid_codelist,
on_or_after="2020-02-01",
match_only_underlying_cause=False,
return_expectations={
"date": {
"earliest": "2020-02-01"
},
# """
# has_follow_up AND
# (age >=18 AND age <= 110) AND
# (sex = "M" OR sex = "F") AND
# imd > 0 AND
# (rheumatoid OR sle) AND NOT
# chloroquine_not_hcq
# """,
# has_follow_up=patients.registered_with_one_practice_between(
# "2019-02-28", "2020-02-29"
# ),
#),
has_12mfollow_up=patients.registered_with_one_practice_between(
"2019-02-01",
"2020-02-01",
return_expectations={"incidence": 0.9},
),
under_fup_1feb=patients.registered_with_one_practice_between(
"2020-02-01",
"2020-02-01",
return_expectations={"incidence": 0.9},
),
# The rest of the lines define the covariates with associated GitHub issues
# https://github.com/ebmdatalab/tpp-sql-notebook/issues/33
age=patients.age_as_of(
"2020-02-01",
return_expectations={
"rate": "universal",
"int": {
