def get_stroke_probability(self, person):
model_spec = load_model_spec("StrokeMIPartitionModel")
strokePartitionModel = StatsModelLinearRiskFactorModel(
RegressionModel(**model_spec))
strokeProbability = scipySpecial.expit(
strokePartitionModel.estimate_next_risk(person))
return strokeProbability
def __init__(
self,
mi_case_fatality=default_mi_case_fatality,
stroke_case_fatality=default_stroke_case_fatality,
mi_secondary_case_fatality=default_secondary_mi_case_fatality,
stroke_secondary_case_fatality=default_secondary_stroke_case_fatality,
secondary_prevention_multiplier=default_secondary_prevention_multiplier,
):
self.mi_case_fatality = mi_case_fatality
self.mi_secondary_case_fatality = (mi_secondary_case_fatality,)
self.stroke_case_fatality = stroke_case_fatality
self.stroke_secondary_case_fatality = stroke_secondary_case_fatality
self.secondary_prevention_multiplier = secondary_prevention_multiplier
model_spec = load_model_spec("StrokeMIPartitionModel")
self.strokePartitionModel = StatsModelLinearRiskFactorModel(RegressionModel(**model_spec))
def setUp(self):
popSize = 100
age = np.random.normal(loc=70, scale=20, size=popSize)
sbp = age * 1.05 + np.random.normal(loc=40, scale=30, size=popSize)
df = pd.DataFrame({"age": age, "sbp": sbp})
simpleModel = statsmodel.ols(formula="sbp ~ age", data=df)
self.simpleModelResultSM = simpleModel.fit()
self.simpleModelResult = RegressionModel(
self.simpleModelResultSM.params.to_dict(),
self.simpleModelResultSM.bse.to_dict(),
self.simpleModelResultSM.resid.mean(),
self.simpleModelResultSM.resid.std(),
)
self.person = Person(
age=80,
gender=NHANESGender.MALE,
raceEthnicity=NHANESRaceEthnicity.NON_HISPANIC_WHITE,
sbp=120,
dbp=80,
a1c=5.5,
hdl=50,
totChol=200,
bmi=27,
ldl=90,
trig=150,
waist=70,
anyPhysicalActivity=0,
education=Education.COLLEGEGRADUATE,
smokingStatus=SmokingStatus.NEVER,
alcohol=AlcoholCategory.NONE,
antiHypertensiveCount=0,
statin=0,
otherLipidLoweringMedicationCount=0,
creatinine=0.0,
initializeAfib=initializeAfib,
)
self.people = [
Person(
age=80,
gender=NHANESGender.MALE,
raceEthnicity=NHANESRaceEthnicity.NON_HISPANIC_WHITE,
sbp=bpinstance,
dbp=80,
a1c=5.5,
hdl=50,
totChol=200,
bmi=27,
ldl=90,
trig=150,
waist=70,
anyPhysicalActivity=0,
education=Education.COLLEGEGRADUATE,
smokingStatus=SmokingStatus.NEVER,
alcohol=AlcoholCategory.NONE,
antiHypertensiveCount=0,
statin=0,
otherLipidLoweringMedicationCount=0,
creatinine=0.0,
initializeAfib=initializeAfib,
) for bpinstance in sbp
]
for person in self.people:
self.advancePerson(person)
self.population_dataframe = init_vectorized_population_dataframe(
self.people,
with_base_gcp=True,
)
df2 = pd.DataFrame({
"age":
age,
"sbp": [person._sbp[-1] for person in self.people],
"meanSbp":
[np.array(person._sbp).mean() for person in self.people],
})
self.meanModelResultSM = statsmodel.ols(formula="sbp ~ age + meanSbp",
data=df2).fit()
self.meanModelResult = RegressionModel(
self.meanModelResultSM.params.to_dict(),
self.meanModelResultSM.bse.to_dict(),
self.meanModelResultSM.resid.mean(),
self.meanModelResultSM.resid.std(),
)
df3 = pd.DataFrame({
"age":
age,
"sbp": [person._sbp[-1] for person in self.people],
"logMeanSbp":
[np.log(np.array(person._sbp).mean()) for person in self.people],
})
self.logMeanModelResultSM = statsmodel.ols(
formula="sbp ~ age + logMeanSbp", data=df3).fit()
self.logMeanModelResult = RegressionModel(
self.logMeanModelResultSM.params.to_dict(),
self.logMeanModelResultSM.bse.to_dict(),
self.logMeanModelResultSM.resid.mean(),
self.logMeanModelResultSM.resid.std(),
)
race = np.random.randint(1, 5, size=popSize)
df4 = pd.DataFrame({"age": age, "sbp": sbp, "raceEthnicity": race})
df4.raceEthnicity = df4.raceEthnicity.astype("category")
self.raceModelResultSM = statsmodel.ols(
formula="sbp ~ age + raceEthnicity", data=df4).fit()
self.raceModelResult = RegressionModel(
self.raceModelResultSM.params.to_dict(),
self.raceModelResultSM.bse.to_dict(),
self.raceModelResultSM.resid.mean(),
self.raceModelResultSM.resid.std(),
)
dfMeanAndLag = pd.DataFrame({
"age":
age,
"sbp": [person._sbp[-1] for person in self.people],
"meanSbp":
[np.array(person._sbp).mean() for person in self.people],
"lagSbp": [person._sbp[-1] for person in self.people],
})
self.meanLagModelResultSM = statsmodel.ols(
formula="sbp ~ age + meanSbp + lagSbp", data=dfMeanAndLag).fit()
self.meanLagModelResult = RegressionModel(
self.meanLagModelResultSM.params.to_dict(),
self.meanLagModelResultSM.bse.to_dict(),
self.meanLagModelResultSM.resid.mean(),
self.meanLagModelResultSM.resid.std(),
)
self.ageSbpInteractionCoeff = 0.02
self.sbpInteractionCoeff = 0.5
self.interactionModel = RegressionModel(
{
"meanSbp#age": self.ageSbpInteractionCoeff,
"meanSbp": self.sbpInteractionCoeff,
"Intercept": 0,
},
{
"meanSbp#age": 0.0,
"meanSbp": 0.0
},
0,
0,
)
def load_regression_model(modelname):
model_spec = load_model_spec(modelname)
return RegressionModel(**model_spec)
def __init__(self):
self.mi_case_fatality = CVOutcomeDetermination.default_mi_case_fatality
self.secondary_mi_case_fatality = CVOutcomeDetermination.default_secondary_mi_case_fatality
self.stroke_case_fatality = CVOutcomeDetermination.default_stroke_case_fatality
self.secondary_stroke_case_fatality = (
CVOutcomeDetermination.default_secondary_stroke_case_fatality)
self.secondary_prevention_multiplier = (
CVOutcomeDetermination.default_secondary_prevention_multiplier)
self.outcomeDet = CVOutcomeDetermination(
self.mi_case_fatality,
self.stroke_case_fatality,
self.secondary_mi_case_fatality,
self.secondary_stroke_case_fatality,
self.secondary_prevention_multiplier,
)
# variable used in testing to control whether a patient will have a stroke or mi
self.manualStrokeMIProbability = None
self._models = {}
femaleCVCoefficients = {
"lagAge": 0.106501,
"black": 0.432440,
"lagSbp#lagSbp": 0.000056,
"lagSbp": 0.017666,
"current_bp_treatment": 0.731678,
"current_diabetes": 0.943970,
"current_smoker": 1.009790,
"lagAge#black": -0.008580,
"lagSbp#current_bp_treatment": -0.003647,
"lagSbp#black": 0.006208,
"black#current_bp_treatment": 0.152968,
"lagAge#lagSbp": -0.000153,
"black#current_diabetes": 0.115232,
"black#current_smoker": -0.092231,
"lagSbp#black#current_bp_treatment": -0.000173,
"lagAge#lagSbp#black": -0.000094,
"Intercept": -12.823110,
}
maleCVCoefficients = {
"lagAge": 0.064200,
"black": 0.482835,
"lagSbp#lagSbp": -0.000061,
"lagSbp": 0.038950,
"current_bp_treatment": 2.055533,
"current_diabetes": 0.842209,
"current_smoker": 0.895589,
"lagAge#black": 0,
"lagSbp#current_bp_treatment": -0.014207,
"lagSbp#black": 0.011609,
"black#current_bp_treatment": -0.119460,
"lagAge#lagSbp": 0.000025,
"black#current_diabetes": -0.077214,
"black#current_smoker": -0.226771,
"lagSbp#black#current_bp_treatment": 0.004190,
"lagAge#lagSbp#black": -0.000199,
"Intercept": -11.679980,
}
self._models[OutcomeModelType.CARDIOVASCULAR] = {
"female":
ASCVDOutcomeModel(
RegressionModel(
coefficients=femaleCVCoefficients,
coefficient_standard_errors={
key: 0
for key in femaleCVCoefficients
},
residual_mean=0,
residual_standard_deviation=0,
),
tot_chol_hdl_ratio=0.151318,
black_race_x_tot_chol_hdl_ratio=0.070498,
),
"male":
ASCVDOutcomeModel(
RegressionModel(
coefficients=maleCVCoefficients,
coefficient_standard_errors={
key: 0
for key in maleCVCoefficients
},
residual_mean=0,
residual_standard_deviation=0,
),
tot_chol_hdl_ratio=0.193307,
black_race_x_tot_chol_hdl_ratio=-0.117749,
),
}
self._models[
OutcomeModelType.GLOBAL_COGNITIVE_PERFORMANCE] = GCPModel()
self._models[OutcomeModelType.DEMENTIA] = DementiaModel()
# This represents non-cardiovascular mortality..
nonCVModelSpec = load_model_spec("nhanesMortalityModelLogit")
mortModel = StatsModelLogisticRiskFactorModel(
RegressionModel(**nonCVModelSpec), False)
# Recalibrate mortalitly model to align with life table data, as explored in notebook
# buildNHANESMortalityModel
mortModel.non_intercept_params[
"age"] = mortModel.non_intercept_params["age"] * -1
mortModel.non_intercept_params["squareAge"] = (
mortModel.non_intercept_params["squareAge"] * 4)
self._models[OutcomeModelType.NON_CV_MORTALITY] = mortModel
def __init__(self):
self.mi_case_fatality = CVOutcomeDetermination.default_mi_case_fatality
self.secondary_mi_case_fatality = CVOutcomeDetermination.default_secondary_mi_case_fatality
self.stroke_case_fatality = CVOutcomeDetermination.default_stroke_case_fatality
self.secondary_stroke_case_fatality = CVOutcomeDetermination.default_secondary_stroke_case_fatality
self.secondary_prevention_multiplier = CVOutcomeDetermination.default_secondary_prevention_multiplier
# variable used in testing to control whether a patient will have a stroke or mi
self.manualStrokeMIProbability = None
self._models = {}
femaleCVCoefficients = {
'lagAge': 0.106501,
'black': 0.432440,
'lagSbp#lagSbp': 0.000056,
'lagSbp': 0.017666,
'current_bp_treatment': 0.731678,
'current_diabetes': 0.943970,
'current_smoker': 1.009790,
'lagAge#black': -0.008580,
'lagSbp#current_bp_treatment': -0.003647,
'lagSbp#black': 0.006208,
'black#current_bp_treatment': 0.152968,
'lagAge#lagSbp': -0.000153,
'black#current_diabetes': 0.115232,
'black#current_smoker': -0.092231,
'lagSbp#black#current_bp_treatment': -0.000173,
'lagAge#lagSbp#black': -0.000094,
'Intercept': -12.823110
}
maleCVCoefficients = {
'lagAge': 0.064200,
'black': 0.482835,
'lagSbp#lagSbp': -0.000061,
'lagSbp': 0.038950,
'current_bp_treatment': 2.055533,
'current_diabetes': 0.842209,
'current_smoker': 0.895589,
'lagAge#black': 0,
'lagSbp#current_bp_treatment': -0.014207,
'lagSbp#black': 0.011609,
'black#current_bp_treatment': -0.119460,
'lagAge#lagSbp': 0.000025,
'black#current_diabetes': -0.077214,
'black#current_smoker': -0.226771,
'lagSbp#black#current_bp_treatment': 0.004190,
'lagAge#lagSbp#black': -0.000199,
'Intercept': -11.679980
}
self._models[OutcomeModelType.CARDIOVASCULAR] = {
"female":
ASCVDOutcomeModel(RegressionModel(
coefficients=femaleCVCoefficients,
coefficient_standard_errors={
key: 0
for key in femaleCVCoefficients
},
residual_mean=0,
residual_standard_deviation=0),
tot_chol_hdl_ratio=0.151318,
black_race_x_tot_chol_hdl_ratio=0.070498),
"male":
ASCVDOutcomeModel(RegressionModel(coefficients=maleCVCoefficients,
coefficient_standard_errors={
key: 0
for key in maleCVCoefficients
},
residual_mean=0,
residual_standard_deviation=0),
tot_chol_hdl_ratio=0.193307,
black_race_x_tot_chol_hdl_ratio=-0.117749)
}
self._models[
OutcomeModelType.GLOBAL_COGNITIVE_PERFORMANCE] = GCPModel()
# This represents non-cardiovascular mortality..
self._models[
OutcomeModelType.NON_CV_MORTALITY] = self.initialize_cox_model(
"nhanesMortalityModel")