Diabetes

Presentation

We provide the DiabetesFromICD10 class to extract visits or patients with ICD10 codes related to diabetes

Available diabetes types

DIABETES_IN_PREGNANCY
DIABETES_MALNUTRITION
DIABETES_TYPE_I
DIABETES_TYPE_II
OTHER_DIABETES_MELLITUS

How it works

The algorithm works by looking for either DP, DR or DAS ICD10 codes associated with cancer. Those codes are available under DiabetesFromICD10.ICD10_CODES

Usage

By default, all diabetes types mentionned above are extracted

from eds_scikit.io import HiveData
data = HiveData(DBNAME)

from eds_scikit.phenotype import DiabetesFromICD10

diabetes = DiabetesFromICD10(data)
data = diabetes.to_data()

To choose a subset of disorders, use the diabetes_types argument:

diabetes = DiabetesFromICD10(
    data,
    diabetes_types=[
        "DIABETES_TYPE_I",
        "DIABETES_IN_PREGNANCY",
    ],
)

The final phenotype DataFrame is then available at data.computed["DiabetesFromICD10"]

Optional parameters

PARAMETER	DESCRIPTION
`data`	A BaseData object TYPE: `BaseData`
`diabetes_types`	Optional list of diabetes types to use for phenotyping TYPE: `Optional[List[str]]` DEFAULT: `None`
`level`	On which level to do the aggregation, either "patient" or "visit" TYPE: `str` DEFAULT: `'visit'`
`subphenotype`	Whether the threshold should apply to the phenotype ("phenotype" column) of the subphenotype ("subphenotype" column) TYPE: `bool` DEFAULT: `True`
`threshold`	Minimal number of events (which definition depends on the `level` value) TYPE: `int` DEFAULT: `1`

Reference

Check the code reference here for a more detailled look.