## LIBRARIES - simple study definitions
# cohort extractor
from cohortextractor import (StudyDefinition, patients)
# dictionaries of STP codes (for dummy data)
from dictionaries import dict_stp
# set the index date
index_date = "2020-01-01"
## STUDY POPULATION
study = StudyDefinition(
default_expectations={
"date": {
"earliest": index_date,
"latest": "today"
}, # date range for simulation
"rate": "uniform",
"incidence": 1
},
population=patients.registered_as_of(index_date),
stp=patients.registered_practice_as_of(index_date,
returning="stp_code",
return_expectations={
"category": {
"ratios": dict_stp
},
}))
"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": {
#return_expectations= { "incidence": 0.6 },),
return_expectations={
"category": {
"ratios": {
"0": 0.5,
"1": 0.5
}
},
},
),
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}),
return_expectations={
"rate": "universal",
"category": {
"ratios": {
"M": 0.49,
"F": 0.5,
"U": 0.01
}
},
}),
practice=patients.registered_practice_as_of("index_date",
returning="pseudo_id",
return_expectations={
"int": {
"distribution":
"normal",
"mean": 25,
"stddev": 5
},
"incidence": 0.5
}),
region=patients.registered_practice_as_of(
"index_date",
returning="nuts1_region_name",
return_expectations={
"category": {
"ratios": {
"North East": 0.1,
"North West": 0.1,
"Yorkshire and the Humber": 0.1,
"East Midlands": 0.1,
},
},
),
# GEOGRAPHIC REGION CALLED STP
stp=patients.registered_practice_as_of(
"2019-02-01",
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",
},
},
),
# 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,
}
},
},
),
# OTHER REGION
region=patients.registered_practice_as_of(
"2020-02-01",
returning="nuts1_region_name",
"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
"latest": "today"
},
"rate": "uniform",
},
index_date="2020-01-01",
population=patients.registered_with_one_practice_between(
"index_date", "index_date"),
region=patients.registered_practice_as_of(
"index_date",
returning="nuts1_region_name",
return_expectations={
"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,
}
},
"incidence": 0.8
}),
sex=patients.sex(return_expectations={
"rate": "universal",
"category": {
"ratios": {
"M": 0.49,
"F": 0.51
}
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
}
},
},
),
)
measures = [
Measure(
id="liver_disease_by_stp",
numerator="has_chronic_liver_disease",
denominator="population",
group_by="stp",
small_number_suppression=True,
),
"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,
# 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}
),
)
(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(