study = StudyDefinition(
# Configure the expectations framework
default_expectations={
"date": {
"earliest": "1900-01-01",
"latest": "today"
},
"rate": "uniform",
"incidence": 0.1,
},
# This line defines the study population
population=patients.registered_with_one_practice_between(
"2019-03-01", "2020-03-01"),
# 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_date_cpns=patients.with_death_recorded_in_cpns(
on_or_before="2020-06-01",
returning="date_of_death",
include_month=True,
include_day=True,
return_expectations={"date": {
"earliest": "2020-03-01"
}},
),
died_ons_covid_flag_any=patients.with_these_codes_on_death_certificate(
covid_identification,
on_or_after="2020-03-01",
match_only_underlying_cause=False,
return_expectations={
"date": {
"earliest": "2020-03-01"
},
"incidence": 0.1
},
),
died_ons_covid_flag_underlying=patients.
with_these_codes_on_death_certificate(
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="2020-06-01",
returning="date_of_death",
include_month=True,
include_day=True,
return_expectations={
"date": {
"earliest": "2020-03-01"
},
"incidence": 0.1
},
),
# 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(
"2020-03-01",
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": {
"ratios": {
"M": 0.49,
"F": 0.51
}
},
}),
ethnicity=patients.with_these_clinical_events(
ethnicity_codes,
returning="category",
find_last_match_in_period=True,
include_date_of_match=True,
return_expectations={
"category": {
"ratios": {
"1": 0.8,
"5": 0.1,
"3": 0.1
}
},
"incidence": 0.75,
},
),
# IMID disease codes
crohns_disease=first_diagnosis_in_period(crohns_disease_codes),
ulcerative_colitis=first_diagnosis_in_period(ulcerative_colitis_codes),
inflammatory_bowel_disease_unclassified=first_diagnosis_in_period(
inflammatory_bowel_disease_unclassified_codes),
psoriasis=first_diagnosis_in_period(psoriasis_codes),
hidradenitis_suppurativa=first_diagnosis_in_period(
hidradenitis_suppurativa_codes),
psoriatic_arthritis=first_diagnosis_in_period(psoriatic_arthritis_codes),
rheumatoid_arthritis=first_diagnosis_in_period(rheumatoid_arthritis_codes),
# Comorbidities
chronic_cardiac_disease=first_diagnosis_in_period(
chronic_cardiac_disease_codes),
diabetes=first_diagnosis_in_period(diabetes_codes),
hba1c_new=first_diagnosis_in_period(hba1c_new_codes),
hba1c_old=first_diagnosis_in_period(hba1c_old_codes),
hba1c_mmol_per_mol=patients.with_these_clinical_events(
hba1c_new_codes,
find_last_match_in_period=True,
on_or_before="2020-02-29",
returning="numeric_value",
include_date_of_match=True,
include_month=True,
return_expectations={
"date": {
"latest": "2020-02-29"
},
"float": {
"distribution": "normal",
"mean": 40.0,
"stddev": 20
},
"incidence": 0.95,
},
),
hba1c_percentage=patients.with_these_clinical_events(
hba1c_old_codes,
find_last_match_in_period=True,
on_or_before="2020-02-29",
returning="numeric_value",
include_date_of_match=True,
include_month=True,
return_expectations={
"date": {
"latest": "2020-02-29"
},
"float": {
"distribution": "normal",
"mean": 5,
"stddev": 2
},
"incidence": 0.95,
},
),
hypertension=first_diagnosis_in_period(hypertension_codes),
chronic_respiratory_disease=first_diagnosis_in_period(
chronic_respiratory_disease_codes),
copd=first_diagnosis_in_period(copd_codes),
chronic_liver_disease=first_diagnosis_in_period(
chronic_liver_disease_codes),
stroke=first_diagnosis_in_period(stroke_codes),
lung_cancer=first_diagnosis_in_period(lung_cancer_codes),
haem_cancer=first_diagnosis_in_period(haem_cancer_codes),
other_cancer=first_diagnosis_in_period(other_cancer_codes),
#CKD
creatinine=patients.with_these_clinical_events(
creatinine_codes,
find_last_match_in_period=True,
between=["2018-12-01", "2020-02-29"],
returning="numeric_value",
include_date_of_match=True,
include_month=True,
return_expectations={
"float": {
"distribution": "normal",
"mean": 150.0,
"stddev": 200.0
},
"date": {
"earliest": "2018-12-01",
"latest": "2020-02-29"
},
"incidence": 0.95,
},
),
#### end stage renal disease codes incl. dialysis / transplant
esrf=patients.with_these_clinical_events(
ckd_codes,
on_or_before="2020-02-29",
return_last_date_in_period=True,
include_month=True,
return_expectations={"date": {
"latest": "2020-02-29"
}},
),
ckd=first_diagnosis_in_period(ckd_codes),
organ_transplant=first_diagnosis_in_period(organ_transplant_codes),
# https://github.com/ebmdatalab/tpp-sql-notebook/issues/10
bmi=patients.most_recent_bmi(
on_or_after="2010-02-01",
minimum_age_at_measurement=16,
include_measurement_date=True,
include_month=True,
return_expectations={
"incidence": 0.6,
"float": {
"distribution": "normal",
"mean": 35,
"stddev": 10
},
},
),
# https://github.com/ebmdatalab/tpp-sql-notebook/issues/54
stp=patients.registered_practice_as_of(
"2020-03-01",
returning="stp_code",
return_expectations={
"rate": "universal",
"category": {
"ratios": {
"STP1": 0.5,
"STP2": 0.5
}
},
},
),
msoa=patients.registered_practice_as_of(
"2020-03-01",
returning="msoa_code",
return_expectations={
"rate": "universal",
"category": {
"ratios": {
"MSOA1": 0.5,
"MSOA2": 0.5
}
},
},
),
# https://github.com/ebmdatalab/tpp-sql-notebook/issues/52
imd=patients.address_as_of(
"2020-03-01",
returning="index_of_multiple_deprivation",
round_to_nearest=100,
return_expectations={
"rate": "universal",
"category": {
"ratios": {
"100": 0.1,
"200": 0.2,
"300": 0.7
}
},
},
),
rural_urban=patients.address_as_of(
"2020-03-01",
returning="rural_urban_classification",
return_expectations={
"rate": "universal",
"category": {
"ratios": {
"rural": 0.1,
"urban": 0.9
}
},
},
),
#SMOKING
smoking_status=patients.categorised_as(
{
"S": "most_recent_smoking_code = 'S'",
"E": """
most_recent_smoking_code = 'E' OR (
most_recent_smoking_code = 'N' AND ever_smoked
)
""",
"N": "most_recent_smoking_code = 'N' AND NOT ever_smoked",
"M": "DEFAULT",
},
return_expectations={
"category": {
"ratios": {
"S": 0.6,
"E": 0.1,
"N": 0.2,
"M": 0.1
}
}
},
most_recent_smoking_code=patients.with_these_clinical_events(
clear_smoking_codes,
find_last_match_in_period=True,
on_or_before="2020-02-29",
returning="category",
),
ever_smoked=patients.with_these_clinical_events(
filter_codes_by_category(clear_smoking_codes, include=["S", "E"]),
on_or_before="2020-02-29",
),
),
smoking_status_date=patients.with_these_clinical_events(
clear_smoking_codes,
on_or_before="2020-02-29",
return_last_date_in_period=True,
include_month=True,
return_expectations={"date": {
"latest": "2020-02-29"
}},
),
### GP CONSULTATION RATE
gp_consult_count=patients.with_gp_consultations(
between=["2019-03-01", "2020-02-29"],
returning="number_of_matches_in_period",
return_expectations={
"int": {
"distribution": "normal",
"mean": 4,
"stddev": 2
},
"date": {
"earliest": "2019-03-01",
"latest": "2020-02-29"
},
"incidence": 0.7,
},
),
has_consultation_history=patients.
with_complete_gp_consultation_history_between(
"2019-03-01",
"2020-02-29",
return_expectations={"incidence": 0.9},
),
# Medications
**medication_counts_and_dates_all([
("oral_prednisolone",
"opensafely-asthma-oral-prednisolone-medication"),
("anti_tnf", "crossimid-anti-tnf-medication"),
("anti_il6", "crossimid-anti-il6-medication"),
("anti_il12-23", "crossimid-anti-il12-23-medication"),
("anti_il1", "crossimid-anti-il1-medication"),
("anti_il4", "crossimid-anti-il4-medication"),
("jak_inhibitors", "crossimid-jak-inhibitors-medication"),
("rituximab", "crossimid-rituximab-medication"),
("anti_integrin", "crossimid-anti-integrin-medication"),
("azathioprine", "crossimid-azathioprine-medication"),
("ciclosporin", "crossimid-ciclosporin-medication"),
("gold", "crossimid-gold-medication"),
("jak_inhibitors", "crossimid-jak-inhibitors-medication"),
("leflunomide", "crossimid-leflunomide-medication"),
("mercaptopurine", "crossimid-mercaptopurine-medication"),
("methotrexate", "crossimid-methotrexate-medication"),
("mycophenolate", "crossimid-mycophenolate-medication"),
("penicillamine", "crossimid-penicillamine-medication"),
("sulfasalazine", "crossimid-sulfasalazine-medication")
]))
study = StudyDefinition(
# 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(
"""
age >= 16 AND
(NOT died) AND
(registered) AND
(cns)
""",
died=patients.died_from_any_cause(on_or_before=index_date,
returning="binary_flag"),
pop_age=patients.age_as_of(index_date),
registered=patients.registered_as_of(index_date),
cns=patients.with_these_clinical_events(
cns_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"
}
}),
age_group=patients.categorised_as(
{
"0": "DEFAULT",
"16 - under 40": " age >= 16 AND age < 40",
"40 - under 50": " age >= 40 AND age < 50",
"50 - under 65": " age >= 50 AND age < 65",
"65 plus": " age >= 65",
},
return_expectations={
"rate": "universal",
"category": {
"ratios": {
"16 - under 40": 0.5,
"40 - under 50": 0.125,
"50 - under 65": 0.25,
"65 plus": 0.125,
}
},
},
),
stp=patients.registered_practice_as_of(
"index_date",
returning="stp_code",
return_expectations={
"category": {
"ratios": {
"STP1": 0.5,
"STP2": 0.5
}
},
},
),
first_dose=patients.with_these_clinical_events(
first_dose_code,
returning="binary_flag",
between=["index_date", "index_date + 1 month"],
return_expectations={"incidence": 0.4}),
second_dose=patients.with_these_clinical_events(
second_dose_code,
returning="binary_flag",
between=["index_date", "index_date + 1 month"],
return_expectations={"incidence": 0.4}),
)
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": {
"ratios": {
"M": 0.49,
"F": 0.51
}
},
}),
# https://github.com/ebmdatalab/tpp-sql-notebook/issues/52
imd=patients.address_as_of(
from_date,
returning="index_of_multiple_deprivation",
round_to_nearest=100,
return_expectations={
"rate": "universal",
"category": {
"ratios": {
"100": 0.1,
"200": 0.2,
"300": 0.7
}
},
},
),
# https://github.com/ebmdatalab/tpp-sql-notebook/issues/54
stp=patients.registered_practice_as_of(
from_date,
returning="stp_code",
return_expectations={
"rate": "universal",
"category": {
"ratios": {
"STP1": 0.1,
"STP2": 0.1,
"STP3": 0.1,
"STP4": 0.1,
"STP5": 0.1,
"STP6": 0.1,
"STP7": 0.1,
"STP8": 0.1,
"STP9": 0.1,
"STP10": 0.1,
}
},
},
),
# region - one of NHS England 9 regions
region=patients.registered_practice_as_of(
from_date,
returning="nuts1_region_name",
return_expectations={
"rate": "universal",
"category": {
"ratios": {
"North East": 0.1,
"North West": 0.1,
"Yorkshire and the Humber": 0.1,
"East Midlands": 0.1,
"West Midlands": 0.1,
"East of England": 0.1,
"London": 0.2,
"South East": 0.2,
},
},
},
),
# covid-related code dates
**date_X("codes_antigen_negative", n=m),
**date_X("codes_exposure_to_disease", n=n),
**date_X("codes_historic_covid", n=n),
**date_X("codes_potential_historic_covid", n=m),
**date_X("codes_probable_covid", n=m),
**date_X("codes_probable_covid_pos_test", n=n),
**date_X("codes_probable_covid_sequelae", n=n),
**date_X("codes_suspected_covid_advice", n=m),
**date_X("codes_suspected_covid_had_test", n=m),
**date_X("codes_suspected_covid_isolation", n=n),
**date_X("codes_suspected_covid_nonspecific", n=n),
**date_X("codes_suspected_covid", n=m),
**date_X("codes_covid_unrelated_to_case_status", n=m),
**date_X("codes_suspected_covid_had_antigen_test", n=n),
**sgss_X(n=n),
# Outcomes
died_ons_covid=patients.with_these_codes_on_death_certificate(
codes_covid_death,
returning="binary_flag",
on_or_after=from_date,
match_only_underlying_cause=False,
return_expectations={"date": {
"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={
"category": {
"ratios": {
"alive": 0.8,
"covid-death": 0.1,
"non-covid-death": 0.1
}
}
},
),
date_died_ons=patients.died_from_any_cause(
returning="date_of_death",
on_or_after=from_date,
date_format="YYYY-MM-DD",
return_expectations={"date": {
"earliest": from_date
}},
),
)
study = StudyDefinition(
# Configure the expectations framework
default_expectations={
"date": {
"earliest": "1900-01-01",
"latest": "today"
},
"rate": "uniform",
"incidence": 0.5,
},
# STUDY POPULATION
population=patients.satisfying(
"""
has_follow_up AND
(age >=18 AND age <= 110) AND
(rheumatoid OR osteoarthritis) AND
imd >0 AND NOT (
(has_asthma AND saba_single) OR
aspirin_ten_years OR
stroke OR
mi OR
gi_bleed_ulcer
)
""",
has_follow_up=patients.registered_with_one_practice_between(
"2019-02-28", "2020-02-29"),
has_asthma=patients.with_these_clinical_events(
current_asthma_codes,
between=["2017-02-28", "2020-02-29"],
),
),
# The rest of the lines define the covariates with from the protocol with associated GitHub issues
# OUTCOMES
died_ons_covid_flag_any=patients.with_these_codes_on_death_certificate(
covid_identification,
on_or_after="2020-03-01",
match_only_underlying_cause=False,
return_expectations={"date": {
"earliest": "2020-03-01"
}},
),
died_ons_covid_flag_underlying=patients.
with_these_codes_on_death_certificate(
covid_identification,
on_or_after="2020-03-01",
match_only_underlying_cause=True,
return_expectations={"date": {
"earliest": "2020-03-01"
}},
),
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"
}},
),
# PLACEHOLDER - SECONDARY OUTCOME:PRESENTING AT ED - this is a wip placeholder
aande_attendance_with_covid=patients.attended_emergency_care(
on_or_after="2020-03-01",
returning="date_arrived",
date_format="YYYY-MM-DD",
with_these_diagnoses=
ics_codes, # placeholder https://github.com/opensafely/cohort-extractor/issues/182#issuecomment-651782064
return_expectations={"date": {
"earliest": "2020-03-01"
}},
),
# MEDICATIONS
# NSAID
nsaid_last_three_years=patients.with_these_medications(
nsaid_codes,
between=["2017-02-28", "2020-02-29"],
returning="date",
find_last_match_in_period=True,
include_month=True,
include_day=False,
return_expectations={
"date": {
"earliest": "2017-02-28",
"latest": "2020-02-29"
}
},
),
nsaid_after_march=patients.with_these_medications(
nsaid_codes,
on_or_after="2020-03-01",
returning="date",
find_first_match_in_period=True,
include_month=True,
include_day=True,
return_expectations={
"date": {
"earliest": "2020-03-01",
"latest": "2020-05-29"
}
},
),
nsaid_last_four_months=patients.with_these_medications(
nsaid_codes,
between=["2019-11-01", "2020-02-29"],
returning="date",
find_last_match_in_period=True,
include_month=True,
include_day=False,
return_expectations={
"date": {
"earliest": "2017-02-28",
"latest": "2020-02-29"
}
},
),
nsaid_last_two_months=patients.with_these_medications(
nsaid_codes,
between=["2020-01-01", "2020-02-29"],
returning="date",
find_last_match_in_period=True,
include_month=True,
include_day=False,
return_expectations={
"date": {
"earliest": "2020-01-01",
"latest": "2020-02-29"
}
},
),
nsaid_last_month=patients.with_these_medications(
nsaid_codes,
between=["2020-02-01", "2020-02-29"],
returning="date",
find_last_match_in_period=True,
include_month=True,
include_day=False,
return_expectations={
"date": {
"earliest": "2020-02-01",
"latest": "2020-02-29"
}
},
),
# naproxen - high dose
naproxen_high=patients.with_these_medications(
naproxen_high_codes,
between=["2019-11-01", "2020-02-29"],
returning="date",
find_last_match_in_period=True,
include_month=True,
include_day=False,
return_expectations={
"date": {
"earliest": "2019-11-01",
"latest": "2020-02-29"
}
},
),
# naproxen low dose
naproxen_low=patients.with_these_medications(
naproxen_low_codes,
between=["2019-11-01", "2020-02-29"],
returning="date",
find_last_match_in_period=True,
include_month=True,
include_day=False,
return_expectations={
"date": {
"earliest": "2019-11-01",
"latest": "2020-02-29"
}
},
),
# naproxen - other
naproxen_other=patients.with_these_medications(
naproxen_other_codes,
between=["2019-11-01", "2020-02-29"],
returning="date",
find_last_match_in_period=True,
include_month=True,
include_day=False,
return_expectations={
"date": {
"earliest": "2019-11-01",
"latest": "2020-02-29"
}
},
),
# COX2 SPECIFIC
cox_medication=patients.with_these_medications(
cox_medication,
between=["2019-11-01", "2020-02-29"],
returning="date",
find_last_match_in_period=True,
include_month=True,
include_day=False,
return_expectations={
"date": {
"earliest": "2019-11-01",
"latest": "2020-02-29"
}
},
),
# ASPIRIN
aspirin_ten_years=patients.with_these_medications(
aspirin_med_codes,
between=["2010-02-01", "2020-02-29"],
returning="date",
find_last_match_in_period=True,
include_month=True,
include_day=False,
return_expectations={
"date": {
"earliest": "2010-11-01",
"latest": "2020-02-29"
}
},
),
aspirin_ever=patients.with_these_medications(
aspirin_med_codes,
on_or_before="2020-02-29",
returning="date",
find_last_match_in_period=True,
include_month=True,
include_day=False,
return_expectations={
"date": {
"earliest": "2010-11-01",
"latest": "2020-02-29"
}
},
),
# IBUPROFEN
ibuprofen=patients.with_these_medications(
ibuprofen_med_codes,
between=["2019-11-01", "2020-02-29"],
returning="date",
find_last_match_in_period=True,
include_month=True,
include_day=False,
return_expectations={
"date": {
"earliest": "2019-11-01",
"latest": "2020-02-29"
}
},
),
# indometacin
indometacin=patients.with_these_medications(
indometacin_codes,
between=["2019-11-01", "2020-02-29"],
returning="date",
find_last_match_in_period=True,
include_month=True,
include_day=False,
return_expectations={
"date": {
"earliest": "2017-02-28",
"latest": "2020-02-29"
}
},
),
# Oral steroid - prednisolone
steroid_prednisolone=patients.with_these_medications(
prednisolone_med_codes,
between=["2019-11-01", "2020-02-29"],
returning="date",
find_last_match_in_period=True,
include_month=True,
include_day=False,
return_expectations={
"date": {
"earliest": "2017-02-28",
"latest": "2020-02-29"
}
},
),
# hydroxychloqoquine
hydroxychloroquine=patients.with_these_medications(
hcq_med_code,
between=["2019-11-01", "2020-02-29"],
returning="date",
find_last_match_in_period=True,
include_month=True,
include_day=False,
return_expectations={
"date": {
"earliest": "2017-02-28",
"latest": "2020-02-29"
}
},
),
# dmards
dmards_primary_care=patients.with_these_medications(
dmards_med_code,
between=["2019-11-01", "2020-02-29"],
returning="date",
find_last_match_in_period=True,
include_month=True,
include_day=False,
return_expectations={
"date": {
"earliest": "2017-02-28",
"latest": "2020-02-29"
}
},
),
# The rest of the lines define the covariates with from the protocol with associated GitHub issues
# https://github.com/opensafely/nsaids-research/issues/1
# PATIENT DEMOGRAPHICS
age=patients.age_as_of(
"2020-03-01",
return_expectations={
"rate": "universal",
"int": {
"distribution": "population_ages"
},
},
),
sex=patients.sex(return_expectations={
"rate": "universal",
"category": {
"ratios": {
"M": 0.49,
"F": 0.51
}
},
}),
stp=patients.registered_practice_as_of(
"2020-02-29",
returning="stp_code",
return_expectations={
"rate": "universal",
"category": {
"ratios": {
"STP1": 0.1,
"STP2": 0.1,
"STP3": 0.1,
"STP4": 0.1,
"STP5": 0.1,
"STP6": 0.1,
"STP7": 0.1,
"STP8": 0.1,
"STP9": 0.1,
"STP10": 0.1,
}
},
},
),
imd=patients.address_as_of(
"2020-02-29",
returning="index_of_multiple_deprivation",
round_to_nearest=100,
return_expectations={
"rate": "universal",
"category": {
"ratios": {
"100": 0.1,
"200": 0.2,
"300": 0.7
}
},
},
),
msoa=patients.registered_practice_as_of(
"2020-02-01",
returning="msoa_code",
return_expectations={
"rate": "universal",
"category": {
"ratios": {
"MSOA1": 0.5,
"MSOA2": 0.5
}
},
},
),
rural_urban=patients.address_as_of(
"2020-02-01",
returning="rural_urban_classification",
return_expectations={
"rate": "universal",
"category": {
"ratios": {
"rural": 0.1,
"urban": 0.9
}
},
},
),
ethnicity=patients.with_these_clinical_events(
ethnicity_codes,
returning="category",
find_last_match_in_period=True,
include_date_of_match=True,
return_expectations={
"category": {
"ratios": {
"1": 0.8,
"5": 0.1,
"3": 0.1
}
},
"incidence": 0.75,
},
),
# CLINICAL COVARIATES
# BMI
bmi=patients.most_recent_bmi(
on_or_after="2010-02-01",
minimum_age_at_measurement=16,
include_measurement_date=True,
include_month=True,
return_expectations={
"incidence": 0.6,
"float": {
"distribution": "normal",
"mean": 35,
"stddev": 10
},
},
),
# SMOKING
smoking_status=patients.categorised_as(
{
"S": "most_recent_smoking_code = 'S'",
"E": """
most_recent_smoking_code = 'E' OR (
most_recent_smoking_code = 'N' AND ever_smoked
)
""",
"N": "most_recent_smoking_code = 'N' AND NOT ever_smoked",
"M": "DEFAULT",
},
return_expectations={
"category": {
"ratios": {
"S": 0.6,
"E": 0.1,
"N": 0.2,
"M": 0.1
}
}
},
most_recent_smoking_code=patients.with_these_clinical_events(
clear_smoking_codes,
find_last_match_in_period=True,
on_or_before="2020-02-29",
returning="category",
),
ever_smoked=patients.with_these_clinical_events(
filter_codes_by_category(clear_smoking_codes, include=["S", "E"]),
on_or_before="2020-02-29",
),
),
smoking_status_date=patients.with_these_clinical_events(
clear_smoking_codes,
on_or_before="2020-02-29",
return_last_date_in_period=True,
include_month=True,
return_expectations={"date": {
"latest": "2020-02-29"
}},
),
# HYPERTENSION - CLINICAL CODES ONLY
hypertension=patients.with_these_clinical_events(
hypertension_codes,
on_or_before="2020-02-29",
return_first_date_in_period=True,
include_month=True,
return_expectations={"date": {
"latest": "2020-02-29"
}},
),
# HEART FAILURE
heart_failure=patients.with_these_clinical_events(
heart_failure_codes,
on_or_before="2020-02-29",
return_first_date_in_period=True,
include_month=True,
return_expectations={"date": {
"latest": "2020-02-29"
}},
),
# OTHER HEART DISEASES
other_heart_disease=patients.with_these_clinical_events(
other_heart_disease_codes,
on_or_before="2020-02-29",
return_first_date_in_period=True,
include_month=True,
return_expectations={"date": {
"latest": "2020-02-29"
}},
),
# DIABETES
diabetes=patients.with_these_clinical_events(
diabetes_codes,
on_or_before="2020-02-29",
return_first_date_in_period=True,
include_month=True,
return_expectations={"date": {
"latest": "2020-02-29"
}},
),
hba1c_mmol_per_mol=patients.with_these_clinical_events(
hba1c_new_codes,
find_last_match_in_period=True,
on_or_before="2020-02-29",
returning="numeric_value",
include_date_of_match=True,
include_month=True,
return_expectations={
"date": {
"latest": "2020-02-29"
},
"float": {
"distribution": "normal",
"mean": 40.0,
"stddev": 20
},
"incidence": 0.95,
},
),
hba1c_percentage=patients.with_these_clinical_events(
hba1c_old_codes,
find_last_match_in_period=True,
on_or_before="2020-02-29",
returning="numeric_value",
include_date_of_match=True,
include_month=True,
return_expectations={
"date": {
"latest": "2020-02-29"
},
"float": {
"distribution": "normal",
"mean": 5,
"stddev": 2
},
"incidence": 0.95,
},
),
# COPD
copd=patients.with_these_clinical_events(
copd_codes,
on_or_before="2020-02-29",
return_first_date_in_period=True,
include_month=True,
return_expectations={"date": {
"latest": "2020-02-29"
}},
),
# OTHER RESPIRATORY DISEASES
other_respiratory=patients.with_these_clinical_events(
other_respiratory_codes,
on_or_before="2020-02-29",
return_first_date_in_period=True,
include_month=True,
return_expectations={"date": {
"latest": "2020-02-29"
}},
),
# CURRENT ASTHMA
asthma=patients.with_these_clinical_events(
current_asthma_codes,
on_or_before="2020-02-29",
return_first_date_in_period=True,
include_month=True,
return_expectations={"date": {
"latest": "2020-02-29"
}},
),
# CANCER - 3 TYPES
cancer=patients.with_these_clinical_events(
combine_codelists(lung_cancer_codes, haem_cancer_codes,
other_cancer_codes),
on_or_before="2020-02-29",
return_first_date_in_period=True,
include_month=True,
return_expectations={"date": {
"latest": "2020-02-29"
}},
),
# IMMUNOSUPPRESSION
#### PERMANENT
permanent_immunodeficiency=patients.with_these_clinical_events(
combine_codelists(
hiv_codes,
permanent_immune_codes,
sickle_cell_codes,
organ_transplant_codes,
spleen_codes,
),
on_or_before="2020-02-29",
return_last_date_in_period=True,
include_month=True,
return_expectations={"date": {
"latest": "2020-02-29"
}},
),
aplastic_anaemia=patients.with_these_clinical_events(
aplastic_codes,
between=["2019-03-01", "2020-02-29"],
return_last_date_in_period=True,
include_month=True,
return_expectations={
"date": {
"earliest": "2019-03-01",
"latest": "2020-02-29"
}
},
),
#### TEMPORARY
temporary_immunodeficiency=patients.with_these_clinical_events(
temp_immune_codes,
between=["2019-03-01", "2020-02-29"],
return_last_date_in_period=True,
include_month=True,
return_expectations={
"date": {
"earliest": "2019-03-01",
"latest": "2020-02-29"
}
},
),
# CKD
creatinine=patients.with_these_clinical_events(
creatinine_codes,
find_last_match_in_period=True,
between=["2019-02-28", "2020-02-29"],
returning="numeric_value",
include_date_of_match=True,
include_month=True,
return_expectations={
"float": {
"distribution": "normal",
"mean": 60.0,
"stddev": 15
},
"date": {
"earliest": "2019-02-28",
"latest": "2020-02-29"
},
"incidence": 0.95,
},
),
#### end stage renal disease codes incl. dialysis / transplant
esrf=patients.with_these_clinical_events(
ckd_codes, # CHECK IS THIS DEF RIGHT HERE
on_or_before="2020-02-29",
return_last_date_in_period=True,
include_month=True,
return_expectations={"date": {
"latest": "2020-02-29"
}},
),
#### stroke
stroke=patients.with_these_clinical_events(
stroke_codes,
on_or_before="2020-02-29",
return_last_date_in_period=True,
include_month=True,
return_expectations={"date": {
"latest": "2020-02-29"
}},
),
#### Myocardial infarction
mi=patients.with_these_clinical_events(
mi_codes,
on_or_before="2020-02-29",
return_last_date_in_period=True,
include_month=True,
return_expectations={"date": {
"latest": "2020-02-29"
}},
),
#### GI BLEED
gi_bleed_ulcer=patients.with_these_clinical_events(
gi_bleed_ulcer_codes,
on_or_before="2020-02-29",
return_last_date_in_period=True,
include_month=True,
return_expectations={"date": {
"latest": "2020-02-29"
}},
),
# OSTEOARTHRITIS
osteoarthritis=patients.with_these_clinical_events(
osteoarthritis_codes,
on_or_before="2020-02-29",
return_last_date_in_period=True,
include_month=True,
return_expectations={"date": {
"latest": "2020-02-29"
}},
),
# RHEUMATOID ARTHRITIS
rheumatoid=patients.with_these_clinical_events(
rheumatoid_codes,
on_or_before="2020-02-29",
return_last_date_in_period=True,
include_month=True,
return_expectations={"date": {
"latest": "2020-02-29"
}},
),
# RHEUMATOID ARTHRITIS/OSTEOARTHRITIS MIXED
mixed_arthritis=patients.categorised_as(
{
"R": "rheumatoid = 'R'",
"O": "osteoarthritis = 'O'",
"RO": """
rheumatoid OR osteoarthritis
""",
"M": "DEFAULT",
},
return_expectations={
"category": {
"ratios": {
"R": 0.3,
"O": 0.1,
"RO": 0.2,
"M": 0.4
}
}
},
),
# FLU VACCINATION STATUS
flu_vaccine_tpp_table=patients.with_tpp_vaccination_record(
target_disease_matches="INFLUENZA",
between=["2019-09-01", "2020-02-29"], # current flu season
returning="date",
find_first_match_in_period=True,
return_expectations={
"date": {
"earliest": "2019-09-01",
"latest": "2020-02-29"
}
},
),
flu_vaccine_med=patients.with_these_medications(
flu_med_codes,
between=["2019-09-01", "2020-02-29"], # current flu season
returning="date",
find_last_match_in_period=True,
include_month=True,
include_day=True,
return_expectations={
"date": {
"earliest": "2019-09-01",
"latest": "2020-02-29"
}
},
),
flu_vaccine_clinical=patients.with_these_clinical_events(
flu_clinical_given_codes,
ignore_days_where_these_codes_occur=flu_clinical_not_given_codes,
between=["2019-09-01", "2020-02-29"], # current flu season
return_first_date_in_period=True,
include_month=True,
return_expectations={
"date": {
"earliest": "2019-09-01",
"latest": "2020-02-29"
}
},
),
flu_vaccine=patients.satisfying(
"""
flu_vaccine_tpp_table OR
flu_vaccine_med OR
flu_vaccine_clinical
""", ),
# PNEUMOCOCCAL VACCINATION STATUS
pneumococcal_vaccine_tpp_table=patients.with_tpp_vaccination_record(
target_disease_matches="PNEUMOCOCCAL",
between=["2015-03-01", "2020-02-29"],
returning="date",
find_last_match_in_period=True,
return_expectations={
"date": {
"earliest": "2015-03-01",
"latest": "2020-02-29"
}
},
),
pneumococcal_vaccine_med=patients.with_these_medications(
pneumococcal_med_codes,
between=["2015-03-01", "2020-02-29"], # past five years
returning="date",
return_first_date_in_period=True,
include_month=True,
return_expectations={
"date": {
"earliest": "2015-03-01",
"latest": "2020-02-29"
}
},
),
pneumococcal_vaccine_clinical=patients.with_these_clinical_events(
pneumococcal_clinical_given_codes,
ignore_days_where_these_codes_occur=
pneumococcal_clinical_not_given_codes,
between=["2015-03-01", "2020-02-29"], # past five years
return_first_date_in_period=True,
include_month=True,
return_expectations={
"date": {
"earliest": "2015-03-01",
"latest": "2020-02-29"
}
},
),
pneumococcal_vaccine=patients.satisfying(
"""
pneumococcal_vaccine_tpp_table OR
pneumococcal_vaccine_med OR
pneumococcal_vaccine_clinical
""", ),
# STATIN USAGE
statin=patients.with_these_medications(
statin_med_codes,
between=["2019-11-01", "2020-02-29"],
returning="date",
find_last_match_in_period=True,
include_month=True,
include_day=False,
return_expectations={
"date": {
"earliest": "2019-11-01",
"latest": "2020-02-29"
}
},
),
# PROTON PUMP INHIBITOR USAGE
ppi=patients.with_these_medications(
ppi_med_codes,
between=["2019-11-01", "2020-02-29"],
returning="date",
find_last_match_in_period=True,
include_month=True,
include_day=False,
return_expectations={
"date": {
"earliest": "2019-11-01",
"latest": "2020-02-29"
}
},
),
#### SABA SINGLE CONSTITUENT - asthma treatment
saba_single=patients.with_these_medications(
saba_med_codes,
between=["2019-11-01", "2020-02-29"],
returning="date",
find_last_match_in_period=True,
include_month=True,
include_day=False,
return_expectations={
"date": {
"earliest": "2019-11-01",
"latest": "2020-02-29"
},
},
),
##A&E ATTENDANCE IN PREVIOUS YEAR
annde_attendance_last_year=patients.attended_emergency_care(
between=["2019-03-01", "2020-02-29"],
returning="number_of_matches_in_period",
return_expectations={
"int": {
"distribution": "normal",
"mean": 2,
"stddev": 2
},
"date": {
"earliest": "2019-03-01",
"latest": "2020-02-29"
},
"incidence": 0.3,
},
),
### GP CONSULTATION RATE
gp_consult_count=patients.with_gp_consultations(
between=["2019-03-01", "2020-02-29"],
returning="number_of_matches_in_period",
return_expectations={
"int": {
"distribution": "normal",
"mean": 4,
"stddev": 2
},
"date": {
"earliest": "2019-03-01",
"latest": "2020-02-29"
},
"incidence": 0.7,
},
),
has_consultation_history=patients.
with_complete_gp_consultation_history_between(
"2019-03-01",
"2020-02-29",
return_expectations={"incidence": 0.9},
),
)
study = StudyDefinition(
# Configure the expectations framework (optional)
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,
between=["2017-02-28", "2020-02-29"],
return_expectations={"incidence": 0.05},
),
other_respiratory=patients.with_these_clinical_events(
other_respiratory_codes,
on_or_before="2020-02-29",
return_expectations={"incidence": 0.05},
),
#### NEBULES
nebules=patients.with_these_medications(
nebulised_med_codes,
between=["2019-02-28", "2020-02-29"],
return_expectations={"incidence": 0.05},
),
ltra_single=patients.with_these_medications(
leukotriene_med_codes,
between=["2019-11-01", "2020-02-29"],
return_expectations={"incidence": 0.05},
),
)
study = StudyDefinition(
# Configure the expectations framework (optional)
default_expectations={
"date": {
"earliest": "1970-01-01",
"latest": "today"
},
"rate": "uniform",
"incidence": 0.2,
},
## STUDY POPULATION (required)
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
"""),
),
## 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,
returning="date_admitted",
return_expectations={"date": {
"earliest": "2020-03-01"
}},
),
died_date_cpns=patients.with_death_recorded_in_cpns(
on_or_after="2020-03-01",
returning="date_of_death",
include_month=True,
include_day=True,
return_expectations={"date": {
"earliest": "2020-03-01"
}},
),
died_ons_covid_flag_any=patients.with_these_codes_on_death_certificate(
covid_codelist,
on_or_after="2020-03-01",
match_only_underlying_cause=False,
return_expectations={"date": {
"earliest": "2020-03-01"
}},
),
died_ons_covid_flag_underlying=patients.
with_these_codes_on_death_certificate(
covid_codelist,
on_or_after="2020-03-01",
match_only_underlying_cause=True,
return_expectations={"date": {
"earliest": "2020-03-01"
}},
),
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"
}},
),
## DEMOGRAPHIC INFORMATION
age=patients.age_as_of(
"2020-02-29",
return_expectations={
"rate": "universal",
"int": {
"distribution": "population_ages"
},
},
),
sex=patients.sex(return_expectations={
"rate": "universal",
"category": {
"ratios": {
"M": 0.49,
"F": 0.51
}
},
}),
stp=patients.registered_practice_as_of(
"2020-02-29",
returning="stp_code",
return_expectations={
"rate": "universal",
"category": {
"ratios": {
"STP1": 0.1,
"STP2": 0.1,
"STP3": 0.1,
"STP4": 0.1,
"STP5": 0.1,
"STP6": 0.1,
"STP7": 0.1,
"STP8": 0.1,
"STP9": 0.1,
"STP10": 0.1,
}
},
},
),
imd=patients.address_as_of(
"2020-02-29",
returning="index_of_multiple_deprivation",
round_to_nearest=100,
return_expectations={
"rate": "universal",
"category": {
"ratios": {
"100": 0.1,
"200": 0.2,
"300": 0.7
}
},
},
),
ethnicity=patients.with_these_clinical_events(
ethnicity_codes,
returning="category",
find_last_match_in_period=True,
include_date_of_match=True,
return_expectations={
"category": {
"ratios": {
"1": 0.8,
"5": 0.1,
"3": 0.1
}
},
"incidence": 0.75,
},
),
## COVARIATES
bmi=patients.most_recent_bmi(
between=["2010-02-28", "2020-02-29"],
minimum_age_at_measurement=16,
include_measurement_date=True,
include_month=True,
return_expectations={
"date": {},
"float": {
"distribution": "normal",
"mean": 35,
"stddev": 10
},
"incidence": 0.95,
},
),
smoking_status=patients.categorised_as(
{
"S": "most_recent_smoking_code = 'S'",
"E": """
most_recent_smoking_code = 'E' OR (
most_recent_smoking_code = 'N' AND ever_smoked
)
""",
"N": "most_recent_smoking_code = 'N' AND NOT ever_smoked",
"M": "DEFAULT",
},
return_expectations={
"category": {
"ratios": {
"S": 0.6,
"E": 0.1,
"N": 0.2,
"M": 0.1
}
}
},
most_recent_smoking_code=patients.with_these_clinical_events(
clear_smoking_codes,
find_last_match_in_period=True,
on_or_before="2020-02-29",
returning="category",
),
ever_smoked=patients.with_these_clinical_events(
filter_codes_by_category(clear_smoking_codes, include=["S", "E"]),
on_or_before="2020-02-29",
),
),
smoking_status_date=patients.with_these_clinical_events(
clear_smoking_codes,
on_or_before="2020-02-29",
return_last_date_in_period=True,
include_month=True,
return_expectations={"date": {
"latest": "2020-02-29"
}},
),
#### HIGH DOSE ICS - all preparation
high_dose_ics=patients.with_these_medications(
high_dose_ics_med_codes,
between=["2019-11-01", "2020-02-29"],
return_last_date_in_period=True,
include_month=True,
return_expectations={
"date": {
"earliest": "2019-11-01",
"latest": "2020-02-29"
}
},
),
#### HIGH DOSE ICS - single ingredient preparations
high_dose_ics_single_ing=patients.with_these_medications(
high_dose_ics_single_ingredient_med_codes,
between=["2019-11-01", "2020-02-29"],
return_last_date_in_period=True,
include_month=True,
return_expectations={
"date": {
"earliest": "2019-11-01",
"latest": "2020-02-29"
}
},
),
#### HIGH DOSE ICS - multiple ingredient preparation
high_dose_ics_multiple_ingredient=patients.with_these_medications(
high_dose_ics_multiple_ingredient_med_codes,
between=["2019-11-01", "2020-02-29"],
return_last_date_in_period=True,
include_month=True,
return_expectations={
"date": {
"earliest": "2019-11-01",
"latest": "2020-02-29"
}
},
),
### LOW-MED DOSE ICS - single ingredient preparations
low_med_dose_ics_single_ingredient=patients.with_these_medications(
low_medium_ics_single_ingredient_med_codes,
between=["2019-11-01", "2020-02-29"],
return_last_date_in_period=True,
include_month=True,
return_expectations={
"date": {
"earliest": "2019-11-01",
"latest": "2020-02-29"
},
},
),
### LOW-MED DOSE ICS - multiple ingredient preparations
low_med_dose_ics_multiple_ingredient=patients.with_these_medications(
low_medium_ics_multiple_ingredient_med_codes,
between=["2019-11-01", "2020-02-29"],
return_last_date_in_period=True,
include_month=True,
),
### LOW-MED DOSE ICS - all preparation
low_med_dose_ics=patients.with_these_medications(
low_medium_ics_med_codes,
between=["2019-11-01", "2020-02-29"],
return_last_date_in_period=True,
include_month=True,
return_expectations={
"date": {
"earliest": "2019-11-01",
"latest": "2020-02-29"
},
},
),
#### ICS SINGLE CONSTITUENT
ics_single=patients.with_these_medications(
ics_single_med_codes,
between=["2019-11-01", "2020-02-29"],
return_last_date_in_period=True,
include_month=True,
return_expectations={
"date": {
"earliest": "2019-11-01",
"latest": "2020-02-29"
},
},
),
#### ORAL STEROIDS SINGLE CONSTITUENT
oral_steroids=patients.with_these_medications(
oral_steroid_med_codes,
between=["2019-11-01", "2020-02-29"],
return_last_date_in_period=True,
include_month=True,
return_expectations={
"date": {
"earliest": "2019-11-01",
"latest": "2020-02-29"
},
},
),
#### SABA SINGLE CONSTITUENT
saba_single=patients.with_these_medications(
saba_med_codes,
between=["2019-11-01", "2020-02-29"],
return_last_date_in_period=True,
include_month=True,
return_expectations={
"date": {
"earliest": "2019-11-01",
"latest": "2020-02-29"
},
},
),
#### SAMA SINGLE CONSTITUENT
sama_single=patients.with_these_medications(
sama_med_codes,
between=["2019-11-01", "2020-02-29"],
return_last_date_in_period=True,
include_month=True,
return_expectations={
"date": {
"earliest": "2019-11-01",
"latest": "2020-02-29"
},
},
),
#### LABA SINGLE CONSTITUENT
laba_single=patients.with_these_medications(
single_laba_med_codes,
between=["2019-11-01", "2020-02-29"],
return_last_date_in_period=True,
include_month=True,
return_expectations={
"date": {
"earliest": "2019-11-01",
"latest": "2020-02-29"
},
},
),
#### LAMA SINGLE CONSTITUENT
lama_single=patients.with_these_medications(
single_lama_med_codes,
between=["2019-11-01", "2020-02-29"],
return_last_date_in_period=True,
include_month=True,
return_expectations={
"date": {
"earliest": "2019-11-01",
"latest": "2020-02-29"
},
},
),
#### LABA + ICS
laba_ics=patients.with_these_medications(
laba_ics_med_codes,
between=["2019-11-01", "2020-02-29"],
return_last_date_in_period=True,
include_month=True,
return_expectations={
"date": {
"earliest": "2019-11-01",
"latest": "2020-02-29"
},
},
),
#### LABA + LAMA
laba_lama=patients.with_these_medications(
laba_lama_med_codes,
between=["2019-11-01", "2020-02-29"],
return_last_date_in_period=True,
include_month=True,
return_expectations={
"date": {
"earliest": "2019-11-01",
"latest": "2020-02-29"
},
},
),
#### LABA + LAMA + ICS
laba_lama_ics=patients.with_these_medications(
laba_lama__ics_med_codes,
between=["2019-11-01", "2020-02-29"],
return_last_date_in_period=True,
include_month=True,
return_expectations={
"date": {
"earliest": "2019-11-01",
"latest": "2020-02-29"
},
},
),
#### LTRA SINGLE CONSTITUENT
ltra_single=patients.with_these_medications(
leukotriene_med_codes,
between=["2019-11-01", "2020-02-29"],
return_last_date_in_period=True,
include_month=True,
return_expectations={
"date": {
"earliest": "2019-11-01",
"latest": "2020-02-29"
},
},
),
### OXYGEN THERAPY LEFT OUT AT PRESENT DUE TO POOR RECORDS
### COPD
copd=patients.with_these_clinical_events(
copd_codes,
on_or_before="2020-02-29",
return_first_date_in_period=True,
include_month=True,
return_expectations={"date": {
"latest": "2020-02-29"
}},
),
### OTHER RESPIRATORY
other_respiratory=patients.with_these_clinical_events(
other_respiratory_codes,
on_or_before="2020-02-29",
return_first_date_in_period=True,
include_month=True,
return_expectations={"date": {
"latest": "2020-02-29"
}},
),
### ASTHMA EVER
asthma_ever=patients.with_these_clinical_events(
asthma_ever_codes,
on_or_before="2020-02-29",
return_first_date_in_period=True,
include_month=True,
return_expectations={"date": {
"latest": "2020-02-29"
}},
),
### OTHER HEART DISEASE
other_heart_disease=patients.with_these_clinical_events(
other_heart_disease_codes,
on_or_before="2020-02-29",
return_first_date_in_period=True,
include_month=True,
return_expectations={"date": {
"latest": "2020-02-29"
}},
),
### ILI
ili=patients.with_these_clinical_events(
ili_codes,
return_first_date_in_period=True,
include_month=True,
between=["2016-09-01", "2020-02-29"],
return_expectations={
"date": {
"earliest": "2019-09-01",
"latest": "2020-02-29"
}
},
),
### HYPERTENSION
hypertension=patients.with_these_clinical_events(
hypertension_codes,
on_or_before="2020-02-29",
return_first_date_in_period=True,
include_month=True,
return_expectations={"date": {
"latest": "2020-02-29"
}},
),
### HEART FAILURE
heart_failure=patients.with_these_clinical_events(
heart_failure_codes,
on_or_before="2020-02-29",
return_first_date_in_period=True,
include_month=True,
return_expectations={"date": {
"latest": "2020-02-29"
}},
),
#### SYSTOLIC BLOOD PRESSURE
bp_sys=patients.mean_recorded_value(
systolic_blood_pressure_codes,
on_most_recent_day_of_measurement=True,
on_or_before="2020-02-29",
include_measurement_date=True,
include_month=True,
return_expectations={
"float": {
"distribution": "normal",
"mean": 80,
"stddev": 10
},
"date": {
"latest": "2020-02-29"
},
"incidence": 0.95,
},
),
### DIASTOLIC BLOOD PRESSURE
bp_dias=patients.mean_recorded_value(
diastolic_blood_pressure_codes,
on_most_recent_day_of_measurement=True,
on_or_before="2020-02-29",
include_measurement_date=True,
include_month=True,
return_expectations={
"float": {
"distribution": "normal",
"mean": 120,
"stddev": 10
},
"date": {
"latest": "2020-02-29"
},
"incidence": 0.95,
},
),
### DIABETES
diabetes=patients.with_these_clinical_events(
diabetes_codes,
on_or_before="2020-02-29",
return_first_date_in_period=True,
include_month=True,
return_expectations={"date": {
"latest": "2020-02-29"
}},
),
hba1c_mmol_per_mol=patients.with_these_clinical_events(
hba1c_new_codes,
find_last_match_in_period=True,
on_or_before="2020-02-29",
returning="numeric_value",
include_date_of_match=True,
include_month=True,
return_expectations={
"date": {
"latest": "2020-02-29"
},
"float": {
"distribution": "normal",
"mean": 40.0,
"stddev": 20
},
"incidence": 0.95,
},
),
hba1c_percentage=patients.with_these_clinical_events(
hba1c_old_codes,
find_last_match_in_period=True,
on_or_before="2020-02-29",
returning="numeric_value",
include_date_of_match=True,
include_month=True,
return_expectations={
"date": {
"latest": "2020-02-29"
},
"float": {
"distribution": "normal",
"mean": 5,
"stddev": 2
},
"incidence": 0.95,
},
),
### CANCER - 3 TYPES
lung_cancer=patients.with_these_clinical_events(
lung_cancer_codes,
on_or_before="2020-02-29",
return_first_date_in_period=True,
include_month=True,
return_expectations={"date": {
"latest": "2020-02-29"
}},
),
haem_cancer=patients.with_these_clinical_events(
haem_cancer_codes,
on_or_before="2020-02-29",
return_first_date_in_period=True,
include_month=True,
return_expectations={"date": {
"latest": "2020-02-29"
}},
),
other_cancer=patients.with_these_clinical_events(
other_cancer_codes,
on_or_before="2020-02-29",
return_first_date_in_period=True,
include_month=True,
return_expectations={"date": {
"latest": "2020-02-29"
}},
),
# IMMUNOSUPPRESSION - 4 TYPES
# https://github.com/ebmdatalab/tpp-sql-notebook/issues/36
aplastic_anaemia=patients.with_these_clinical_events(
aplastic_codes,
on_or_before="2020-02-29",
return_last_date_in_period=True,
include_month=True,
return_expectations={"date": {
"latest": "2020-02-29"
}},
),
hiv=patients.with_these_clinical_events(
hiv_codes,
on_or_before="2020-02-29",
return_first_date_in_period=True,
include_month=True,
return_expectations={"date": {
"latest": "2020-02-29"
}},
),
permanent_immunodeficiency=patients.with_these_clinical_events(
permanent_immune_codes,
on_or_before="2020-02-29",
return_first_date_in_period=True,
include_month=True,
return_expectations={"date": {
"latest": "2020-02-29"
}},
),
temporary_immunodeficiency=patients.with_these_clinical_events(
temp_immune_codes,
between=["2019-03-01", "2020-02-29"],
return_last_date_in_period=True,
include_month=True,
return_expectations={
"date": {
"earliest": "2019-03-01",
"latest": "2020-02-29"
}
},
),
### CHRONIC KIDNEY DISEASE
creatinine=patients.with_these_clinical_events(
creatinine_codes,
find_last_match_in_period=True,
between=["2019-02-28", "2020-02-29"],
returning="numeric_value",
include_date_of_match=True,
include_month=True,
return_expectations={
"float": {
"distribution": "normal",
"mean": 60.0,
"stddev": 15
},
"date": {
"earliest": "2019-02-28",
"latest": "2020-02-29"
},
"incidence": 0.95,
},
),
#### end stage renal disease codes incl. dialysis / transplant
esrf=patients.with_these_clinical_events(
ckd_codes,
on_or_before="2020-02-29",
return_last_date_in_period=True,
include_month=True,
return_expectations={"date": {
"latest": "2020-02-29"
}},
),
### VACCINATION HISTORY
flu_vaccine_tpp_table=patients.with_tpp_vaccination_record(
target_disease_matches="INFLUENZA",
between=["2019-09-01", "2020-02-29"], # current flu season
find_first_match_in_period=True,
returning="date",
return_expectations={
"date": {
"earliest": "2019-09-01",
"latest": "2020-02-29"
}
},
),
flu_vaccine_med=patients.with_these_medications(
flu_med_codes,
between=["2019-09-01", "2020-02-29"], # current flu season
return_first_date_in_period=True,
include_month=True,
return_expectations={
"date": {
"earliest": "2019-09-01",
"latest": "2020-02-29"
}
},
),
flu_vaccine_clinical=patients.with_these_clinical_events(
flu_clinical_given_codes,
ignore_days_where_these_codes_occur=flu_clinical_not_given_codes,
between=["2019-09-01", "2020-02-29"], # current flu season
return_first_date_in_period=True,
include_month=True,
return_expectations={
"date": {
"earliest": "2019-09-01",
"latest": "2020-02-29"
}
},
),
flu_vaccine=patients.satisfying(
"""
flu_vaccine_tpp_table OR
flu_vaccine_med OR
flu_vaccine_clinical
""", ),
# PNEUMOCOCCAL VACCINE
pneumococcal_vaccine_tpp_table=patients.with_tpp_vaccination_record(
target_disease_matches="PNEUMOCOCCAL",
between=["2015-03-01", "2020-02-29"],
find_first_match_in_period=True,
returning="date",
return_expectations={
"date": {
"earliest": "2015-03-01",
"latest": "2020-02-29"
}
},
),
pneumococcal_vaccine_med=patients.with_these_medications(
pneumococcal_med_codes,
between=["2015-03-01", "2020-02-29"], # past five years
return_first_date_in_period=True,
include_month=True,
return_expectations={
"date": {
"earliest": "2015-03-01",
"latest": "2020-02-29"
}
},
),
pneumococcal_vaccine_clinical=patients.with_these_clinical_events(
pneumococcal_clinical_given_codes,
ignore_days_where_these_codes_occur=
pneumococcal_clinical_not_given_codes,
between=["2015-03-01", "2020-02-29"], # past five years
return_first_date_in_period=True,
include_month=True,
return_expectations={
"date": {
"earliest": "2015-03-01",
"latest": "2020-02-29"
}
},
),
pneumococcal_vaccine=patients.satisfying(
"""
pneumococcal_vaccine_tpp_table OR
pneumococcal_vaccine_med OR
pneumococcal_vaccine_clinical
""", ),
### EXACERBATION
# count
exacerbation_count=patients.with_these_medications(
oral_steroid_med_codes,
between=["2019-03-01", "2020-02-29"],
ignore_days_where_these_clinical_codes_occur=combine_codelists(
sle_codes,
interstital_lung_codes,
ra_codes,
ms_codes,
temporal_arteritis_codes,
),
returning="number_of_episodes",
episode_defined_as="series of events each <= 14 days apart",
return_expectations={
"int": {
"distribution": "normal",
"mean": 2,
"stddev": 1
},
"incidence": 0.2,
},
),
# # binary flag
exacerbations=patients.satisfying(
"""
exacerbation_count > 0
""", ),
### INSULIN USE
insulin=patients.with_these_medications(
insulin_med_codes,
between=["2019-11-01", "2020-02-29"],
return_last_date_in_period=True,
include_month=True,
return_expectations={
"date": {
"earliest": "2019-11-01",
"latest": "2020-02-29"
}
},
),
### STATIN USE
statin=patients.with_these_medications(
statin_med_codes,
between=["2019-11-01", "2020-02-29"],
return_last_date_in_period=True,
include_month=True,
return_expectations={
"date": {
"earliest": "2019-11-01",
"latest": "2020-02-29"
}
},
),
### GP CONSULTATION RATE
gp_consult_count=patients.with_gp_consultations(
between=["2019-03-01", "2020-02-29"],
returning="number_of_matches_in_period",
return_expectations={
"int": {
"distribution": "normal",
"mean": 4,
"stddev": 2
},
"date": {
"earliest": "2019-03-01",
"latest": "2020-02-29"
},
"incidence": 0.7,
},
),
has_consultation_history=patients.
with_complete_gp_consultation_history_between(
"2019-03-01",
"2020-02-29",
return_expectations={"incidence": 0.9},
),
)
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"),
# Set index date to start date
index_date="2020-02-01",
## DEMOGRAPHIC INFORMATION
### Age
age=patients.age_as_of(
"2020-03-31",
return_expectations={
"rate": "universal",
"int": {
"distribution": "population_ages"
},
"incidence": 0.001
},
),
### Sex
sex=patients.sex(return_expectations={
"rate": "universal",
"category": {
"ratios": {
"M": 0.49,
"F": 0.51
}
},
}),
### Ethnicity
ethnicity=patients.with_these_clinical_events(
ethnicity_codes,
returning="category",
find_last_match_in_period=True,
on_or_before="index_date",
return_expectations={
"category": {
"ratios": {
"1": 0.25,
"2": 0.05,
"3": 0.05,
"4": 0.05,
"5": 0.05,
"6": 0.05,
"7": 0.05,
"8": 0.05,
"9": 0.05,
"10": 0.05,
"11": 0.05,
"12": 0.05,
"13": 0.05,
"14": 0.05,
"15": 0.05,
"16": 0.05,
}
},
"incidence": 0.75,
},
),
### BMI
bmi=patients.with_these_clinical_events(
bmi_codes,
returning="numeric_value",
ignore_missing_values=True,
find_last_match_in_period=True,
on_or_before="index_date",
return_expectations={
"float": {
"distribution": "normal",
"mean": 28,
"stddev": 5
},
},
),
### Diabetes
diabetes=patients.with_these_clinical_events(
diabetes_codes,
returning="binary_flag",
find_last_match_in_period=True,
on_or_before="index_date",
return_expectations={"incidence": 0.10},
),
### Chronic liver disease
chronic_liver_disease=patients.with_these_clinical_events(
chronis_liver_disease_codes,
on_or_before="index_date",
returning="binary_flag",
return_expectations={"incidence": 0.01},
),
### Index of multiple deprivation
imd=patients.categorised_as(
{
"0": "DEFAULT",
"1":
"""index_of_multiple_deprivation >=1 AND index_of_multiple_deprivation < 32844*1/5""",
"2":
"""index_of_multiple_deprivation >= 32844*1/5 AND index_of_multiple_deprivation < 32844*2/5""",
"3":
"""index_of_multiple_deprivation >= 32844*2/5 AND index_of_multiple_deprivation < 32844*3/5""",
"4":
"""index_of_multiple_deprivation >= 32844*3/5 AND index_of_multiple_deprivation < 32844*4/5""",
"5": """index_of_multiple_deprivation >= 32844*4/5 """,
},
index_of_multiple_deprivation=patients.address_as_of(
"index_date",
returning="index_of_multiple_deprivation",
round_to_nearest=100,
),
return_expectations={
"rate": "universal",
"category": {
"ratios": {
"0": 0.01,
"1": 0.20,
"2": 0.20,
"3": 0.20,
"4": 0.20,
"5": 0.19,
}
},
}),
### Region - NHS England 9 regions
region=patients.registered_practice_as_of(
"index_date",
returning="nuts1_region_name",
return_expectations={
"rate": "universal",
"category": {
"ratios": {
"North East": 0.1,
"North West": 0.1,
"Yorkshire and The Humber": 0.1,
"East Midlands": 0.1,
"West Midlands": 0.1,
"East": 0.1,
"London": 0.2,
"South West": 0.1,
"South East": 0.1,
},
},
},
),
### STP (regional grouping of practices)
stp=patients.registered_practice_as_of(
"index_date",
returning="stp_code",
return_expectations={
"rate": "universal",
"category": {
"ratios": {
"STP1": 0.1,
"STP2": 0.1,
"STP3": 0.1,
"STP4": 0.1,
"STP5": 0.1,
"STP6": 0.1,
"STP7": 0.1,
"STP8": 0.1,
"STP9": 0.1,
"STP10": 0.1,
}
},
},
),
### Urban vs rural
rural_urban=patients.address_as_of(
"index_date",
returning="rural_urban_classification",
return_expectations={
"rate": "universal",
"category": {
"ratios": {
1: 0.125,
2: 0.125,
3: 0.125,
4: 0.125,
5: 0.125,
6: 0.125,
7: 0.125,
8: 0.125
}
},
},
),
### History of covid
prior_covid_date=patients.with_these_clinical_events(
combine_codelists(
covid_primary_care_code,
covid_primary_care_positive_test,
covid_primary_care_sequalae,
),
returning="date",
date_format="YYYY-MM-DD",
on_or_before="index_date",
find_first_match_in_period=True,
return_expectations={"rate": "exponential_increase"},
),
)
study = StudyDefinition(
# 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)",
died=patients.died_from_any_cause(on_or_before=index_date,
returning="binary_flag"),
registered=patients.registered_as_of(index_date),
),
age=patients.age_as_of(index_date,
return_expectations={
"rate": "universal",
"int": {
"distribution": "population_ages"
}
}),
age_group=patients.categorised_as(
{
"0": "DEFAULT",
"16 - under 40": """ age >= 16 AND age < 40""",
"40 - under 50": """ age >= 40 AND age < 50""",
"50 - under 65": """ age >= 50 AND age < 65""",
"65 plus": """ age >= 65""",
},
return_expectations={
"rate": "universal",
"category": {
"ratios": {
"16 - under 40": 0.25,
"40 - under 50": 0.25,
"50 - under 65": 0.25,
"65 plus": 0.25,
}
},
},
),
stp=patients.registered_practice_as_of(
"index_date",
returning="stp_code",
return_expectations={
"category": {
"ratios": {
"STP1": 0.5,
"STP2": 0.5
}
},
},
),
first_dose=patients.with_these_clinical_events(
first_dose_code,
returning="binary_flag",
between=["index_date", "index_date + 1 month"],
return_expectations={"incidence": 0.4}),
second_dose=patients.with_these_clinical_events(
second_dose_code,
returning="binary_flag",
between=["index_date", "index_date + 1 month"],
return_expectations={"incidence": 0.4}),
ethnicity_white_british=patients.with_these_clinical_events(
ethnicity_white_british_code,
returning="binary_flag",
between=["index_date", "index_date + 1 month"],
return_expectations={"incidence": 0.4}),
ethnicity_white_irish=patients.with_these_clinical_events(
ethnicity_white_irish_code,
returning="binary_flag",
between=["index_date", "index_date + 1 month"],
return_expectations={"incidence": 0.4}),
ethnicity_white_other=patients.with_these_clinical_events(
ethnicity_white_other_code,
returning="binary_flag",
between=["index_date", "index_date + 1 month"],
return_expectations={"incidence": 0.4}),
ethnicity_mixed_white_caribbean=patients.with_these_clinical_events(
ethnicity_mixed_white_caribbean_code,
returning="binary_flag",
between=["index_date", "index_date + 1 month"],
return_expectations={"incidence": 0.4}),
ethnicity_mixed_white_african=patients.with_these_clinical_events(
ethnicity_mixed_white_african_code,
returning="binary_flag",
between=["index_date", "index_date + 1 month"],
return_expectations={"incidence": 0.4}),
ethnicity_mixed_white_asian=patients.with_these_clinical_events(
ethnicity_mixed_white_asian_code,
returning="binary_flag",
between=["index_date", "index_date + 1 month"],
return_expectations={"incidence": 0.4}),
ethnicity_mixed_other=patients.with_these_clinical_events(
ethnicity_mixed_other_code,
returning="binary_flag",
between=["index_date", "index_date + 1 month"],
return_expectations={"incidence": 0.4}),
ethnicity_asian_indian=patients.with_these_clinical_events(
ethnicity_asian_indian_code,
returning="binary_flag",
between=["index_date", "index_date + 1 month"],
return_expectations={"incidence": 0.4}),
ethnicity_asian_pak=patients.with_these_clinical_events(
ethnicity_asian_pak_code,
returning="binary_flag",
between=["index_date", "index_date + 1 month"],
return_expectations={"incidence": 0.4}),
ethnicity_mixed_asian_bang=patients.with_these_clinical_events(
ethnicity_mixed_asian_bang_code,
returning="binary_flag",
between=["index_date", "index_date + 1 month"],
return_expectations={"incidence": 0.4}),
ethnicity_asian_other=patients.with_these_clinical_events(
ethnicity_asian_other_code,
returning="binary_flag",
between=["index_date", "index_date + 1 month"],
return_expectations={"incidence": 0.4}),
ethnicity_black_caribbean=patients.with_these_clinical_events(
ethnicity_black_caribbean_code,
returning="binary_flag",
between=["index_date", "index_date + 1 month"],
return_expectations={"incidence": 0.4}),
ethnicity_black_african=patients.with_these_clinical_events(
ethnicity_black_african_code,
returning="binary_flag",
between=["index_date", "index_date + 1 month"],
return_expectations={"incidence": 0.4}),
ethnicity_black_other=patients.with_these_clinical_events(
ethnicity_black_other_code,
returning="binary_flag",
between=["index_date", "index_date + 1 month"],
return_expectations={"incidence": 0.4}),
ethnicity_chinese=patients.with_these_clinical_events(
ethnicity_chinese_code,
returning="binary_flag",
between=["index_date", "index_date + 1 month"],
return_expectations={"incidence": 0.4}),
ethnicity_other=patients.with_these_clinical_events(
ethnicity_other_code,
returning="binary_flag",
between=["index_date", "index_date + 1 month"],
return_expectations={"incidence": 0.4}),
ethnicity_non_other=patients.with_these_clinical_events(
ethnicity_non_other_code,
returning="binary_flag",
between=["index_date", "index_date + 1 month"],
return_expectations={"incidence": 0.4}),
ethnicity_not_stated=patients.with_these_clinical_events(
ethnicity_not_stated_code,
returning="binary_flag",
between=["index_date", "index_date + 1 month"],
return_expectations={"incidence": 0.4}),
ethnicity_not_recorded=patients.with_these_clinical_events(
ethnicity_not_recorded_code,
returning="binary_flag",
between=["index_date", "index_date + 1 month"],
return_expectations={"incidence": 0.4}),
ethnicity_not_given_refused=patients.with_these_clinical_events(
ethnicity_not_given_refused_code,
returning="binary_flag",
between=["index_date", "index_date + 1 month"],
return_expectations={"incidence": 0.4}),
ethnicity=patients.categorised_as(
{
"0": "DEFAULT",
"white_british": """ (ethnicity_white_british) """,
"white_irish": """ (ethnicity_white_irish) """,
"white_other": """ (ethnicity_white_other) """,
"mixed_white_caribbean": """ (ethnicity_mixed_white_caribbean) """,
"mixed_white_african": """ (ethnicity_mixed_white_african) """,
"mixed_white_asian": """ (ethnicity_mixed_white_asian) """,
"mixed_other": """ (ethnicity_mixed_other) """,
"asian_indian": """ (ethnicity_asian_indian) """,
"asian_pak": """ (ethnicity_asian_pak) """,
"mixed_asian_bang": """ (ethnicity_mixed_asian_bang) """,
"asian_other": """ (ethnicity_asian_other) """,
"black_caribbean": """ (ethnicity_black_caribbean) """,
"black_african": """ (ethnicity_black_african) """,
"black_other": """ (ethnicity_black_other) """,
"chinese": """ (ethnicity_chinese) """,
"other": """ (ethnicity_other) """,
"non_other": """ (ethnicity_non_other) """,
"not_stated": """ (ethnicity_not_stated) """,
"not_recorded": """ (ethnicity_not_recorded) """,
"not_given_refused": """ (ethnicity_not_given_refused) """,
},
return_expectations={
"rate": "universal",
"category": {
"ratios": {
"white_british": 0.05,
"white_irish": 0.05,
"white_other": 0.05,
"mixed_white_caribbean": 0.05,
"mixed_white_african": 0.05,
"mixed_white_asian": 0.05,
"mixed_other": 0.05,
"asian_indian": 0.05,
"asian_pak": 0.05,
"mixed_asian_bang": 0.05,
"asian_other": 0.05,
"black_caribbean": 0.05,
"black_african": 0.05,
"black_other": 0.05,
"chinese": 0.05,
"other": 0.05,
"non_other": 0.05,
"not_stated": 0.05,
"not_recorded": 0.05,
"not_given_refused": 0.05,
}
},
},
),
)
study = StudyDefinition(
# Configure the expectations framework
default_expectations={
"date": {
"earliest": "1900-01-01",
"latest": "today"
},
"rate": "exponential_increase",
},
# Define the study population
population=patients.registered_with_one_practice_between(
"2019-02-01", "2020-02-01"),
# Define input variables {
age=patients.age_as_of(
"2020-02-01",
return_expectations={
"rate": "universal",
"int": {
"distribution": "population_ages"
},
},
),
sex=patients.sex(return_expectations={
"rate": "universal",
"category": {
"ratios": {
"M": 0.49,
"F": 0.51
}
},
}),
cardiac_disease=patients.with_these_clinical_events(
cardiac_disease_codes,
returning="binary_flag",
return_expectations={"incidence": 0.2},
),
# }
# Define output variable
covid_on_death_certificate=patients.with_these_codes_on_death_certificate(
covid_codes,
match_only_underlying_cause=False,
return_expectations={"incidence": 0.001},
),
)
def test_validate_category_expectations():
categorised_codelist = codelist([("X", "Y")], system="ctv3")
categorised_codelist.has_categories = True
category_definitions = {"A": "sex = 'F'", "B": "sex = 'M'"}
study = StudyDefinition(population=patients.all())
# validate against codelists
with pytest.raises(ValueError):
study.validate_category_expectations(
codelist=categorised_codelist,
return_expectations={"category": {
"ratios": {
"X": 1
}
}},
)
study.validate_category_expectations(
codelist=categorised_codelist,
return_expectations={"category": {
"ratios": {
"Y": 1
}
}},
)
# validate against definitions
with pytest.raises(ValueError):
study.validate_category_expectations(
category_definitions=category_definitions,
return_expectations={"category": {
"ratios": {
"X": 1
}
}},
)
study.validate_category_expectations(
category_definitions=category_definitions,
return_expectations={"category": {
"ratios": {
"A": 1
}
}},
)
# validate that supplied category definitions override categories
# in codelists
with pytest.raises(ValueError):
study.validate_category_expectations(
codelist=categorised_codelist,
category_definitions=category_definitions,
return_expectations={"category": {
"ratios": {
"Y": 1
}
}},
)
study.validate_category_expectations(
codelist=categorised_codelist,
category_definitions=category_definitions,
return_expectations={"category": {
"ratios": {
"A": 1
}
}},
)
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"
},
"incidence": 0.5
},
),
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": "2020-08-01"
},
"incidence": 0.5
},
),
### Primary care COVID cases
covid_tpp_probable=patients.with_these_clinical_events(
combine_codelists(
covid_identification_in_primary_care_case_codes_clinical,
covid_identification_in_primary_care_case_codes_test,
covid_identification_in_primary_care_case_codes_seq),
return_first_date_in_period=True,
include_day=True,
return_expectations={
"date": {
"earliest": "2020-10-20"
},
"incidence": 0.2
},
),
# Any COVID vaccination (first dose)
covid_vacc_date=patients.with_tpp_vaccination_record(
target_disease_matches="SARS-2 CORONAVIRUS",
on_or_after="2020-12-01", # check all december to date
find_first_match_in_period=True,
returning="date",
date_format="YYYY-MM-DD",
return_expectations={
"date": {
"earliest":
"2020-12-08", # first vaccine administered on the 8/12
"latest": "2021-01-31",
},
"incidence": 0.1
},
),
### COVID test positive (SGSS)
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": "2020-06-01"
},
"incidence": 0.4
},
),
### SGSS positive in study period
sgss_pos_inrange=patients.with_test_result_in_sgss(
pathogen="SARS-CoV-2",
test_result="positive",
find_first_match_in_period=True,
between=["2020-11-16", "2021-01-11"],
returning="date",
date_format="YYYY-MM-DD",
return_expectations={
"date": {
"earliest": "2020-11-16",
"latest": "2021-01-11"
},
"incidence": 0.9
},
),
sgtf=patients.with_test_result_in_sgss(
pathogen="SARS-CoV-2",
test_result="positive",
find_first_match_in_period=True,
between=["2020-11-16", "2021-01-11"],
returning="s_gene_target_failure",
return_expectations={
"rate": "universal",
"category": {
"ratios": {
"0": 0.4,
"1": 0.4,
"9": 0.1,
"": 0.1
}
},
},
),
# SUS HOSPITAL ADMISSION
covid_admission_date=patients.admitted_to_hospital(
returning="date_admitted",
with_these_diagnoses=covid_codelist,
on_or_after="sgss_pos_inrange",
find_first_match_in_period=True,
date_format="YYYY-MM-DD",
return_expectations={
"date": {
"earliest": "2020-11-16"
},
"incidence": 0.3
},
),
covid_discharge_date=patients.admitted_to_hospital(
returning="date_discharged",
with_these_diagnoses=covid_codelist,
on_or_after="sgss_pos_inrange",
find_first_match_in_period=True,
date_format="YYYY-MM-DD",
return_expectations={
"date": {
"earliest": "2020-11-16"
},
"incidence": 0.2
},
),
# DAYS SPENT IN ICU
covid_icu_days=patients.admitted_to_hospital(
returning="days_in_critical_care",
with_these_diagnoses=covid_codelist,
on_or_after="sgss_pos_inrange",
find_first_match_in_period=True,
return_expectations={
"category": {
"ratios": {
"10": 0.5,
"20": 0.5
}
},
"incidence": 0.4,
},
),
# ICU ADMISSION
icu_admission_date=patients.admitted_to_icu(
on_or_after="sgss_pos_inrange",
find_first_match_in_period=True,
returning="date_admitted",
date_format="YYYY-MM-DD",
return_expectations={
"date": {
"earliest": "2020-11-16"
},
"incidence": 0.2
},
),
### DEMOGRAPHIC COVARIATES
# AGE
age=patients.age_as_of(
"sgss_pos_inrange",
return_expectations={
"rate": "universal",
"int": {
"distribution": "population_ages"
},
},
),
# SEX
sex=patients.sex(return_expectations={
"rate": "universal",
"category": {
"ratios": {
"M": 0.49,
"F": 0.51
}
},
}),
# DEPRIVIATION
imd=patients.address_as_of(
"sgss_pos_inrange",
returning="index_of_multiple_deprivation",
round_to_nearest=100,
return_expectations={
"rate": "universal",
"category": {
"ratios": {
"100": 0.1,
"200": 0.2,
"300": 0.2,
"400": 0.2,
"500": 0.2,
"600": 0.1
}
},
},
),
# GEOGRAPHIC REGION CALLED STP
stp=patients.registered_practice_as_of(
"sgss_pos_inrange",
returning="stp_code",
return_expectations={
"rate": "universal",
"category": {
"ratios": {
"STP1": 0.1,
"STP2": 0.1,
"STP3": 0.1,
"STP4": 0.1,
"STP5": 0.1,
"STP6": 0.1,
"STP7": 0.1,
"STP8": 0.1,
"STP9": 0.1,
"STP10": 0.1,
}
},
},
),
# GEOGRAPHIC REGION MSOA
msoa=patients.registered_practice_as_of(
"sgss_pos_inrange",
returning="msoa_code",
return_expectations={
"rate": "universal",
"category": {
"ratios": dict_msoa
},
},
),
# REGION - one of NHS England 9 regions
region=patients.registered_practice_as_of(
"sgss_pos_inrange",
returning="nuts1_region_name",
return_expectations={
"rate": "universal",
"category": {
"ratios": {
"North East": 0.1,
"North West": 0.1,
"Yorkshire and The Humber": 0.1,
"East Midlands": 0.1,
"West Midlands": 0.1,
"East of England": 0.1,
"London": 0.2,
"South East": 0.1,
"South West": 0.1,
},
},
},
),
# RURAL OR URBAN LOCATION
rural_urban=patients.address_as_of(
"sgss_pos_inrange",
returning="rural_urban_classification",
return_expectations={
"rate": "universal",
"category": {
"ratios": {
"1": 0.1,
"2": 0.1,
"3": 0.1,
"4": 0.1,
"5": 0.1,
"6": 0.1,
"7": 0.2,
"8": 0.2,
}
},
},
),
# HOUSEHOLD INFORMATION
household_id=patients.household_as_of(
"2020-02-01",
returning="pseudo_id",
return_expectations={
"int": {
"distribution": "normal",
"mean": 1000,
"stddev": 200
},
"incidence": 1,
},
),
household_size=patients.household_as_of(
"2020-02-01",
returning="household_size",
return_expectations={
"int": {
"distribution": "normal",
"mean": 3,
"stddev": 1
},
"incidence": 1,
},
),
care_home_type=patients.care_home_status_as_of(
"sgss_pos_inrange",
categorised_as={
"PC": """
IsPotentialCareHome
AND LocationDoesNotRequireNursing='Y'
AND LocationRequiresNursing='N'
""",
"PN": """
IsPotentialCareHome
AND LocationDoesNotRequireNursing='N'
AND LocationRequiresNursing='Y'
""",
"PS": "IsPotentialCareHome",
"U": "DEFAULT",
},
return_expectations={
"rate": "universal",
"category": {
"ratios": {
"PC": 0.05,
"PN": 0.05,
"PS": 0.05,
"U": 0.85,
},
},
},
),
# https://github.com/ebmdatalab/tpp-sql-notebook/issues/10
bmi=patients.most_recent_bmi(
between=["2010-02-01", "sgss_pos_inrange"],
minimum_age_at_measurement=16,
include_measurement_date=True,
include_month=True,
return_expectations={
"date": {},
"float": {
"distribution": "normal",
"mean": 35,
"stddev": 10
},
"incidence": 0.95,
},
),
# https://github.com/ebmdatalab/tpp-sql-notebook/issues/6
smoking_status=patients.categorised_as(
{
"S": "most_recent_smoking_code = 'S'",
"E": """
most_recent_smoking_code = 'E' OR (
most_recent_smoking_code = 'N' AND ever_smoked
)
""",
"N": "most_recent_smoking_code = 'N' AND NOT ever_smoked",
"M": "DEFAULT",
},
return_expectations={
"category": {
"ratios": {
"S": 0.6,
"E": 0.1,
"N": 0.2,
"M": 0.1
}
}
},
most_recent_smoking_code=patients.with_these_clinical_events(
clear_smoking_codes,
find_last_match_in_period=True,
on_or_before="sgss_pos_inrange",
returning="category",
),
ever_smoked=patients.with_these_clinical_events(
filter_codes_by_category(clear_smoking_codes, include=["S", "E"]),
on_or_before="sgss_pos_inrange",
),
),
# https://github.com/ebmdatalab/tpp-sql-notebook/issues/27
ethnicity=patients.with_these_clinical_events(
ethnicity_codes,
returning="category",
find_last_match_in_period=True,
include_date_of_match=True,
return_expectations={
"category": {
"ratios": {
"1": 0.75,
"2": 0.05,
"3": 0.05,
"4": 0.05,
"5": 0.1
}
},
"incidence": 0.75,
},
),
ethnicity_16=patients.with_these_clinical_events(
ethnicity_codes_16,
returning="category",
find_last_match_in_period=True,
include_date_of_match=True,
return_expectations={
"category": {
"ratios": {
"1": 0.8,
"5": 0.1,
"3": 0.1
}
},
"incidence": 0.75,
},
),
# https://github.com/ebmdatalab/tpp-sql-notebook/issues/21
chronic_respiratory_disease=patients.with_these_clinical_events(
chronic_respiratory_disease_codes,
return_first_date_in_period=True,
include_month=True,
),
# https://github.com/ebmdatalab/tpp-sql-notebook/issues/55
asthma=patients.categorised_as(
{
"0":
"DEFAULT",
"1":
"""
(
recent_asthma_code OR (
asthma_code_ever AND NOT
copd_code_ever
)
) AND (
prednisolone_last_year = 0 OR
prednisolone_last_year > 4
)
""",
"2":
"""
(
recent_asthma_code OR (
asthma_code_ever AND NOT
copd_code_ever
)
) AND
prednisolone_last_year > 0 AND
prednisolone_last_year < 5
""",
},
return_expectations={
"category": {
"ratios": {
"0": 0.8,
"1": 0.1,
"2": 0.1
}
},
},
recent_asthma_code=patients.with_these_clinical_events(
asthma_codes,
between=["2017-02-01", "2020-11-16"],
),
asthma_code_ever=patients.with_these_clinical_events(asthma_codes),
copd_code_ever=patients.with_these_clinical_events(
chronic_respiratory_disease_codes),
prednisolone_last_year=patients.with_these_medications(
pred_codes,
between=["2019-11-16", "2020-11-16"],
returning="number_of_matches_in_period",
),
),
# https://github.com/ebmdatalab/tpp-sql-notebook/issues/7
chronic_cardiac_disease=patients.with_these_clinical_events(
chronic_cardiac_disease_codes,
return_first_date_in_period=True,
include_month=True,
),
# https://github.com/ebmdatalab/tpp-sql-notebook/issues/30
diabetes=patients.with_these_clinical_events(
diabetes_codes,
return_first_date_in_period=True,
include_month=True,
),
# https://github.com/ebmdatalab/tpp-sql-notebook/issues/32
lung_cancer=patients.with_these_clinical_events(
lung_cancer_codes,
return_first_date_in_period=True,
include_month=True,
),
haem_cancer=patients.with_these_clinical_events(
haem_cancer_codes,
return_first_date_in_period=True,
include_month=True,
),
other_cancer=patients.with_these_clinical_events(
other_cancer_codes,
return_first_date_in_period=True,
include_month=True,
),
# https://github.com/ebmdatalab/tpp-sql-notebook/issues/12
chronic_liver_disease=patients.with_these_clinical_events(
chronic_liver_disease_codes,
return_first_date_in_period=True,
include_month=True,
),
# https://github.com/ebmdatalab/tpp-sql-notebook/issues/14
other_neuro=patients.with_these_clinical_events(
other_neuro,
return_first_date_in_period=True,
include_month=True,
),
stroke=patients.with_these_clinical_events(
stroke,
return_first_date_in_period=True,
include_month=True,
),
dementia=patients.with_these_clinical_events(
dementia,
return_first_date_in_period=True,
include_month=True,
),
# Chronic kidney disease
# https://github.com/ebmdatalab/tpp-sql-notebook/issues/17
creatinine=patients.with_these_clinical_events(
creatinine_codes,
find_last_match_in_period=True,
on_or_before="2020-11-16",
returning="numeric_value",
include_date_of_match=True,
include_month=True,
return_expectations={
"float": {
"distribution": "normal",
"mean": 60.0,
"stddev": 15
},
"date": {
"earliest": "2019-02-28",
"latest": "2020-11-16"
},
"incidence": 0.95,
},
),
dialysis=patients.with_these_clinical_events(
dialysis_codes,
return_first_date_in_period=True,
include_month=True,
),
# https://github.com/ebmdatalab/tpp-sql-notebook/issues/31
organ_transplant=patients.with_these_clinical_events(
organ_transplant_codes,
return_first_date_in_period=True,
include_month=True,
),
# https://github.com/ebmdatalab/tpp-sql-notebook/issues/13
dysplenia=patients.with_these_clinical_events(
spleen_codes,
return_first_date_in_period=True,
include_month=True,
),
sickle_cell=patients.with_these_clinical_events(
sickle_cell_codes,
return_first_date_in_period=True,
include_month=True,
),
# https://github.com/ebmdatalab/tpp-sql-notebook/issues/36
aplastic_anaemia=patients.with_these_clinical_events(
aplastic_codes,
return_last_date_in_period=True,
include_month=True,
),
hiv=patients.with_these_clinical_events(
hiv_codes,
returning="category",
find_first_match_in_period=True,
include_date_of_match=True,
include_month=True,
return_expectations={
"category": {
"ratios": {
"43C3.": 0.8,
"XaFuL": 0.2
}
},
},
),
permanent_immunodeficiency=patients.with_these_clinical_events(
permanent_immune_codes,
return_first_date_in_period=True,
include_month=True,
),
temporary_immunodeficiency=patients.with_these_clinical_events(
temp_immune_codes,
return_last_date_in_period=True,
include_month=True,
),
# https://github.com/ebmdatalab/tpp-sql-notebook/issues/23
# immunosuppressant_med=
# hypertension
hypertension=patients.with_these_clinical_events(
hypertension_codes,
return_first_date_in_period=True,
include_month=True,
),
# Blood pressure
# https://github.com/ebmdatalab/tpp-sql-notebook/issues/35
bp_sys=patients.mean_recorded_value(
systolic_blood_pressure_codes,
on_most_recent_day_of_measurement=True,
on_or_before="2020-11-16",
include_measurement_date=True,
include_month=True,
return_expectations={
"float": {
"distribution": "normal",
"mean": 80,
"stddev": 10
},
"date": {
"latest": "2020-11-16"
},
"incidence": 0.95,
},
),
bp_dias=patients.mean_recorded_value(
diastolic_blood_pressure_codes,
on_most_recent_day_of_measurement=True,
on_or_before="2020-11-16",
include_measurement_date=True,
include_month=True,
return_expectations={
"float": {
"distribution": "normal",
"mean": 120,
"stddev": 10
},
"date": {
"latest": "2020-11-16"
},
"incidence": 0.95,
},
),
hba1c_mmol_per_mol=patients.with_these_clinical_events(
hba1c_new_codes,
find_last_match_in_period=True,
on_or_before="2020-11-16",
returning="numeric_value",
include_date_of_match=True,
include_month=True,
return_expectations={
"date": {
"latest": "2020-11-16"
},
"float": {
"distribution": "normal",
"mean": 40.0,
"stddev": 20
},
"incidence": 0.95,
},
),
hba1c_percentage=patients.with_these_clinical_events(
hba1c_old_codes,
find_last_match_in_period=True,
on_or_before="2020-11-16",
returning="numeric_value",
include_date_of_match=True,
include_month=True,
return_expectations={
"date": {
"latest": "2020-11-16"
},
"float": {
"distribution": "normal",
"mean": 5,
"stddev": 2
},
"incidence": 0.95,
},
),
# # https://github.com/ebmdatalab/tpp-sql-notebook/issues/49
ra_sle_psoriasis=patients.with_these_clinical_events(
ra_sle_psoriasis_codes,
return_first_date_in_period=True,
include_month=True,
),
)
def test_make_df_from_expectations_with_aggregate_of():
# aggregate of variables defined in their own right
study = StudyDefinition(
default_expectations={
"date": {
"earliest": "1900-01-01",
"latest": "today"
},
"rate": "exponential_increase",
"incidence": 0.2,
},
population=patients.all(),
date_1=patients.with_these_clinical_events(
codelist(["X"], system="ctv3"),
returning="date",
date_format="YYYY-MM-DD",
),
date_2=patients.with_these_clinical_events(
codelist(["X"], system="ctv3"),
returning="date",
date_format="YYYY-MM-DD",
),
date_min=patients.minimum_of(
"date_1",
"date_2",
),
date_max=patients.maximum_of(
"date_1",
"date_2",
),
date_min_fixed=patients.minimum_of(
"date_1",
"1980-10-20",
),
int_1=patients.with_these_clinical_events(
codelist(["X"], system="ctv3"),
returning="number_of_matches_in_period",
return_expectations={
"int": {
"distribution": "normal",
"mean": 25,
"stddev": 5
},
"incidence": 0.5,
},
),
int_2=patients.with_these_clinical_events(
codelist(["X"], system="ctv3"),
returning="number_of_matches_in_period",
return_expectations={
"int": {
"distribution": "normal",
"mean": 25,
"stddev": 5
},
"incidence": 0.5,
},
),
int_min=patients.minimum_of("int_1", "int_2"),
int_max=patients.maximum_of("int_1", "int_2"),
)
population_size = 10000
result = study.make_df_from_expectations(population_size)
for _, row in result.iterrows():
print(row)
dates = [
d for d in [row["date_1"], row["date_2"]] if isinstance(d, str)
]
if dates:
date_min = min(dates)
date_max = max(dates)
else:
date_min = float("nan")
date_max = float("nan")
assert_nan_equal(row["date_min"], date_min)
assert_nan_equal(row["date_max"], date_max)
ints = [i for i in [row["int_1"], row["int_2"]] if isinstance(i, int)]
if ints:
int_min = min(ints)
int_max = max(ints)
else:
int_min = float("nan")
int_max = float("nan")
assert_nan_equal(row["int_min"], int_min)
assert_nan_equal(row["int_max"], int_max)
# aggregate of variables defined only within aggregate function
study = StudyDefinition(
default_expectations={
"date": {
"earliest": "1900-01-01",
"latest": "today"
},
"rate": "exponential_increase",
"incidence": 1,
},
# We use an expression here (never mind that it's a trivial and
# pointless one) as that triggers a bug which we want to ensure we've
# fixed
population=patients.satisfying("foo OR bar",
foo=patients.all(),
bar=patients.all()),
date_min=patients.maximum_of(
date_1=patients.with_these_clinical_events(
codelist(["X"], system="ctv3"),
returning="date",
date_format="YYYY-MM-DD",
),
date_2=patients.with_these_clinical_events(
codelist(["X"], system="ctv3"),
returning="date",
date_format="YYYY-MM-DD",
),
),
date_max=patients.maximum_of(
date_3=patients.with_these_clinical_events(
codelist(["X"], system="ctv3"),
returning="date",
date_format="YYYY-MM-DD",
),
date_4=patients.with_these_clinical_events(
codelist(["X"], system="ctv3"),
returning="date",
date_format="YYYY-MM-DD",
),
),
int_min=patients.minimum_of(
int_1=patients.with_these_clinical_events(
codelist(["X"], system="ctv3"),
returning="number_of_matches_in_period",
return_expectations={
"int": {
"distribution": "normal",
"mean": 25,
"stddev": 5
},
"incidence": 0.5,
},
),
int_2=patients.with_these_clinical_events(
codelist(["X"], system="ctv3"),
returning="number_of_matches_in_period",
return_expectations={
"int": {
"distribution": "normal",
"mean": 25,
"stddev": 5
},
"incidence": 0.5,
},
),
),
int_max=patients.maximum_of(
int_3=patients.with_these_clinical_events(
codelist(["X"], system="ctv3"),
returning="number_of_matches_in_period",
return_expectations={
"int": {
"distribution": "normal",
"mean": 25,
"stddev": 5
},
"incidence": 0.5,
},
),
int_4=patients.with_these_clinical_events(
codelist(["X"], system="ctv3"),
returning="number_of_matches_in_period",
return_expectations={
"int": {
"distribution": "normal",
"mean": 25,
"stddev": 5
},
"incidence": 0.5,
},
),
),
)
population_size = 10000
result = study.make_df_from_expectations(population_size)
for _, row in result.iterrows():
print(row)
assert pd.notna(row["date_min"])
assert pd.notna(row["date_max"])
assert pd.notna(row["int_min"])
assert pd.notna(row["int_max"])
# aggregate of variables defined both inside and outside aggregation
study = StudyDefinition(
default_expectations={
"date": {
"earliest": "1900-01-01",
"latest": "today"
},
"rate": "exponential_increase",
"incidence": 0.2,
},
population=patients.all(),
date_1=patients.with_these_clinical_events(
codelist(["X"], system="ctv3"),
returning="date",
date_format="YYYY-MM-DD",
),
date_2=patients.with_these_clinical_events(
codelist(["X"], system="ctv3"),
returning="date",
date_format="YYYY-MM-DD",
),
date_min=patients.minimum_of(
"date_1",
"date_2",
date_3=patients.with_these_clinical_events(
codelist(["X"], system="ctv3"),
returning="date",
date_format="YYYY-MM-DD",
),
),
date_max=patients.maximum_of(
"date_1",
"date_2",
date_4=patients.with_these_clinical_events(
codelist(["X"], system="ctv3"),
returning="date",
date_format="YYYY-MM-DD",
),
),
int_1=patients.with_these_clinical_events(
codelist(["X"], system="ctv3"),
returning="number_of_matches_in_period",
return_expectations={
"int": {
"distribution": "normal",
"mean": 25,
"stddev": 5
},
"incidence": 0.5,
},
),
int_2=patients.with_these_clinical_events(
codelist(["X"], system="ctv3"),
returning="number_of_matches_in_period",
return_expectations={
"int": {
"distribution": "normal",
"mean": 25,
"stddev": 5
},
"incidence": 0.5,
},
),
int_min=patients.minimum_of(
"int_1",
"int_2",
int_3=patients.with_these_clinical_events(
codelist(["X"], system="ctv3"),
returning="number_of_matches_in_period",
return_expectations={
"int": {
"distribution": "normal",
"mean": 25,
"stddev": 5
},
"incidence": 0.5,
},
),
),
int_max=patients.maximum_of(
"int_1",
"int_2",
int_4=patients.with_these_clinical_events(
codelist(["X"], system="ctv3"),
returning="number_of_matches_in_period",
return_expectations={
"int": {
"distribution": "normal",
"mean": 25,
"stddev": 5
},
"incidence": 0.5,
},
),
),
)
population_size = 10000
result = study.make_df_from_expectations(population_size)
for _, row in result.iterrows():
print(row)
dates = [
d for d in [row["date_1"], row["date_2"]] if isinstance(d, str)
]
if dates:
date_min = min(dates)
date_max = max(dates)
else:
date_min = float("nan")
date_max = float("nan")
assert_nan_equal(row["date_min"], date_min)
assert_nan_equal(row["date_max"], date_max)
ints = [i for i in [row["int_1"], row["int_2"]] if isinstance(i, int)]
if ints:
int_min = min(ints)
int_max = max(ints)
else:
int_min = float("nan")
int_max = float("nan")
assert_nan_equal(row["int_min"], int_min)
assert_nan_equal(row["int_max"], int_max)
study = StudyDefinition(
default_expectations={
"date": {
"earliest": "1970-01-01",
"latest": "today"
},
"rate": "uniform",
"incidence": 0.2,
},
population=patients.registered_with_one_practice_between(
"2019-02-01", "2020-02-01"),
dereg_date=patients.date_deregistered_from_all_supported_practices(
on_or_before="2020-12-01",
date_format="YYYY-MM",
return_expectations={"date": {
"earliest": "2020-02-01"
}},
),
a_e_consult_date=patients.attended_emergency_care(
on_or_after="2020-02-01",
returning="date_arrived",
date_format="YYYY-MM-DD",
find_first_match_in_period=True,
return_expectations={
"date": {
"earliest": "2020-02-01"
},
"rate": "exponential_increase",
},
),
icu_date_admitted=patients.admitted_to_icu(
on_or_after="2020-02-01",
include_day=True,
returning="date_admitted",
find_first_match_in_period=True,
return_expectations={
"date": {
"earliest": "2020-02-01"
},
"rate": "exponential_increase",
},
),
died_date_cpns=patients.with_death_recorded_in_cpns(
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",
},
),
age=patients.age_as_of(
"2020-02-01",
return_expectations={
"rate": "universal",
"int": {
"distribution": "population_ages"
},
},
),
sex=patients.sex(return_expectations={
"rate": "universal",
"category": {
"ratios": {
"M": 0.49,
"F": 0.51
}
},
}),
imd=patients.address_as_of(
"2020-02-01",
returning="index_of_multiple_deprivation",
round_to_nearest=100,
return_expectations={
"rate": "universal",
"category": {
"ratios": {
"100": 0.1,
"200": 0.2,
"300": 0.7
}
},
},
),
)
study = StudyDefinition(
# Configure the expectations framework
default_expectations={
"date": {
"earliest": "1900-01-01",
"latest": "today"
},
"rate": "uniform",
"incidence": 0.1,
},
# STUDY POPULATION
# This line defines the study population
population=patients.all(),
#population=patients.satisfying(
# """
# 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": {
"distribution": "population_ages"
},
},
),
# https://github.com/ebmdatalab/tpp-sql-notebook/issues/46
sex=patients.sex(return_expectations={
"rate": "universal",
"category": {
"ratios": {
"M": 0.49,
"F": 0.51
}
},
}),
imd=patients.address_as_of(
"2020-02-29",
returning="index_of_multiple_deprivation",
round_to_nearest=100,
return_expectations={
"rate": "universal",
"category": {
"ratios": {
"100": 0.1,
"200": 0.2,
"300": 0.7
}
},
},
),
)
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",
},
return_expectations={
"incidence": 1,
"category": {
"ratios": {
"COVID-19 positive": 0.1,
"COVID-19 hospitalised": 0.1,
"General population": 0.8,
}
},
},
covid_positive=patients.with_test_result_in_sgss(
pathogen="SARS-CoV-2",
test_result="positive",
between=["2020-01-01", "last_day_of_month(index_date)"],
date_format="YYYY-MM-DD",
return_expectations={"date": {
"earliest": "index_date"
}},
),
covid_hospitalised=patients.admitted_to_hospital(
with_these_diagnoses=covid_codelist,
between=["2020-01-01", "last_day_of_month(index_date)"],
return_expectations={"incidence": 0.20},
),
),
stroke=patients.satisfying(
"stroke_gp OR stroke_hospital OR stroke_ons",
stroke_gp=patients.with_these_clinical_events(
stroke,
between=["index_date", "last_day_of_month(index_date)"],
return_expectations={"incidence": 0.05},
),
stroke_hospital=patients.admitted_to_hospital(
with_these_diagnoses=stroke_hospital,
between=["index_date", "last_day_of_month(index_date)"],
return_expectations={"incidence": 0.05},
),
stroke_ons=patients.with_these_codes_on_death_certificate(
stroke_hospital,
between=["index_date", "last_day_of_month(index_date)"],
return_expectations={"incidence": 0.05},
),
),
DVT=patients.satisfying(
"dvt_gp OR dvt_hospital OR dvt_ons",
dvt_gp=patients.with_these_clinical_events(
filter_codes_by_category(vte_codes_gp, include=["dvt"]),
between=["index_date", "last_day_of_month(index_date)"],
return_expectations={"incidence": 0.05},
),
dvt_hospital=patients.admitted_to_hospital(
with_these_diagnoses=filter_codes_by_category(vte_codes_hospital,
include=["dvt"]),
between=["index_date", "last_day_of_month(index_date)"],
return_expectations={"incidence": 0.05},
),
dvt_ons=patients.with_these_codes_on_death_certificate(
filter_codes_by_category(vte_codes_hospital, include=["dvt"]),
between=["index_date", "last_day_of_month(index_date)"],
return_expectations={"incidence": 0.05},
),
),
PE=patients.satisfying(
"pe_gp OR pe_hospital OR pe_ons",
pe_gp=patients.with_these_clinical_events(
filter_codes_by_category(vte_codes_gp, include=["pe"]),
between=["index_date", "last_day_of_month(index_date)"],
return_expectations={"incidence": 0.05},
),
pe_hospital=patients.admitted_to_hospital(
with_these_diagnoses=filter_codes_by_category(vte_codes_hospital,
include=["pe"]),
between=["index_date", "last_day_of_month(index_date)"],
return_expectations={"incidence": 0.05},
),
pe_ons=patients.with_these_codes_on_death_certificate(
filter_codes_by_category(vte_codes_hospital, include=["pe"]),
between=["index_date", "last_day_of_month(index_date)"],
return_expectations={"incidence": 0.05},
),
),
AKI=patients.satisfying(
"aki_hospital OR aki_ons",
aki_hospital=patients.admitted_to_hospital(
with_these_diagnoses=aki_codes,
between=["index_date", "last_day_of_month(index_date)"],
return_expectations={"incidence": 0.05},
),
aki_ons=patients.with_these_codes_on_death_certificate(
aki_codes,
between=["index_date", "last_day_of_month(index_date)"],
return_expectations={"incidence": 0.05},
),
),
MI=patients.satisfying(
"mi_gp OR mi_hospital OR mi_ons",
mi_gp=patients.with_these_clinical_events(
mi_codes,
between=["index_date", "last_day_of_month(index_date)"],
return_expectations={"incidence": 0.05},
),
mi_hospital=patients.admitted_to_hospital(
with_these_diagnoses=filter_codes_by_category(mi_codes_hospital,
include=["1"]),
between=["index_date", "last_day_of_month(index_date)"],
return_expectations={"incidence": 0.05},
),
mi_ons=patients.with_these_codes_on_death_certificate(
filter_codes_by_category(mi_codes_hospital, include=["1"]),
between=["index_date", "last_day_of_month(index_date)"],
return_expectations={"incidence": 0.05},
),
),
heart_failure=patients.satisfying(
"heart_failure_gp OR heart_failure_hospital OR heart_failure_ons",
heart_failure_gp=patients.with_these_clinical_events(
heart_failure_codes,
between=["index_date", "last_day_of_month(index_date)"],
return_expectations={"incidence": 0.05},
),
heart_failure_hospital=patients.admitted_to_hospital(
with_these_diagnoses=filter_codes_by_category(
heart_failure_codes_hospital, include=["1"]),
between=["index_date", "last_day_of_month(index_date)"],
return_expectations={"incidence": 0.05},
),
heart_failure_ons=patients.with_these_codes_on_death_certificate(
filter_codes_by_category(heart_failure_codes_hospital,
include=["1"]),
between=["index_date", "last_day_of_month(index_date)"],
return_expectations={"incidence": 0.05},
),
),
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},
),
)
),
event_date_month=patients.with_these_clinical_events(
cl,
returning="date",
date_format="YYYY-MM",
return_expectations={"rate": "uniform", "incidence": 0.5},
),
event_date_year=patients.with_these_clinical_events(
cl,
returning="date",
date_format="YYYY",
return_expectations={"rate": "uniform", "incidence": 0.5},
),
)
study = StudyDefinition(**column_definitions)
covariate_definitions = study.covariate_definitions
fixtures_path = Path(__file__).parent / "fixtures" / "dummy-data"
# Create a second test study to which we can add columns without needing to rebuild all
# the test fixtures
study_2 = StudyDefinition(
**column_definitions,
category_date=patients.categorised_as(
{
"2020-10-15": "age > 50",
"2021-11-16": "DEFAULT",
},
return_expectations={
## STUDY POPULATION
study = StudyDefinition(
default_expectations={
"date": {
"earliest": index_date,
"latest": "today"
}, # date range for simulated dates
"rate": "uniform",
"incidence": 1
},
# This line defines the study population
population=patients.registered_as_of(index_date),
# this line defines the stp variable we want to extract
stp=patients.registered_practice_as_of(
index_date,
returning="stp_code",
return_expectations={
"category": {
"ratios": {
"STP1": 0.3,
"STP2": 0.2,
"STP3": 0.5
}
},
},
),
)
# Import codelists
from codelists import *
from datetime import date
start_date = "2020-12-07"
end_date = "2021-02-01"
# Specifiy study definition
study = StudyDefinition(
default_expectations={
"date": {"earliest": start_date, "latest": end_date},
"rate": "exponential_increase",
"incidence": 0.1,
},
population=patients.registered_as_of(start_date),
practice=patients.registered_practice_as_of(
start_date,
returning="pseudo_id",
return_expectations={
"int": {"distribution": "normal", "mean": 25, "stddev": 5}, "incidence": 0.5}
),
)
study = StudyDefinition(
index_date="2020-02-01",
default_expectations={
"date": {
"earliest": "1900-01-01",
"latest": "index_date"
},
"rate": "exponential_increase",
},
population=patients.registered_with_one_practice_between(
"index_date - 1 year", "index_date"),
has_chronic_liver_disease=patients.with_these_clinical_events(
chronic_liver_disease_codes,
returning="binary_flag",
return_expectations={
"incidence": 1.0,
"date": {
"earliest": "1950-01-01",
"latest": "index_date"
},
},
),
stp=patients.registered_practice_as_of(
"index_date",
returning="stp_code",
return_expectations={
"rate": "universal",
"category": {
"ratios": {
"STP1": 1.0
}
},
},
),
)
study = StudyDefinition(
# Configure the expectations framework
default_expectations={
"date": {
"earliest": "1900-01-01",
"latest": "today"
},
"rate": "uniform",
"incidence": 0.1,
},
# STUDY POPULATION
# This line defines the study population
population=patients.all(),
has_follow_up=patients.registered_with_one_practice_between(
"2019-02-28",
"2020-02-01",
return_expectations={"incidence": 0.9},
),
# ETHNICITY
#ETHNICITY IN 16 CATEGORIES
ethnicity_16=patients.with_these_clinical_events(
ethnicity_codes_16,
returning="category",
find_last_match_in_period=True,
include_date_of_match=True,
return_expectations={
"category": {
"ratios": {
"1": 0.0625,
"2": 0.0625,
"3": 0.0625,
"4": 0.0625,
"5": 0.0625,
"6": 0.0625,
"7": 0.0625,
"8": 0.0625,
"9": 0.0625,
"10": 0.0625,
"11": 0.0625,
"12": 0.0625,
"13": 0.0625,
"14": 0.0625,
"15": 0.0625,
"16": 0.0625,
}
},
"incidence": 0.75,
},
),
# ETHNICITY IN 6 CATEGORIES
ethnicity=patients.with_these_clinical_events(
ethnicity_codes,
returning="category",
find_last_match_in_period=True,
include_date_of_match=True,
return_expectations={
"category": {
"ratios": {
"1": 0.2,
"2": 0.2,
"3": 0.2,
"4": 0.2,
"5": 0.2
}
},
"incidence": 0.75,
},
),
# 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(
"2020-03-01",
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": {
"ratios": {
"M": 0.49,
"F": 0.51
}
},
}),
)
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": {"ratios": {"M": 0.49, "F": 0.51}},
}
),
# https://github.com/ebmdatalab/tpp-sql-notebook/issues/7
chronic_cardiac_disease=patients.with_these_clinical_events(
chronic_cardiac_disease_codes,
returning="date",
find_first_match_in_period=True,
include_month=True,
return_expectations={"incidence": 0.2},
),
# https://github.com/ebmdatalab/tpp-sql-notebook/issues/12
chronic_liver_disease=patients.with_these_clinical_events(
chronic_liver_disease_codes,
returning="date",
find_first_match_in_period=True,
include_month=True,
return_expectations={
"incidence": 0.2,
"date": {"earliest": "1950-01-01", "latest": "index_date"},
},
),
has_chronic_liver_disease=patients.with_these_clinical_events(
chronic_liver_disease_codes,
returning="binary_flag",
return_expectations={
"incidence": 0.2,
"date": {"earliest": "1950-01-01", "latest": "index_date"},
},
),
# https://github.com/ebmdatalab/tpp-sql-notebook/issues/10
bmi=patients.most_recent_bmi(
on_or_after="index_date",
minimum_age_at_measurement=16,
include_measurement_date=True,
include_month=True,
return_expectations={
"incidence": 0.6,
"float": {"distribution": "normal", "mean": 35, "stddev": 10},
},
),
# https://github.com/ebmdatalab/tpp-sql-notebook/issues/35
bp_sys=patients.mean_recorded_value(
systolic_blood_pressure_codes,
on_most_recent_day_of_measurement=True,
on_or_before="index_date",
include_measurement_date=True,
include_month=True,
return_expectations={
"incidence": 0.6,
"float": {"distribution": "normal", "mean": 80, "stddev": 10},
},
),
bp_dias=patients.mean_recorded_value(
diastolic_blood_pressure_codes,
on_most_recent_day_of_measurement=True,
on_or_before="index_date",
include_measurement_date=True,
include_month=True,
return_expectations={
"incidence": 0.6,
"float": {"distribution": "normal", "mean": 120, "stddev": 10},
},
),
# https://github.com/ebmdatalab/tpp-sql-notebook/issues/54
stp=patients.registered_practice_as_of(
"index_date",
returning="stp_code",
return_expectations={
"rate": "universal",
"category": {"ratios": {"STP1": 0.5, "STP2": 0.5}},
},
),
msoa=patients.registered_practice_as_of(
"index_date",
returning="msoa_code",
return_expectations={
"rate": "universal",
"category": {"ratios": {"MSOA1": 0.5, "MSOA2": 0.5}},
},
),
# https://github.com/ebmdatalab/tpp-sql-notebook/issues/52
imd=patients.address_as_of(
"index_date",
returning="index_of_multiple_deprivation",
round_to_nearest=100,
return_expectations={
"rate": "universal",
"category": {"ratios": {"100": 0.1, "200": 0.2, "300": 0.7}},
},
),
rural_urban=patients.address_as_of(
"index_date",
returning="rural_urban_classification",
return_expectations={
"rate": "universal",
"category": {"ratios": {"rural": 0.1, "urban": 0.9}},
},
),
recent_salbutamol_count=patients.with_these_medications(
salbutamol_codes,
between=["index_date - 2 years", "index_date"],
returning="number_of_matches_in_period",
return_expectations={
"incidence": 0.6,
"int": {"distribution": "normal", "mean": 8, "stddev": 2},
},
),
)
study = StudyDefinition(
# 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)",
died=patients.died_from_any_cause(on_or_before=index_date,
returning="binary_flag"),
registered=patients.registered_as_of(index_date),
),
age=patients.age_as_of(index_date,
return_expectations={
"rate": "universal",
"int": {
"distribution": "population_ages"
}
}),
age_group=patients.categorised_as(
{
"0": "DEFAULT",
"0 - under 16": """ age < 16""",
"16 - under 30": """ age >= 16 AND age < 30""",
"30 - under 40": """ age >= 30 AND age < 40""",
"40 - under 50": """ age >= 40 AND age < 50""",
"50 - under 55": """ age >= 50 AND age < 55""",
"55 - under 60": """ age >= 55 AND age < 60""",
"60 - under 65": """ age >= 60 AND age < 65""",
"65 - under 70": """ age >= 65 AND age < 70""",
"70 - under 75": """ age >= 70 AND age < 75""",
"75 - under 80": """ age >= 75 AND age < 80""",
"80 - under 85": """ age >= 80 AND age < 85""",
"85 plus": """ age >= 85""",
},
return_expectations={
"rate": "universal",
"category": {
"ratios": {
"0 - under 16": 0.05,
"16 - under 30": 0.1,
"30 - under 40": 0.1,
"40 - under 50": 0.1,
"50 - under 55": 0.1,
"55 - under 60": 0.05,
"60 - under 65": 0.1,
"65 - under 70": 0.1,
"70 - under 75": 0.05,
"75 - under 80": 0.1,
"80 - under 85": 0.1,
"85 plus": 0.05,
}
},
},
),
stp=patients.registered_practice_as_of(
"index_date",
returning="stp_code",
return_expectations={
"category": {
"ratios": {
"STP1": 0.5,
"STP2": 0.5
}
},
},
),
first_dose=patients.with_these_clinical_events(
first_dose_code,
returning="binary_flag",
between=["index_date", "index_date + 1 month"],
return_expectations={"incidence": 0.4}),
second_dose=patients.with_these_clinical_events(
second_dose_code,
returning="binary_flag",
between=["index_date", "index_date + 1 month"],
return_expectations={"incidence": 0.4}),
az_first_dose=patients.with_these_clinical_events(
az_first_dose_code,
returning="binary_flag",
between=["index_date", "index_date + 1 month"],
return_expectations={"incidence": 0.4}),
az_second_dose=patients.with_these_clinical_events(
az_second_dose_code,
returning="binary_flag",
between=["index_date", "index_date + 1 month"],
return_expectations={"incidence": 0.4}),
pf_first_dose=patients.with_these_clinical_events(
pf_first_dose_code,
returning="binary_flag",
between=["index_date", "index_date + 1 month"],
return_expectations={"incidence": 0.4}),
pf_second_dose=patients.with_these_clinical_events(
pf_second_dose_code,
returning="binary_flag",
between=["index_date", "index_date + 1 month"],
return_expectations={"incidence": 0.4}),
mo_first_dose=patients.with_these_clinical_events(
mo_first_dose_code,
returning="binary_flag",
between=["index_date", "index_date + 1 month"],
return_expectations={"incidence": 0.4}),
mo_second_dose=patients.with_these_clinical_events(
mo_second_dose_code,
returning="binary_flag",
between=["index_date", "index_date + 1 month"],
return_expectations={"incidence": 0.4}),
nx_first_dose=patients.with_these_clinical_events(
nx_first_dose_code,
returning="binary_flag",
between=["index_date", "index_date + 1 month"],
return_expectations={"incidence": 0.4}),
nx_second_dose=patients.with_these_clinical_events(
nx_second_dose_code,
returning="binary_flag",
between=["index_date", "index_date + 1 month"],
return_expectations={"incidence": 0.4}),
jn_first_dose=patients.with_these_clinical_events(
jn_first_dose_code,
returning="binary_flag",
between=["index_date", "index_date + 1 month"],
return_expectations={"incidence": 0.4}),
jn_second_dose=patients.with_these_clinical_events(
jn_second_dose_code,
returning="binary_flag",
between=["index_date", "index_date + 1 month"],
return_expectations={"incidence": 0.4}),
gs_first_dose=patients.with_these_clinical_events(
gs_first_dose_code,
returning="binary_flag",
between=["index_date", "index_date + 1 month"],
return_expectations={"incidence": 0.4}),
gs_second_dose=patients.with_these_clinical_events(
gs_second_dose_code,
returning="binary_flag",
between=["index_date", "index_date + 1 month"],
return_expectations={"incidence": 0.4}),
vl_first_dose=patients.with_these_clinical_events(
vl_first_dose_code,
returning="binary_flag",
between=["index_date", "index_date + 1 month"],
return_expectations={"incidence": 0.4}),
vl_second_dose=patients.with_these_clinical_events(
vl_second_dose_code,
returning="binary_flag",
between=["index_date", "index_date + 1 month"],
return_expectations={"incidence": 0.4}),
)
study = StudyDefinition(
# Configure the expectations framework
default_expectations={
"date": {"earliest": index_date, "latest": end_date},
"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, "F": 0.51}},
"incidence": 1
}
),
date_death = patients.died_from_any_cause(
between = [index_date, end_date],
returning = "date_of_death",
date_format = "YYYY-MM-DD",
return_expectations = {
"incidence": 0.2,
},
),
death_category = patients.categorised_as(
{
"covid-death": "died_covid",
"non-covid-death": "(NOT died_covid) AND died_any",
"alive" : "DEFAULT"
},
died_covid = patients.with_these_codes_on_death_certificate(
codes_ICD10_covid,
returning = "binary_flag",
match_only_underlying_cause = False,
between = [index_date, end_date],
),
died_any = patients.died_from_any_cause(
between = [index_date, end_date],
returning = "binary_flag",
),
return_expectations = {
"category": {"ratios": {"alive": 0.8, "covid-death": 0.1, "non-covid-death": 0.1}},
"incidence": 1
},
),
)
study = StudyDefinition(
# Configure the expectations framework
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, on_or_after="2020-03-01", match_only_underlying_cause=False,
return_expectations={"date": {"earliest": "2020-03-01"}, "incidence": 0.1},
),
died_ons_covid_flag_underlying=patients.with_these_codes_on_death_certificate(
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"}},
),
# 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(
"2020-03-01",
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": {"ratios": {"M": 0.49, "F": 0.51}},
}
),
ethnicity=patients.with_these_clinical_events(
ethnicity_codes,
returning="category",
find_last_match_in_period=True,
include_date_of_match=True,
return_expectations={
"category": {"ratios": {"1": 0.8, "5": 0.1, "3": 0.1}},
"incidence": 0.75,
},
),
# IMID disease codes
atopic_dermatitis=first_diagnosis_in_period(atopic_dermatitis_codes),
crohns_disease=first_diagnosis_in_period(crohns_disease_codes),
ulcerative_colitis=first_diagnosis_in_period(ulcerative_colitis_codes),
inflammatory_bowel_disease_unclassified=first_diagnosis_in_period(inflammatory_bowel_disease_unclassified_codes),
psoriasis=first_diagnosis_in_period(psoriasis_codes),
hidradenitis_suppurativa=first_diagnosis_in_period(hidradenitis_suppurativa_codes),
psoriatic_arthritis=first_diagnosis_in_period(psoriatic_arthritis_codes),
rheumatoid_arthritis=first_diagnosis_in_period(rheumatoid_arthritis_codes),
ankylosing_spondylitis=first_diagnosis_in_period(ankylosing_spondylitis_codes),
# Comorbidities
chronic_cardiac_disease=first_diagnosis_in_period(chronic_cardiac_disease_codes),
diabetes=first_diagnosis_in_period(diabetes_codes),
hba1c_new=first_diagnosis_in_period(hba1c_new_codes),
hba1c_old=first_diagnosis_in_period(hba1c_old_codes),
hba1c_mmol_per_mol=patients.with_these_clinical_events(
hba1c_new_codes,
find_last_match_in_period=True,
on_or_before="2020-02-29",
returning="numeric_value",
include_date_of_match=True,
include_month=True,
return_expectations={
"date": {"latest": "2020-02-29"},
"float": {"distribution": "normal", "mean": 40.0, "stddev": 20},
"incidence": 0.95,
},
),
hba1c_percentage=patients.with_these_clinical_events(
hba1c_old_codes,
find_last_match_in_period=True,
on_or_before="2020-02-29",
returning="numeric_value",
include_date_of_match=True,
include_month=True,
return_expectations={
"date": {"latest": "2020-02-29"},
"float": {"distribution": "normal", "mean": 5, "stddev": 2},
"incidence": 0.95,
},
),
hypertension=first_diagnosis_in_period(hypertension_codes),
chronic_respiratory_disease=first_diagnosis_in_period(chronic_respiratory_disease_codes),
copd=first_diagnosis_in_period(copd_codes),
chronic_liver_disease=first_diagnosis_in_period(chronic_liver_disease_codes),
stroke=first_diagnosis_in_period(stroke_codes),
lung_cancer=first_diagnosis_in_period(lung_cancer_codes),
haem_cancer=first_diagnosis_in_period(haem_cancer_codes),
other_cancer=first_diagnosis_in_period(other_cancer_codes),
#CKD
creatinine=patients.with_these_clinical_events(
creatinine_codes,
find_last_match_in_period=True,
between=["2018-12-01", "2020-02-29"],
returning="numeric_value",
include_date_of_match=True,
include_month=True,
return_expectations={
"float": {"distribution": "normal", "mean": 150.0, "stddev": 200.0},
"date": {"earliest": "2018-12-01", "latest": "2020-02-29"},
"incidence": 0.95,
},
),
#### end stage renal disease codes incl. dialysis / transplant
esrf=patients.with_these_clinical_events(
ckd_codes,
on_or_before="2020-02-29",
return_last_date_in_period=True,
include_month=True,
return_expectations={"date": {"latest": "2020-02-29"}},
),
ckd=first_diagnosis_in_period(ckd_codes),
organ_transplant=first_diagnosis_in_period(organ_transplant_codes),
# https://github.com/ebmdatalab/tpp-sql-notebook/issues/10
bmi=patients.most_recent_bmi(
on_or_after="2010-02-01",
minimum_age_at_measurement=16,
include_measurement_date=True,
include_month=True,
return_expectations={
"incidence": 0.6,
"float": {"distribution": "normal", "mean": 35, "stddev": 10},
},
),
# https://github.com/ebmdatalab/tpp-sql-notebook/issues/54
stp=patients.registered_practice_as_of(
"2020-03-01",
returning="stp_code",
return_expectations={
"rate": "universal",
"category": {"ratios": {"STP1": 0.5, "STP2": 0.5}},
},
),
# https://github.com/ebmdatalab/tpp-sql-notebook/issues/52
imd=patients.address_as_of(
"2020-03-01",
returning="index_of_multiple_deprivation",
round_to_nearest=100,
return_expectations={
"rate": "universal",
"category": {"ratios": {"100": 0.1, "200": 0.2, "300": 0.7}},
},
),
#SMOKING
smoking_status=patients.categorised_as(
{
"S": "most_recent_smoking_code = 'S'",
"E": """
most_recent_smoking_code = 'E' OR (
most_recent_smoking_code = 'N' AND ever_smoked
)
""",
"N": "most_recent_smoking_code = 'N' AND NOT ever_smoked",
"M": "DEFAULT",
},
return_expectations={
"category": {"ratios": {"S": 0.6, "E": 0.1, "N": 0.2, "M": 0.1}}
},
most_recent_smoking_code=patients.with_these_clinical_events(
clear_smoking_codes,
find_last_match_in_period=True,
on_or_before="2020-02-29",
returning="category",
),
ever_smoked=patients.with_these_clinical_events(
filter_codes_by_category(clear_smoking_codes, include=["S", "E"]),
on_or_before="2020-02-29",
),
),
# smoking_status_date=patients.with_these_clinical_events(
# clear_smoking_codes,
# on_or_before="2020-02-29",
# return_last_date_in_period=True,
# include_month=True,
# return_expectations={"date": {"latest": "2020-02-29"}},
# ),
### GP CONSULTATION RATE
gp_consult_count=patients.with_gp_consultations(
between=["2019-03-01", "2020-02-29"],
returning="number_of_matches_in_period",
return_expectations={
"int": {"distribution": "normal", "mean": 4, "stddev": 2},
"date": {"earliest": "2019-03-01", "latest": "2020-02-29"},
"incidence": 0.7,
},
),
# has_consultation_history=patients.with_complete_gp_consultation_history_between(
# "2019-03-01", "2020-02-29", return_expectations={"incidence": 0.9},
# ),
# Medications
**medication_counts_and_dates("oral_prednisolone", "opensafely-asthma-oral-prednisolone-medication", False),
**medication_counts_and_dates("azathioprine", "crossimid-azathioprine-medication", False),
**medication_counts_and_dates("ciclosporin", "crossimid-ciclosporin-medication", False),
**medication_counts_and_dates("gold", "crossimid-gold-medication", False),
**medication_counts_and_dates("leflunomide", "crossimid-leflunomide-medication", False),
**medication_counts_and_dates("mercaptopurine", "crossimid-mercaptopurine-medication", False),
**medication_counts_and_dates("methotrexate", "crossimid-methotrexate-medication", False),
**medication_counts_and_dates("mycophenolate", "crossimid-mycophenolate-medication", False),
**medication_counts_and_dates("penicillamine", "crossimid-penicillamine-medication", False),
**medication_counts_and_dates("sulfasalazine", "crossimid-sulfasalazine-medication", False),
**medication_counts_and_dates("mesalazine", "crossimid-mesalazine-medication", False),
**medication_counts_and_dates("atopic_dermatitis_meds", "crossimid-atopic-dermatitis-medication", False),
**medication_counts_and_dates("abatacept", "opensafely-high-cost-drugs-abatacept", True),
**medication_counts_and_dates("adalimumab", "opensafely-high-cost-drugs-adalimumab", True),
**medication_counts_and_dates("baricitinib", "opensafely-high-cost-drugs-baricitinib", True),
**medication_counts_and_dates("brodalumab", "opensafely-high-cost-drugs-brodalumab", True),
**medication_counts_and_dates("certolizumab", "opensafely-high-cost-drugs-certolizumab", True),
#**medication_counts_and_dates("dupilumab", "opensafely-high-cost-drugs-dupilumab", True),
**medication_counts_and_dates("etanercept", "opensafely-high-cost-drugs-etanercept", True),
**medication_counts_and_dates("golimumab", "opensafely-high-cost-drugs-golimumab", True),
**medication_counts_and_dates("guselkumab", "opensafely-high-cost-drugs-guselkumab", True),
**medication_counts_and_dates("infliximab", "opensafely-high-cost-drugs-infliximab", True),
**medication_counts_and_dates("ixekizumab", "opensafely-high-cost-drugs-ixekizumab", True),
**medication_counts_and_dates("mepolizumab", "opensafely-high-cost-drugs-mepolizumab", True),
**medication_counts_and_dates("methotrexate_hcd", "opensafely-high-cost-drugs-methotrexate", True),
**medication_counts_and_dates("risankizumab", "opensafely-high-cost-drugs-risankizumab", True),
**medication_counts_and_dates("rituximab", "opensafely-high-cost-drugs-rituximab", True, True),
**medication_counts_and_dates("sarilumab", "opensafely-high-cost-drugs-sarilumab", True),
**medication_counts_and_dates("secukinumab", "opensafely-high-cost-drugs-secukinumab", True),
**medication_counts_and_dates("tildrakizumab", "opensafely-high-cost-drugs-tildrakizumab", True),
**medication_counts_and_dates("tocilizumab", "opensafely-high-cost-drugs-tocilizumab", True),
**medication_counts_and_dates("tofacitinib", "opensafely-high-cost-drugs-tofacitinib", True),
**medication_counts_and_dates("upadacitinib", "opensafely-high-cost-drugs-upadacitinib", True),
**medication_counts_and_dates("ustekinumab", "opensafely-high-cost-drugs-ustekinumab", True),
**medication_counts_and_dates("vedolizumab", "opensafely-high-cost-drugs-vedolizumab", True)
)
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(
covid_codelist,
on_or_after="2020-02-01",
match_only_underlying_cause=False,
return_expectations={
"date": {
"earliest": "2020-02-01"
},
"incidence": 0.6
},
),
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"
},
"incidence": 0.6
},
),
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"
},
"incidence": 0.8
},
),
covid_icu_date=patients.admitted_to_icu(
on_or_after="2020-02-01",
include_day=True,
returning="date_admitted",
find_first_match_in_period=True,
return_expectations={
"date": {
"earliest": "2020-02-01"
},
"incidence": 0.8
},
),
covid_tpp_probable=patients.with_these_clinical_events(
combine_codelists(
covid_identification_in_primary_care_case_codes_clinical,
covid_identification_in_primary_care_case_codes_test,
covid_identification_in_primary_care_case_codes_seq),
return_first_date_in_period=True,
include_day=True,
return_expectations={
"date": {
"earliest": "2020-02-01"
},
"incidence": 0.6
},
),
covid_admission_date=patients.admitted_to_hospital(
returning="date_admitted", # defaults to "binary_flag"
with_these_diagnoses=covid_codelist, # optional
on_or_after="2020-02-01",
find_first_match_in_period=True,
date_format="YYYY-MM-DD",
return_expectations={
"date": {
"earliest": "2020-03-01"
},
"incidence": 0.95
},
),
covid_admission_primary_diagnosis=patients.admitted_to_hospital(
returning="primary_diagnosis",
with_these_diagnoses=covid_codelist, # optional
on_or_after="2020-02-01",
find_first_match_in_period=True,
date_format="YYYY-MM-DD",
return_expectations={
"date": {
"earliest": "2020-03-01"
},
"incidence": 0.95,
"category": {
"ratios": {
"U071": 0.5,
"U072": 0.5
}
},
},
),
positive_covid_test_ever=patients.with_test_result_in_sgss(
pathogen="SARS-CoV-2",
test_result="positive",
return_expectations={"incidence": 0.1},
),
## DEMOGRAPHIC COVARIATES
# AGE
age=patients.age_as_of(
"2020-02-01",
return_expectations={
"rate": "universal",
"int": {
"distribution": "population_ages"
},
},
),
# SEX
sex=patients.sex(return_expectations={
"rate": "universal",
"category": {
"ratios": {
"M": 0.49,
"F": 0.51
}
},
}),
# DEPRIVIATION
imd=patients.address_as_of(
"2020-02-01",
returning="index_of_multiple_deprivation",
round_to_nearest=100,
return_expectations={
"rate": "universal",
"category": {
"ratios": {
"100": 0.1,
"200": 0.2,
"300": 0.7
}
},
},
),
# GEOGRAPHIC REGION CALLED STP
stp=patients.registered_practice_as_of(
"2020-02-01",
returning="stp_code",
return_expectations={
"rate": "universal",
"category": {
"ratios": {
"STP1": 0.1,
"STP2": 0.1,
"STP3": 0.1,
"STP4": 0.1,
"STP5": 0.1,
"STP6": 0.1,
"STP7": 0.1,
"STP8": 0.1,
"STP9": 0.1,
"STP10": 0.1,
}
},
},
),
# ETHNICITY IN 6 CATEGORIES
ethnicity=patients.with_these_clinical_events(
ethnicity_codes,
returning="category",
find_last_match_in_period=True,
include_date_of_match=True,
return_expectations={
"category": {
"ratios": {
"1": 0.8,
"5": 0.1,
"3": 0.1
}
},
"incidence": 0.9,
},
),
# HOUSEHOLD INFORMATION
household_id=patients.household_as_of(
"2020-02-01",
returning="pseudo_id",
return_expectations={
"int": {
"distribution": "normal",
"mean": 1000,
"stddev": 200
},
"incidence": 1,
},
),
household_size=patients.household_as_of(
"2020-02-01",
returning="household_size",
return_expectations={
"int": {
"distribution": "normal",
"mean": 3,
"stddev": 1
},
"incidence": 1,
},
),
care_home_type=patients.care_home_status_as_of(
"2020-02-01",
categorised_as={
"PC": """
IsPotentialCareHome
AND LocationDoesNotRequireNursing='Y'
AND LocationRequiresNursing='N'
""",
"PN": """
IsPotentialCareHome
AND LocationDoesNotRequireNursing='N'
AND LocationRequiresNursing='Y'
""",
"PS": "IsPotentialCareHome",
"U": "DEFAULT",
},
return_expectations={
"rate": "universal",
"category": {
"ratios": {
"PC": 0.01,
"PN": 0.01,
"PS": 0.01,
"U": 0.97,
},
},
},
),
# CONTINUOUS MEASURED COVARIATES
bmi=patients.most_recent_bmi(
on_or_after="2010-02-01",
minimum_age_at_measurement=16,
include_measurement_date=True,
include_month=True,
return_expectations={
"date": {
"earliest": "2015-01-31"
},
"float": {
"distribution": "normal",
"mean": 25,
"stddev": 10
},
"incidence": 0.95,
},
),
# Blood pressure
bp_sys=patients.mean_recorded_value(
systolic_blood_pressure_codes,
on_most_recent_day_of_measurement=True,
on_or_before="2020-02-01",
include_measurement_date=True,
include_month=True,
return_expectations={
"float": {
"distribution": "normal",
"mean": 80,
"stddev": 10
},
"date": {
"latest": "2020-01-31"
},
"incidence": 0.95,
},
),
bp_dias=patients.mean_recorded_value(
diastolic_blood_pressure_codes,
on_most_recent_day_of_measurement=True,
on_or_before="2020-02-01",
include_measurement_date=True,
include_month=True,
return_expectations={
"float": {
"distribution": "normal",
"mean": 120,
"stddev": 10
},
"date": {
"latest": "2020-01-31"
},
"incidence": 0.95,
},
),
# # Creatinine
creatinine=patients.with_these_clinical_events(
creatinine_codes,
find_last_match_in_period=True,
on_or_before="2020-02-01",
returning="numeric_value",
include_date_of_match=True,
include_month=True,
return_expectations={
"float": {
"distribution": "normal",
"mean": 60.0,
"stddev": 15
},
"date": {
"earliest": "2019-02-28",
"latest": "2020-01-31"
},
"incidence": 0.95,
},
),
# COVARIATES
smoking_status=patients.categorised_as(
{
"S": "most_recent_smoking_code = 'S'",
"E": """
most_recent_smoking_code = 'E' OR (
most_recent_smoking_code = 'N' AND ever_smoked
)
""",
"N": "most_recent_smoking_code = 'N' AND NOT ever_smoked",
"M": "DEFAULT",
},
return_expectations={
"category": {
"ratios": {
"S": 0.6,
"E": 0.1,
"N": 0.2,
"M": 0.1
}
}
},
most_recent_smoking_code=patients.with_these_clinical_events(
clear_smoking_codes,
find_last_match_in_period=True,
on_or_before="2020-02-01",
returning="category",
),
ever_smoked=patients.with_these_clinical_events(
filter_codes_by_category(clear_smoking_codes, include=["S", "E"]),
on_or_before="2020-02-01",
),
),
smoking_status_date=patients.with_these_clinical_events(
clear_smoking_codes,
on_or_before="2020-02-01",
return_last_date_in_period=True,
include_month=True,
return_expectations={
"date": {
"latest": "2020-01-31"
},
"incidence": 0.95,
},
),
chronic_respiratory_disease=patients.with_these_clinical_events(
chronic_respiratory_disease_codes,
return_first_date_in_period=True,
include_month=True,
return_expectations={"date": {
"latest": "2020-01-31"
}},
),
chronic_cardiac_disease=patients.with_these_clinical_events(
chronic_cardiac_disease_codes,
return_first_date_in_period=True,
include_month=True,
return_expectations={"date": {
"latest": "2020-01-31"
}},
),
#DIABETES TYPE
type1_diabetes=patients.with_these_clinical_events(
diabetes_t1_codes,
on_or_before="2020-02-01",
return_first_date_in_period=True,
include_month=True,
),
type2_diabetes=patients.with_these_clinical_events(
diabetes_t2_codes,
on_or_before="2020-02-01",
return_first_date_in_period=True,
include_month=True,
),
unknown_diabetes=patients.with_these_clinical_events(
diabetes_unknown_codes,
on_or_before="2020-02-01",
return_first_date_in_period=True,
include_month=True,
),
diabetes_type=patients.categorised_as(
{
"T1DM": """
(type1_diabetes AND NOT
type2_diabetes)
OR
(((type1_diabetes AND type2_diabetes) OR
(type1_diabetes AND unknown_diabetes AND NOT type2_diabetes) OR
(unknown_diabetes AND NOT type1_diabetes AND NOT type2_diabetes))
AND
(insulin_lastyear_meds > 0 AND NOT
oad_lastyear_meds > 0))
""",
"T2DM": """
(type2_diabetes AND NOT
type1_diabetes)
OR
(((type1_diabetes AND type2_diabetes) OR
(type2_diabetes AND unknown_diabetes AND NOT type1_diabetes) OR
(unknown_diabetes AND NOT type1_diabetes AND NOT type2_diabetes))
AND
(oad_lastyear_meds > 0))
""",
"UNKNOWN_DM": """
((unknown_diabetes AND NOT type1_diabetes AND NOT type2_diabetes) AND NOT
oad_lastyear_meds AND NOT
insulin_lastyear_meds)
""",
"NO_DM": "DEFAULT",
},
return_expectations={
"category": {
"ratios": {
"T1DM": 0.03,
"T2DM": 0.2,
"UNKNOWN_DM": 0.02,
"NO_DM": 0.75
}
},
"rate": "universal"
},
oad_lastyear_meds=patients.with_these_medications(
oad_med_codes,
between=["2019-02-01", "2020-02-01"],
returning="number_of_matches_in_period",
),
insulin_lastyear_meds=patients.with_these_medications(
insulin_med_codes,
between=["2019-02-01", "2020-02-01"],
returning="number_of_matches_in_period",
),
),
#EXETER ALGORITHM USING OPENSAFELY CODELISTS
diabetes_exeter_os=patients.categorised_as(
{
"T1DM_EX_OS": """
insulin_last6mo >= 2 AND t1dm_count >= t2dm_count * 2
""",
"T2DM_EX_OS": """
(insulin_last6mo < 2 AND t2dm_count > 0)
OR
(insulin_last6mo >= 2 AND t1dm_count < t2dm_count * 2 AND t2dm_count > 0)
""",
"NO_DM": "DEFAULT",
},
return_expectations={
"category": {
"ratios": {
"T1DM_EX_OS": 0.03,
"T2DM_EX_OS": 0.2,
"NO_DM": 0.77
}
},
"rate": "universal"
},
t1dm_count=patients.with_these_clinical_events(
diabetes_t1_codes,
on_or_before="2020-02-01",
returning="number_of_matches_in_period",
),
t2dm_count=patients.with_these_clinical_events(
diabetes_t2_codes,
on_or_before="2020-02-01",
returning="number_of_matches_in_period",
),
insulin_last6mo=patients.with_these_medications(
insulin_med_codes,
between=["2019-08-01", "2020-02-01"],
returning="number_of_matches_in_period",
),
),
#EXETER ALGORITHM USING EXETER CODELISTS
diabetes_exeter=patients.categorised_as(
{
"T1DM_EX": """
insulin_last6mo >= 2 AND t1dm_count_ex >= t2dm_count_ex * 2
""",
"T2DM_EX": """
(insulin_last6mo < 2 AND t2dm_count_ex > 0)
OR
(insulin_last6mo >= 2 AND t1dm_count_ex < t2dm_count_ex * 2 AND t2dm_count_ex > 0)
""",
"NO_DM": "DEFAULT",
},
return_expectations={
"category": {
"ratios": {
"T1DM_EX": 0.1,
"T2DM_EX": 0.2,
"NO_DM": 0.7
}
},
"rate": "universal"
},
t1dm_count_ex=patients.with_these_clinical_events(
filter_codes_by_category(diabetes_t1t2_codes_exeter,
include=["1"]),
on_or_before="2020-02-01",
returning="number_of_matches_in_period",
),
t2dm_count_ex=patients.with_these_clinical_events(
filter_codes_by_category(diabetes_t1t2_codes_exeter,
include=["2"]),
on_or_before="2020-02-01",
returning="number_of_matches_in_period",
),
insulin_last6mo_ex=patients.with_these_medications(
insulin_med_codes,
between=["2019-08-01", "2020-02-01"],
returning="number_of_matches_in_period",
),
),
## HBA1C
hba1c_mmol_per_mol=patients.with_these_clinical_events(
hba1c_new_codes,
find_last_match_in_period=True,
on_or_before="2020-02-01",
returning="numeric_value",
include_date_of_match=True,
include_month=True,
return_expectations={
"date": {
"latest": "2020-02-29"
},
"float": {
"distribution": "normal",
"mean": 40.0,
"stddev": 20
},
"incidence": 0.95,
},
),
hba1c_percentage=patients.with_these_clinical_events(
hba1c_old_codes,
find_last_match_in_period=True,
on_or_before="2020-02-01",
returning="numeric_value",
include_date_of_match=True,
include_month=True,
return_expectations={
"date": {
"latest": "2020-02-29"
},
"float": {
"distribution": "normal",
"mean": 5,
"stddev": 2
},
"incidence": 0.95,
},
),
# CANCER - 3 TYPES
cancer_haem=patients.with_these_clinical_events(
haem_cancer_codes,
return_first_date_in_period=True,
include_month=True,
return_expectations={"date": {
"latest": "2020-01-31"
}},
),
cancer_nonhaem=patients.with_these_clinical_events(
combine_codelists(lung_cancer_codes, other_cancer_codes),
return_first_date_in_period=True,
include_month=True,
return_expectations={"date": {
"latest": "2020-01-31"
}},
),
#### PERMANENT
permanent_immunodeficiency=patients.with_these_clinical_events(
combine_codelists(hiv_codes, permanent_immune_codes,
sickle_cell_codes),
on_or_before="2020-01-31",
return_last_date_in_period=True,
include_month=True,
return_expectations={"date": {
"latest": "2020-01-31"
}},
),
asplenia=patients.with_these_clinical_events(
spleen_codes,
return_first_date_in_period=True,
include_month=True,
return_expectations={"date": {
"latest": "2020-01-31"
}},
),
### TEMPROARY IMMUNE
temporary_immunodeficiency=patients.with_these_clinical_events(
combine_codelists(temp_immune_codes, aplastic_codes),
between=["2019-02-01",
"2020-01-31"], ## THIS IS RESTRICTED TO LAST YEAR
return_last_date_in_period=True,
include_month=True,
return_expectations={
"date": {
"earliest": "2019-03-01",
"latest": "2020-01-31"
}
},
),
chronic_liver_disease=patients.with_these_clinical_events(
chronic_liver_disease_codes,
return_first_date_in_period=True,
include_month=True,
return_expectations={"date": {
"latest": "2020-01-31"
}},
),
stroke_dementia=patients.with_these_clinical_events(
combine_codelists(stroke, dementia),
return_first_date_in_period=True,
include_month=True,
return_expectations={"date": {
"latest": "2020-01-31"
}},
),
other_neuro=patients.with_these_clinical_events(
other_neuro,
return_first_date_in_period=True,
include_month=True,
return_expectations={"date": {
"latest": "2020-01-31"
}},
),
# END STAGE RENAL DISEASE - DIALYSIS, TRANSPLANT OR END STAGE RENAL DISEASE
esrf=patients.with_these_clinical_events(
esrf_codes,
return_first_date_in_period=True,
include_month=True,
return_expectations={"date": {
"latest": "2020-01-31"
}},
),
#Dialysis
dialysis=patients.with_these_clinical_events(
dialysis_codes,
return_first_date_in_period=True,
include_month=True,
return_expectations={"date": {
"latest": "2020-01-31"
}},
),
#Kidney transplant
kidney_transplant=patients.with_these_clinical_events(
kidney_transplant_codes,
return_first_date_in_period=True,
include_month=True,
return_expectations={"date": {
"latest": "2020-01-31"
}},
),
#Other organ transplant
other_transplant=patients.with_these_clinical_events(
other_transplant_codes,
return_first_date_in_period=True,
include_month=True,
return_expectations={"date": {
"latest": "2020-01-31"
}},
),
# hypertension
hypertension=patients.with_these_clinical_events(
hypertension_codes,
return_first_date_in_period=True,
include_month=True,
),
ra_sle_psoriasis=patients.with_these_clinical_events(
ra_sle_psoriasis_codes,
return_first_date_in_period=True,
include_month=True,
return_expectations={"date": {
"latest": "2020-01-31"
}},
),
# asthma
asthma=patients.categorised_as(
{
"0":
"DEFAULT",
"1":
"""
(
recent_asthma_code OR (
asthma_code_ever AND NOT
copd_code_ever
)
) AND (
prednisolone_last_year = 0 OR
prednisolone_last_year > 4
)
""",
"2":
"""
(
recent_asthma_code OR (
asthma_code_ever AND NOT
copd_code_ever
)
) AND
prednisolone_last_year > 0 AND
prednisolone_last_year < 5
""",
},
return_expectations={
"category": {
"ratios": {
"0": 0.6,
"1": 0.1,
"2": 0.3
}
}
},
recent_asthma_code=patients.with_these_clinical_events(
asthma_codes,
between=["2017-02-01", "2020-02-01"],
),
asthma_code_ever=patients.with_these_clinical_events(asthma_codes),
copd_code_ever=patients.with_these_clinical_events(
chronic_respiratory_disease_codes),
prednisolone_last_year=patients.with_these_medications(
pred_codes,
between=["2019-02-01", "2020-02-01"],
returning="number_of_matches_in_period",
),
),
)
study = StudyDefinition(
# Configure the expectations framework
default_expectations={
"date": {"earliest": "1900-01-01", "latest": "today"},
"rate": "uniform",
"incidence": 0.5,
},
# STUDY POPULATION
population=patients.all(),
# has_follow_up AND
# (age >=18 AND age <= 110) AND
# (rheumatoid OR osteoarthritis) AND
# imd >0 AND NOT (
# (has_asthma AND saba_single) OR
# aspirin_ten_years OR
# stroke OR
# mi OR
# gi_bleed_ulcer
# )
has_follow_up=patients.registered_with_one_practice_between(
"2019-02-28", "2020-02-29", return_expectations={"incidence": 0.9},
),
has_asthma=patients.with_these_clinical_events(
current_asthma_codes,
between=["2017-02-28", "2020-02-29"],
return_expectations={"incidence": 0.9},
),
aspirin_ten_years=patients.with_these_medications(
aspirin_med_codes,
between=["2010-02-01", "2020-02-29"],
returning="date",
find_last_match_in_period=True,
include_month=True,
include_day=False,
return_expectations={
"date": {"earliest": "2010-11-01", "latest": "2020-02-29"}
},
),
age=patients.age_as_of(
"2020-03-01",
return_expectations={
"rate": "universal",
"int": {"distribution": "population_ages"},
},
),
imd=patients.address_as_of(
"2020-02-29",
returning="index_of_multiple_deprivation",
round_to_nearest=100,
return_expectations={
"rate": "universal",
"category": {"ratios": {"100": 0.1, "200": 0.2, "300": 0.7}},
},
),
stroke=patients.with_these_clinical_events(
stroke_codes,
on_or_before="2020-02-29",
return_last_date_in_period=True,
include_month=True,
return_expectations={"date": {"latest": "2020-02-29"}},
),
#### Myocardial infarction
mi=patients.with_these_clinical_events(
mi_codes,
on_or_before="2020-02-29",
return_last_date_in_period=True,
include_month=True,
return_expectations={"date": {"latest": "2020-02-29"}},
),
#### GI BLEED
gi_bleed_ulcer=patients.with_these_clinical_events(
gi_bleed_ulcer_codes,
on_or_before="2020-02-29",
return_last_date_in_period=True,
include_month=True,
return_expectations={"date": {"latest": "2020-02-29"}},
),
# OSTEOARTHRITIS
osteoarthritis=patients.with_these_clinical_events(
osteoarthritis_codes,
on_or_before="2020-02-29",
return_last_date_in_period=True,
include_month=True,
return_expectations={"date": {"latest": "2020-02-29"}},
),
# RHEUMATOID ARTHRITIS
rheumatoid=patients.with_these_clinical_events(
rheumatoid_codes,
on_or_before="2020-02-29",
return_last_date_in_period=True,
include_month=True,
return_expectations={"date": {"latest": "2020-02-29"}},
),
#### SABA SINGLE CONSTITUENT - asthma treatment
saba_single=patients.with_these_medications(
saba_med_codes,
between=["2019-11-01", "2020-02-29"],
returning="date",
find_last_match_in_period=True,
include_month=True,
include_day=False,
return_expectations={
"date": {"earliest": "2019-11-01", "latest": "2020-02-29"},
},
),
)
study = StudyDefinition(
# Configure the expectations framework
default_expectations={
"date": {"earliest": "1970-01-01", "latest": "today"},
"rate": "uniform",
"incidence": 0.2,
},
# set an index date (as starting point)
index_date="2020-02-01",
# This line defines the study population that the below varaibles will be defined for
# currently registered patients restricts to those alive
# the age restriction is applied as current TPP linkage only includes linkages to old age care
population=patients.satisfying(
"""
(age >= 65 AND age < 120) AND
is_registered_with_tpp
""",
is_registered_with_tpp=patients.registered_as_of(
"index_date"
),
),
# TPP ADDRESS LINKAGE
# tpp defined care home as of date
tpp_care_home_type=patients.care_home_status_as_of(
"index_date",
categorised_as={
"PC": """
IsPotentialCareHome
AND LocationDoesNotRequireNursing='Y'
AND LocationRequiresNursing='N'
""",
"PN": """
IsPotentialCareHome
AND LocationDoesNotRequireNursing='N'
AND LocationRequiresNursing='Y'
""",
"PS": "IsPotentialCareHome",
"U": "DEFAULT",
},
return_expectations={
"rate": "universal",
"category": {"ratios": {"PC": 0.05, "PN": 0.05, "PS": 0.05, "U": 0.85,},},
},
),
# CODED EVENTS (extracted over different time periods to sense check)
# incentivised codes ever
snomed_carehome_ever=patients.with_these_clinical_events(
nhse_care_home_des_codes,
on_or_before="index_date",
returning="binary_flag",
return_expectations={"incidence": 0.1},
),
# incentivised codes within past year
snomed_carehome_pastyear=patients.with_these_clinical_events(
nhse_care_home_des_codes,
between=["index_date - 1 year", "index_date"],
returning="binary_flag",
return_expectations={"incidence": 0.1},
),
#primis codes ever
primis_carehome_ever=patients.with_these_clinical_events(
primis_codes,
on_or_before="index_date",
returning="binary_flag",
return_expectations={"incidence": 0.1},
),
#primis codes within past year
primis_carehome_pastyear=patients.with_these_clinical_events(
primis_codes,
between=["index_date - 1 year", "index_date"],
returning="binary_flag",
return_expectations={"incidence": 0.1},
),
# HOUSEHOLD RELATED VARIABLES
## household ID
household_id=patients.household_as_of(
"index_date",
returning="pseudo_id",
return_expectations={
"int": {"distribution": "normal", "mean": 1000, "stddev": 200},
"incidence": 1,
},
),
## household size
household_size=patients.household_as_of(
"index_date",
returning="household_size",
return_expectations={
"int": {"distribution": "normal", "mean": 3, "stddev": 1},
"incidence": 1,
},
),
# mixed household flag
nontpp_household=patients.household_as_of(
"index_date",
returning="has_members_in_other_ehr_systems",
return_expectations={ "incidence": 0.75
},
),
# mixed household percentage
tpp_coverage=patients.household_as_of(
"index_date",
returning="percentage_of_members_with_data_in_this_backend",
return_expectations={
"int": {"distribution": "normal", "mean": 75, "stddev": 10},
"incidence": 1,
},
),
# AGE and AGE CATEGORIES (latter needed for comparison w. census only)
# age
age=patients.age_as_of(
"index_date",
return_expectations={
"rate": "universal",
"int": {"distribution": "population_ages"},
},
),
# age band
ageband_narrow = patients.categorised_as(
{
"0": "DEFAULT",
"65-74": """ age >= 65 AND age < 75""",
"75-79": """ age >= 75 AND age < 80""",
"80-84": """ age >= 80 AND age < 85""",
"85-89": """ age >= 85 AND age < 120""",
},
return_expectations={
"rate":"universal",
"category": {"ratios": {"65-74": 0.4, "75-79": 0.2, "80-84":0.2, "85-89":0.2 }}
},
),
# SELECTED DEMOGRAPHIC CHARACTERISTICS TO DESCRIBE
# sex
sex=patients.sex(
return_expectations={
"rate": "universal",
"category": {"ratios": {"M": 0.49, "F": 0.51}},
}
),
# self-reported ethnicity
ethnicity=patients.with_these_clinical_events(
ethnicity_codes,
returning="category",
find_last_match_in_period=True,
include_date_of_match=False,
return_expectations={
"category": {"ratios": {"1": 0.8, "5": 0.1, "3": 0.1}},
"incidence": 0.75,
},
),
# grouped region of the practice
region=patients.registered_practice_as_of(
"index_date",
returning="nuts1_region_name",
return_expectations={
"rate": "universal",
"category": {
"ratios": {
"North East": 0.1,
"North West": 0.1,
"Yorkshire and the Humber": 0.1,
"East Midlands": 0.1,
"West Midlands": 0.1,
"East of England": 0.1,
"London": 0.2,
"South East": 0.2,
},
},
},
),
# imd
imd=patients.address_as_of(
"index_date",
returning="index_of_multiple_deprivation",
round_to_nearest=100,
return_expectations={
"rate": "universal",
"category": {"ratios": {"100": 0.1, "200": 0.2, "300": 0.7}},
},
),
# SELECTED CLINICAL CHARACTERISTICS TO DESCRIBE
# diabetes
diabetes=patients.with_these_clinical_events(
diabetes_codes,
on_or_before="index_date",
returning="binary_flag",
return_expectations={"incidence": 0.10},
),
# chronic respiratory disease (excl asthma)
chronic_respiratory_disease=patients.with_these_clinical_events(
chronic_respiratory_disease_codes,
on_or_before="index_date",
returning="binary_flag",
return_expectations={"incidence": 0.20},
),
# stroke
stroke=patients.with_these_clinical_events(
stroke_codes,
on_or_before="index_date",
returning="binary_flag",
return_expectations={"incidence": 0.05},
),
# chronic heart disease
chronic_cardiac_disease=patients.with_these_clinical_events(
chronic_cardiac_disease_codes,
on_or_before="index_date",
returning="binary_flag",
return_expectations={"incidence": 0.35},
),
# dementia
dementia=patients.with_these_clinical_events(
dementia_codes,
on_or_before="index_date",
returning="binary_flag",
return_expectations={"incidence": 0.45},
),
# cancer
cancer=patients.satisfying(
"lung_cancer OR haem_cancer OR other_cancer",
lung_cancer=patients.with_these_clinical_events(
lung_cancer_codes,
on_or_before="index_date",
returning="binary_flag",
return_expectations={"incidence": 0.10},
),
haem_cancer=patients.with_these_clinical_events(
haem_cancer_codes,
on_or_before="index_date",
return_expectations={"incidence": 0.05},
),
other_cancer=patients.with_these_clinical_events(
other_cancer_codes,
on_or_before="index_date",
return_expectations={"incidence": 0.10},
),
),
)
study = StudyDefinition(
# Configure the expectations framework
default_expectations={
"date": {
"earliest": "1970-01-01",
"latest": latest_date
},
"rate": "uniform",
"incidence": 0.2,
},
# 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
care_home_type=patients.care_home_status_as_of(
campaign_start,
categorised_as={
"PC": """
IsPotentialCareHome
AND LocationDoesNotRequireNursing='Y'
AND LocationRequiresNursing='N'
""",
"PN": """
IsPotentialCareHome
AND LocationDoesNotRequireNursing='N'
AND LocationRequiresNursing='Y'
""",
"PS": "IsPotentialCareHome",
"": "DEFAULT", # use empty string
},
return_expectations={
"rate": "universal",
"category": {
"ratios": {
"PC": 0.05,
"PN": 0.05,
"PS": 0.05,
"": 0.85,
},
},
},
),
# simple care home flag
care_home=patients.categorised_as(
{
1: """care_home_type""",
0: "DEFAULT",
},
return_expectations={
"rate": "universal",
"category": {
"ratios": {
1: 0.15,
0: 0.85,
},
},
},
),
age=patients.age_as_of(
"2021-03-31", # PHE defined date for calulating eligibilty across all vaccination campaigns
return_expectations={
"rate": "universal",
"int": {
"distribution": "population_ages"
},
},
),
ageband=patients.categorised_as(
{
"0": "DEFAULT",
# consider doing an under 16 age band as well to differentiate between workers and children eligble for another reason
"0-19": """ age >= 0 AND age < 20""",
"20-29": """ age >= 20 AND age < 30""",
"30-39": """ age >= 30 AND age < 40""",
"40-49": """ age >= 40 AND age < 50""",
"50-59": """ age >= 50 AND age < 60""",
"60-69": """ age >= 60 AND age < 70""",
"70-79": """ age >= 70 AND age < 80""",
"80+":
""" age >= 80 AND age < 120""", # age eligibility currently set at 80
},
return_expectations={
"rate": "universal",
"category": {
"ratios": {
"0-19": 0.125,
"20-29": 0.125,
"30-39": 0.125,
"40-49": 0.125,
"50-59": 0.125,
"60-69": 0.125,
"70-79": 0.125,
"80+": 0.125,
}
},
},
),
# age bands for patients not in care homes (ie living in the community)
ageband_community=patients.categorised_as(
{
"care home": "DEFAULT",
"0-19": """ age >= 0 AND age < 20 AND NOT care_home_type""",
"20-29": """ age >= 20 AND age < 30 AND NOT care_home_type""",
"30-39": """ age >= 30 AND age < 40 AND NOT care_home_type""",
"40-49": """ age >= 40 AND age < 50 AND NOT care_home_type""",
"50-59": """ age >= 50 AND age < 60 AND NOT care_home_type""",
"60-69": """ age >= 60 AND age < 70 AND NOT care_home_type""",
"70-79": """ age >= 70 AND age < 80 AND NOT care_home_type""",
"80+": """ age >= 80 AND age < 120 AND NOT care_home_type""",
},
return_expectations={
"rate": "universal",
"category": {
"ratios": {
"care home": 0.025,
"0-19": 0.1,
"20-29": 0.125,
"30-39": 0.125,
"40-49": 0.125,
"50-59": 0.125,
"60-69": 0.125,
"70-79": 0.125,
"80+": 0.125,
}
},
},
),
sex=patients.sex(return_expectations={
"rate": "universal",
"category": {
"ratios": {
"M": 0.49,
"F": 0.51
}
},
}),
# ETHNICITY IN 16 CATEGORIES
ethnicity_16=patients.with_these_clinical_events(
ethnicity_codes_16,
returning="category",
find_last_match_in_period=True,
include_date_of_match=False,
return_expectations={
"category": {
"ratios": {
"1": 0.0625,
"2": 0.0625,
"3": 0.0625,
"4": 0.0625,
"5": 0.0625,
"6": 0.0625,
"7": 0.0625,
"8": 0.0625,
"9": 0.0625,
"10": 0.0625,
"11": 0.0625,
"12": 0.0625,
"13": 0.0625,
"14": 0.0625,
"15": 0.0625,
"16": 0.0625,
}
},
"incidence": 0.75,
},
),
# ETHNICITY IN 6 CATEGORIES
ethnicity=patients.with_these_clinical_events(
ethnicity_codes,
returning="category",
find_last_match_in_period=True,
include_date_of_match=False,
return_expectations={
"category": {
"ratios": {
"1": 0.2,
"2": 0.2,
"3": 0.2,
"4": 0.2,
"5": 0.2
}
},
"incidence": 0.75,
},
),
# practice pseudo id
practice_id=patients.registered_practice_as_of(
campaign_start, # day before vaccine campaign start
returning="pseudo_id",
return_expectations={
"int": {
"distribution": "normal",
"mean": 1000,
"stddev": 100
},
"incidence": 1,
},
),
# stp is an NHS administration region based on geography
stp=patients.registered_practice_as_of(
campaign_start,
returning="stp_code",
return_expectations={
"rate": "universal",
"category": {
"ratios": {
"STP1": 0.1,
"STP2": 0.1,
"STP3": 0.1,
"STP4": 0.1,
"STP5": 0.1,
"STP6": 0.1,
"STP7": 0.1,
"STP8": 0.1,
"STP9": 0.1,
"STP10": 0.1,
}
},
},
),
# NHS administrative region
region=patients.registered_practice_as_of(
campaign_start,
returning="nuts1_region_name",
return_expectations={
"rate": "universal",
"category": {
"ratios": {
"North East": 0.1,
"North West": 0.1,
"Yorkshire and the Humber": 0.2,
"East Midlands": 0.1,
"West Midlands": 0.1,
"East of England": 0.1,
"London": 0.1,
"South East": 0.2,
},
},
},
),
# IMD - quintile
imd=patients.categorised_as(
{
"0":
"DEFAULT",
"1":
"""index_of_multiple_deprivation >=1 AND index_of_multiple_deprivation < 32844*1/5""",
"2":
"""index_of_multiple_deprivation >= 32844*1/5 AND index_of_multiple_deprivation < 32844*2/5""",
"3":
"""index_of_multiple_deprivation >= 32844*2/5 AND index_of_multiple_deprivation < 32844*3/5""",
"4":
"""index_of_multiple_deprivation >= 32844*3/5 AND index_of_multiple_deprivation < 32844*4/5""",
"5":
"""index_of_multiple_deprivation >= 32844*4/5 AND index_of_multiple_deprivation < 32844""",
},
index_of_multiple_deprivation=patients.address_as_of(
campaign_start,
returning="index_of_multiple_deprivation",
round_to_nearest=100,
),
return_expectations={
"rate": "universal",
"category": {
"ratios": {
"0": 0.05,
"1": 0.19,
"2": 0.19,
"3": 0.19,
"4": 0.19,
"5": 0.19,
}
},
},
),
# BMI
bmi=patients.categorised_as(
{
"Not obese": "DEFAULT",
"Obese I (30-34.9)": """ bmi_value >= 30 AND bmi_value < 35""",
"Obese II (35-39.9)": """ bmi_value >= 35 AND bmi_value < 40""",
"Obese III (40+)": """ bmi_value >= 40 AND bmi_value < 100""",
# set maximum to avoid any impossibly extreme values being classified as obese
},
bmi_value=patients.most_recent_bmi(on_or_after="2015-12-01",
minimum_age_at_measurement=16),
return_expectations={
"rate": "universal",
"category": {
"ratios": {
"Not obese": 0.7,
"Obese I (30-34.9)": 0.1,
"Obese II (35-39.9)": 0.1,
"Obese III (40+)": 0.1,
}
},
},
),
# CLINICAL CO-MORBIDITIES WORK IN PROGRESS IN COLLABORATION WITH NHSX
# https://github.com/opensafely/vaccine-eligibility/blob/master/analysis/study_definition.py
chronic_cardiac_disease=patients.with_these_clinical_events(
chronic_cardiac_disease_codes,
on_or_before=campaign_start,
returning="binary_flag",
return_expectations={
"incidence": 0.01,
},
),
current_copd=patients.with_these_clinical_events(
current_copd_codes,
on_or_before=campaign_start,
returning="binary_flag",
return_expectations={
"incidence": 0.01,
},
),
# on a dmard - indicative of immunosuppression
dmards=patients.with_these_medications(
dmards_codes,
on_or_before=campaign_start,
returning="binary_flag",
return_expectations={
"incidence": 0.01,
},
),
# dementia
dementia=patients.with_these_clinical_events(
dementia_codes,
on_or_before=campaign_start,
returning="binary_flag",
return_expectations={
"incidence": 0.01,
},
),
dialysis=patients.with_these_clinical_events(
dialysis_codes,
on_or_before=campaign_start,
returning="binary_flag",
return_expectations={
"incidence": 0.01,
},
),
solid_organ_transplantation=patients.with_these_clinical_events(
solid_organ_transplantation_codes,
on_or_before=campaign_start,
returning="binary_flag",
return_expectations={
"incidence": 0.01,
},
),
chemo_or_radio=patients.with_these_clinical_events(
chemotherapy_or_radiotherapy_codes,
on_or_before=campaign_start,
returning="binary_flag",
return_expectations={
"incidence": 0.01,
},
),
intel_dis_incl_downs_syndrome=patients.with_these_clinical_events(
intellectual_disability_including_downs_syndrome_codes,
on_or_before=campaign_start,
returning="binary_flag",
return_expectations={
"incidence": 0.01,
},
),
lung_cancer=patients.with_these_clinical_events(
lung_cancer_codes,
on_or_before=campaign_start,
returning="binary_flag",
return_expectations={
"incidence": 0.01,
},
),
cancer_excl_lung_and_haem=patients.with_these_clinical_events(
cancer_excluding_lung_and_haematological_codes,
on_or_before=campaign_start,
returning="binary_flag",
return_expectations={
"incidence": 0.01,
},
),
haematological_cancer=patients.with_these_clinical_events(
haematological_cancer_codes,
on_or_before=campaign_start,
returning="binary_flag",
return_expectations={
"incidence": 0.01,
},
),
bone_marrow_transplant=patients.with_these_clinical_events(
bone_marrow_transplant_codes,
between=["2020-07-01", campaign_start],
returning="binary_flag",
return_expectations={
"incidence": 0.01,
},
),
cystic_fibrosis=patients.with_these_clinical_events(
cystic_fibrosis_codes,
on_or_before=campaign_start,
returning="binary_flag",
return_expectations={
"incidence": 0.01,
},
),
sickle_cell_disease=patients.with_these_clinical_events(
sickle_cell_disease_codes,
on_or_before=campaign_start,
returning="binary_flag",
return_expectations={
"incidence": 0.01,
},
),
permanant_immunosuppression=patients.with_these_clinical_events(
permanent_immunosuppression_codes,
on_or_before=campaign_start,
returning="binary_flag",
return_expectations={
"incidence": 0.01,
},
),
temporary_immunosuppression=patients.with_these_clinical_events(
temporary_immunosuppression_codes,
on_or_before=campaign_start,
returning="binary_flag",
return_expectations={
"incidence": 0.01,
},
),
#
psychosis_schiz_bipolar=patients.with_these_clinical_events(
psychosis_schizophrenia_bipolar_affective_disease_codes,
on_or_before=campaign_start,
returning="binary_flag",
return_expectations={
"incidence": 0.01,
},
),
ssri=patients.with_these_medications(
ssri_codes,
between=["2019-12-01", campaign_start],
returning="binary_flag",
return_expectations={
"incidence": 0.01,
},
),
# https://github.com/opensafely/codelist-development/issues/4
asplenia=patients.with_these_clinical_events(
asplenia_codes,
on_or_before=campaign_start,
returning="binary_flag",
return_expectations={
"incidence": 0.01,
},
),
###############################################################################
# COVID VACCINATION
###############################################################################
# any COVID vaccination (first dose)
covid_vacc_date=patients.with_tpp_vaccination_record(
target_disease_matches="SARS-2 CORONAVIRUS",
on_or_after="2020-12-01", # check all december to date
find_first_match_in_period=True,
returning="date",
date_format="YYYY-MM-DD",
return_expectations={
"date": {
"earliest":
"2020-12-08", # first vaccine administered on the 8/12
"latest": "2021-01-31",
},
"incidence": 0.4
},
),
# SECOND DOSE COVID VACCINATION
covid_vacc_second_dose_date=patients.with_tpp_vaccination_record(
target_disease_matches="SARS-2 CORONAVIRUS",
on_or_after="covid_vacc_date + 19 days",
find_first_match_in_period=True,
returning="date",
date_format="YYYY-MM-DD",
return_expectations={
"date": {
"earliest":
"2020-12-29", # first reported second dose administered on the 29/12
"latest": latest_date,
},
"incidence": 0.1
},
),
# COVID VACCINATION - Pfizer BioNTech
covid_vacc_pfizer_date=patients.with_tpp_vaccination_record(
product_name_matches=
"COVID-19 mRNA Vac BNT162b2 30mcg/0.3ml conc for susp for inj multidose vials (Pfizer-BioNTech)",
on_or_after="2020-12-01", # check all december to date
find_first_match_in_period=True,
returning="date",
date_format="YYYY-MM-DD",
return_expectations={
"date": {
"earliest":
"2020-12-08", # first vaccine administered on the 8/12
"latest": latest_date,
},
"incidence": 0.3
},
),
# COVID VACCINATION - Oxford AZ
covid_vacc_oxford_date=patients.with_tpp_vaccination_record(
product_name_matches=
"COVID-19 Vac AstraZeneca (ChAdOx1 S recomb) 5x10000000000 viral particles/0.5ml dose sol for inj MDV",
on_or_after="2020-12-01", # check all december to date
find_first_match_in_period=True,
returning="date",
date_format="YYYY-MM-DD",
return_expectations={
"date": {
"earliest":
"2020-01-04", # first vaccine administered on the 4/1
"latest": latest_date,
},
"incidence": 0.1
},
),
# EPI-PEN
adrenaline_pen=patients.with_these_medications(
adrenaline_pen,
on_or_after="2018-12-01", # look for last two years
returning="binary_flag",
return_last_date_in_period=False,
include_month=False,
return_expectations={
"date": {
"earliest": "2018-12-01",
"latest": latest_date
},
"incidence": 0.001,
},
),
)
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"},
},
),
)
study = StudyDefinition(
# Configure the expectations framework
default_expectations={
"date": {
"earliest": index_date,
"latest": "today"
},
"rate": "uniform",
"incidence": 1
},
index_date=index_date,
# This line defines the study population
population=patients.satisfying(
"""
(age >= 18 AND age < 120) AND
(NOT died) AND
(registered)
""",
died=patients.died_from_any_cause(on_or_before=index_date,
returning="binary_flag"),
registered=patients.registered_as_of(index_date),
age=patients.age_as_of(index_date),
),
### geographic/administrative groups
practice=patients.registered_practice_as_of(
index_date,
returning="pseudo_id",
return_expectations={
"int": {
"distribution": "normal",
"mean": 100,
"stddev": 20
}
},
),
stp=patients.registered_practice_as_of(
index_date,
returning="stp_code",
return_expectations={
"category": {
"ratios": dict_stp
},
},
),
cholesterol=patients.with_these_clinical_events(
codes_cholesterol,
returning="number_of_episodes",
between=["index_date", "index_date + 1 month"],
return_expectations={
"int": {
"distribution": "normal",
"mean": 2,
"stddev": 0.5
}
},
),
inr=patients.with_these_clinical_events(
codes_inr,
returning="number_of_episodes",
between=["index_date", "index_date + 1 month"],
return_expectations={
"int": {
"distribution": "normal",
"mean": 3,
"stddev": 0.5
}
},
),
)
