pycomorb

Comorbidity and frailty scores (Charlson, Elixhauser, Combined Comorbidity Score, HFRS) from ICD-9/ICD-10 codes, built on polars. Its distinguishing feature is harmonising ICD-10-GM / ICD-10-CM codes across code-set years before scoring.

Installation

pip install pycomorb

Requires Python 3.10+ and polars>=1.21.0; pandas, pyarrow and pyyaml are installed as dependencies.

Quickstart

One row per patient and code. Polars in, polars out; a pandas DataFrame returns a pandas DataFrame.

import polars as pl
from pycomorb import comorbidity

df = pl.DataFrame({
    "id": [1, 2, 3],
    "code": ["I21", "E119", "C349"],
    "age": [65, 72, 80],
})

result = comorbidity(
    score="charlson", df=df, id_col="id", code_col="code", age_col="age",
    icd_version="icd10", implementation="quan", return_categories=True,
)

return_categories=True adds one column per comorbidity category next to the score.

More

• Citation: see CITATION.cff.
• Data sources and attributions (including BfArM ICD-10-GM): NOTICE.
• Citations for every variant: References.
• MIT license.