pycomorb 0.4__py3-none-any.whl

pycomorb/GagneComorbidityIndex.py

@@ -0,0 +1,95 @@
+# Reference for GCI:
+# 1. Gagne JJ, Glynn RJ, Avorn J, Levin R, Schneeweiss S.
+#    A combined comorbidity score predicted mortality in elderly patients better than existing scores.
+#    J Clin Epidemiol. 2011 Jul;64(7):749-59.
+#    doi: 10.1016/j.jclinepi.2010.10.004. Epub 2011 Jan 5. PMID: 21208778; PMCID: PMC3100405.
+#
+# Reference for source ICD-9-CM Coding Algorithms:
+# 2. Romano PS, Roos LL, Jollis JG.
+#    Adapting a clinical comorbidity index for use with ICD-9-CM administrative data: differing perspectives.
+#    J Clin Epidemiol. 1993 Oct;46(10):1075-9; discussion 1081-90.
+#    doi: 10.1016/0895-4356(93)90103-8. PMID: 8410092.
+# 3. Quan H, Sundararajan V, Halfon P, Fong A, Burnand B, Luthi JC, Saunders LD, Beck CA, Feasby TE, Ghali WA.
+#    Coding algorithms for defining comorbidities in ICD-9-CM and ICD-10 administrative data.
+#    Med Care. 2005 Nov;43(11):1130-9.
+#    doi: 10.1097/01.mlr.0000182534.19832.83. PMID: 16224307.
+#
+# Reference for ICD-9 / ICD-10 mapping:
+# 4. Sun JW, Rogers JR, Her Q, Welch EC, Panozzo CA, Toh S, Gagne JJ.
+#    Adaptation and Validation of the Combined Comorbidity Score for ICD-10-CM.
+#    Med Care. 2017 Dec;55(12):1046-1051.
+#    doi: 10.1097/MLR.0000000000000824. PMID: 29087983.
+
+from pathlib import Path
+
+import pandas as pd
+import polars as pl
+
+# Import the generalized function
+from .CustomComorbidityIndex import CustomComorbidityIndex
+
+
+def GagneComorbidityIndex(
+    df: pl.DataFrame,
+    id_col: str = "id",
+    code_col: str = "code",
+    icd_version: str = "icd9",
+    icd_version_col: str = None,
+    return_categories=False,
+):
+    """
+    Calculate the Gagne Comorbidity Index using ICD codes.
+
+    Args:
+        df (pl.DataFrame): DataFrame with at least columns [id_col, code_col].
+        id_col (str): Name of the column containing unique identifier. Default: "id".
+        code_col (str): Name of the column containing ICD codes. Default: "code".
+        icd_version (str): ICD version ('icd9', 'icd10', or 'icd9_10'). Default: "icd9".
+        icd_version_col (str, optional): Name of the column with ICD version for 'icd9_10'. Default: None.
+        return_categories (bool): If True, also return presence indicators for each Gagne category.
+
+    Returns:
+        - DataFrame with [id_col, "Gagne Score"].
+        - DataFrame with category indicators if return_categories is True, else None.
+    """
+
+    # Check if input is pandas DataFrame and convert to polars
+    is_pandas = pd and isinstance(df, pd.DataFrame)
+    if is_pandas:
+        df = pl.from_pandas(df)
+
+    assert (
+        id_col in df.columns
+    ), f"Column '{id_col}' (ID) must be present in input DataFrame."
+    assert (
+        code_col in df.columns
+    ), f"Column '{code_col}' (ICD code) must be present in input DataFrame."
+
+    definition_file = "GAGNE.csv"
+    definition_file_path = Path(__file__).parent / f"common/{definition_file}"
+    weight_col_name = "weights"
+    score_col_name = "Gagne Score"
+
+    # Define mutual exclusion rules for Gagne
+    mutual_exclusion_rules = [
+        ("Complicated diabetes", "Uncomplicated diabetes")
+    ]
+
+    # Call the generalized function
+    df_gagne = CustomComorbidityIndex(
+        df=df,
+        id_col=id_col,
+        code_col=code_col,
+        icd_version=icd_version,
+        icd_version_col=icd_version_col,
+        definition_data=definition_file_path,
+        weight_col_name=weight_col_name,
+        score_col_name=score_col_name,
+        mutual_exclusion_rules=mutual_exclusion_rules,
+        return_categories=return_categories,
+    )
+
+    if is_pandas:
+        return df_gagne.to_pandas()
+
+    return df_gagne

pycomorb/HospitalFrailtyRiskScore.py

@@ -0,0 +1,182 @@
+# Reference for HFRS:
+# 1. Gilbert T, Neuburger J, Kraindler J, Keeble E, Smith P, Ariti C, Arora S,
+#    Street A, Parker S, Roberts HC, Bardsley M, Conroy S. Development and
+#    validation of a Hospital Frailty Risk Score focusing on older people in
+#    acute care settings using electronic hospital records: an observational
+#    study. Lancet. 2018 May 5;391(10132):1775-1782.
+#    doi: 10.1016/S0140-6736(18)30668-8. Epub 2018 Apr 26. PMID: 29706364;
+#    PMCID: PMC5946808.
+
+from pathlib import Path
+
+import pandas as pd
+import polars as pl
+
+
+def HospitalFrailtyRiskScore(
+    df: pl.DataFrame,
+    id_col: str = "id",
+    code_col: str = "code",
+    icd_version: str = "icd10",
+    return_categories=False,
+):
+    """
+    Calculate the Hospital Frailty Risk Score (HFRS) using ICD-10 codes.
+
+    Args:
+        df (pl.DataFrame): DataFrame with at least columns [id_col, code_col].
+        id_col (str): Name of the column containing unique identifier. Default: "id".
+        code_col (str): Name of the column containing ICD codes. Default: "code".
+        icd_version (str): ICD version ('icd10'). HFRS requires ICD-10. Default: "icd10".
+        return_categories (bool): If True, also return presence indicators for each HFRS category.
+
+    Returns:
+        - DataFrame with [id_col, "HFRS Score"].
+        - DataFrame with category indicators if return_categories is True, else None.
+    """
+
+    # Check if input is pandas DataFrame and convert to polars
+    is_pandas = pd and isinstance(df, pd.DataFrame)
+    if is_pandas:
+        df = pl.from_pandas(df)
+
+    # Input validation
+    assert icd_version == "icd10", "icd_version must be 'icd10' for HFRS."
+    assert (
+        code_col in df.columns
+    ), f"Column '{code_col}' (ICD code) must be present in input DataFrame."
+    assert (
+        id_col in df.columns
+    ), f"Column '{id_col}' (ID) must be present in input DataFrame."
+
+    # Drop rows from df with missing codes
+    df = df.filter(pl.col(code_col).is_not_null())
+
+    # Load definitions
+    definition_file = "HFRS.csv"
+    definition_file_path = Path(__file__).parent / f"common/{definition_file}"
+    definitions = pl.read_csv(definition_file_path, separator=",")
+
+    assert (
+        "category" in definitions.columns
+    ), "'category' column not found in definition file."
+    assert (
+        "weight" in definitions.columns
+    ), "'weight' column not found in definition file."
+
+    def process_single_icd(df, icd_col_name):
+        # Prepare mapping DataFrame: code_col, category
+        code_map_rows = []
+        for row in definitions.iter_rows(named=True):
+            if row["category"] is None or row.get(icd_col_name) is None:
+                continue
+            for code in row[icd_col_name].split("|"):
+                code_map_rows.append(
+                    {"prefix": code.strip(), "category": row["category"]}
+                )
+        code_map = pl.DataFrame(code_map_rows)
+
+        # Create dataframe with presence indicators
+        categories = code_map.select("category").unique()
+        categories_list = categories.to_series().to_list()
+        categories_df = categories.with_columns(
+            pl.when(pl.col("category") == category)
+            .then(pl.lit(1))
+            .otherwise(pl.lit(0))
+            .alias(category)
+            for category in categories_list
+        )
+
+        # Get all unique ICD codes in the data
+        code_prefixes = code_map.select("prefix").to_series()
+        unique_codes = df.select(code_col).unique()
+        code_list = [
+            str(c) for c in unique_codes[code_col].to_list() if c is not None
+        ]
+        if code_list:
+            longest_code_len = max((len(c) for c in code_list), default=1)
+        else:
+            longest_code_len = 1
+
+        # Create a DataFrame with all possible prefixes, then find the best match
+        best_prefix = (
+            unique_codes.with_columns(
+                pl.col(code_col).str.slice(0, n).alias(f"prefix_{n}")
+                for n in range(1, longest_code_len + 1)
+            )
+            .with_columns(
+                pl.when(pl.col(f"prefix_{n}").is_in(code_prefixes))
+                .then(pl.col(f"prefix_{n}"))
+                .otherwise(None)
+                .alias(f"prefix_{n}")
+                for n in range(1, longest_code_len + 1)
+            )
+            .with_columns(
+                pl.coalesce(
+                    *[
+                        pl.col(f"prefix_{n}")
+                        for n in range(longest_code_len, 0, -1)
+                    ]
+                ).alias("best_prefix")
+            )
+            .select(code_col, "best_prefix")
+            .drop_nulls("best_prefix")
+        )
+
+        code_to_category = (
+            best_prefix.join(
+                code_map, left_on="best_prefix", right_on="prefix", how="left"
+            )
+            .select(code_col, "category")
+            .join(categories_df, on="category", how="left")
+            .select(code_col, *categories_list)
+        )
+
+        # Join diagnoses with code_to_category to get the best matching category for each diagnosis
+        df_presence_absence = (
+            df.join(code_to_category, on=code_col, how="left")
+            .group_by(id_col)
+            .agg(pl.max(cat).fill_null(0).alias(cat) for cat in categories_list)
+        )
+
+        # Add missing columns
+        for cat in categories_list:
+            if cat not in df_presence_absence.columns:
+                df_presence_absence = df_presence_absence.with_columns(
+                    pl.lit(0).alias(cat)
+                )
+        df_presence_absence = df_presence_absence.select(
+            [id_col] + categories_list
+        )
+        return df_presence_absence, categories_list
+
+    # Only ICD-10 supported for HFRS
+    df_presence_absence, all_categories = process_single_icd(df, "icd10_codes")
+
+    # STEP 2: calculate HFRS score
+    category_weights = dict(zip(definitions["category"], definitions["weight"]))
+    category_weights = {
+        k: v
+        for k, v in category_weights.items()
+        if k is not None and v is not None
+    }
+
+    score_expr = (
+        pl.sum_horizontal(
+            pl.col(cat) * category_weights.get(cat, 0)
+            for cat in all_categories
+            if cat in df_presence_absence.columns and cat in category_weights
+        )
+        .round(1)
+        .alias("HFRS Score")
+    )
+
+    cols = [id_col] + all_categories if return_categories else [id_col]
+    hfrs_df = df_presence_absence.select(*cols, score_expr).cast(
+        {"HFRS Score": float}
+    )
+
+    if is_pandas:
+        return hfrs_df.to_pandas()
+
+    return hfrs_df

pycomorb/__init__.py

@@ -0,0 +1,114 @@
+"""Top-level package for comorbidipy."""
+
+__author__ = """Finn Fassbender"""
+__email__ = "finn.fassbender@charite.de"
+__version__ = "0.4"
+
+from .CharlsonComorbidityIndex import CharlsonComorbidityIndex
+from .ElixhauserComorbidityIndex import ElixhauserComorbidityIndex
+from .GagneComorbidityIndex import GagneComorbidityIndex
+from .HospitalFrailtyRiskScore import HospitalFrailtyRiskScore
+
+
+def comorbidity(
+    score: str,
+    df,
+    id_col="id",
+    code_col="code",
+    age_col="age",
+    icd_version="icd10",
+    icd_version_col=None,
+    implementation=None,
+    weights=None,
+    return_categories=False,
+):
+    """
+    Unified wrapper to calculate a comorbidity or frailty score.
+
+    Args:
+        score (str): Which score to calculate.
+        df (pl.DataFrame): DataFrame with at least columns [id_col, code_col] (and age_col for Charlson).
+        id_col (str): Name of the column containing unique identifier. Default: "id".
+        code_col (str): Name of the column containing ICD codes. Default: "code".
+        age_col (str): Name of the column containing patient ages (Charlson only). Default: "age".
+        icd_version (str): ICD version. Default: "icd10".
+        icd_version_col (str, optional): Name of the column with ICD version for 'icd9_10'. Default: None.
+        implementation (str, optional): Implementation variant (see individual index docs).
+        weights (str, optional): Weighting scheme (Elixhauser only).
+        return_categories (bool): Whether to return category indicators.
+
+    Returns:
+        - DataFrame with [id_col, score].
+        - DataFrame with category indicators if return_categories is True, else None.
+    """
+    score = score.lower()
+    if score in (
+        "cci",
+        "charlson",
+        "charlsoncomorbidityindex",
+        "charlson_comorbidity_index",
+    ):
+        if age_col not in df.columns:
+            raise ValueError(
+                f"Column '{age_col}' (age) must be present in input DataFrame for Charlson calculation."
+            )
+        return CharlsonComorbidityIndex(
+            df=df,
+            id_col=id_col,
+            code_col=code_col,
+            age_col=age_col,
+            icd_version=icd_version,
+            icd_version_col=icd_version_col,
+            implementation=implementation or "quan",
+            return_categories=return_categories,
+        )
+    elif score in (
+        "eci",
+        "elixhauser",
+        "elixhausercomorbidityindex",
+        "elixhauser_comorbidity_index",
+    ):
+        return ElixhauserComorbidityIndex(
+            df=df,
+            id_col=id_col,
+            code_col=code_col,
+            icd_version=icd_version,
+            icd_version_col=icd_version_col,
+            implementation=implementation or "quan",
+            weights=weights or "van_walraven",
+            return_categories=return_categories,
+        )
+    elif score in (
+        "gci",
+        "gagne",
+        "gagnecomorbidityindex",
+        "gagne_comorbidity_index",
+        "combined",
+        "combinedcomorbidityindex",
+        "combined_comorbidity_index",
+    ):
+        return GagneComorbidityIndex(
+            df=df,
+            id_col=id_col,
+            code_col=code_col,
+            icd_version=icd_version,
+            icd_version_col=icd_version_col,
+            return_categories=return_categories,
+        )
+    elif score in (
+        "hfrs",
+        "hospitalfrailtyriskscore",
+        "hospital_frailty_risk_score",
+    ):
+        return HospitalFrailtyRiskScore(
+            df=df,
+            id_col=id_col,
+            code_col=code_col,
+            icd_version=icd_version,
+            return_categories=return_categories,
+        )
+    else:
+        raise ValueError(
+            f"Unknown score: '{score}'. Must be one of: "
+            "'charlson', 'elixhauser', 'gagne', 'hfrs'."
+        )

pycomorb/common/CHARLSON_AUSTRALIA.csv

@@ -0,0 +1,19 @@
+index,category,icd9_codes,icd10_codes,weights
+0,Age,,YYYY|YYYY,1
+1,Myocardial infarction,,I21|I22|I252,1
+2,Congestive heart failure,,I50,1
+3,Peripheral vascular disease,,I71|I790|I739|R02|Z958|Z959,1
+4,Cerebrovascular disease,,I60|I61|I62|I63|I65|I66|G450|G451|G452|G458|G459|G46|I64|G454|I670|I671|I672|I674|I675|I676|I677|I678|I679|I681|I682|I688|I69,1
+5,Dementia,,F00|F01|F02|F051,1
+6,Chronic pulmonary disease,,J40|J41|J42|J44|J43|J45|J46|J47|J67|J44|J60|J61|J62|J63|J66|J64|J65,1
+7,Connective tissue disorder,,M32|M34|M332|M053|M058|M059|M060|M063|M069|M050|M052|M051|M353,1
+8,Peptic ulcer disease,,K25|K26|K27|K28,1
+9,Mild liver disease,,K702|K703|K73|K717|K740|K742|K746|K743|K744|K745,1
+10,Diabetes,,E109|E119|E139|E149|E101|E111|E131|E141|E105|E115|E135|E145,1
+11,Diabetes complications,,E102|E112|E132|E142|E103|E113|E133|E143|E104|E114|E134|E144,2
+12,Paraplegia,,G81|G041|G820|G821|G822,2
+13,Renal disease,,N03|N052|N053|N054|N055|N056|N072|N073|N074|N01|N18|N19|N25,2
+14,Cancer,,C0|C1|C2|C3|C40|C41|C43|C45|C46|C47|C48|C49|C5|C6|C70|C71|C72|C73|C74|C75|C76|C80|C81|C82|C83|C84|C85|C883|C887|C889|C900|C901|C91|C92|C93|C940|C941|C942|C943|C9451|C947|C95|C96,2
+15,Moderate or severe liver disease,,K729|K766|K767|K721,3
+16,Metastatic solid tumor,,C77|C78|C79|C80,6
+17,AIDS/HIV,,B20|B21|B22|B23|B24,6

pycomorb/common/CHARLSON_DEYO.csv

@@ -0,0 +1,19 @@
+index,category,icd9_codes,icd10_codes,weights
+0,Age,XXXX|XXXX,,1
+1,Myocardial infarction,410|412,,1
+2,Congestive heart failure,428,,1
+3,Peripheral vascular disease,4439|441|7854|V434,,1
+4,Cerebrovascular disease,430|431|432|433|434|435|436|437|438,,1
+5,Dementia,290,,1
+6,Chronic pulmonary disease,49|501|502|503|504|505,,1
+7,Rheumatic disease,7100|7101|7104|7140|7141|7142|71481|725,,1
+8,Peptic ulcer disease,531|532|533|534,,1
+9,Mild liver disease,5712|5714|5715|5716,,1
+10,Diabetes without chronic complication,2500|2501|2502|2503|2507,,1
+11,Diabetes with chronic complication,2504|2505|2506,,2
+12,Hemiplegia or paraplegia,3441|342,,2
+13,Renal disease,582|5830|5831|5832|5833|5834|5835|5836|5837|585|586|588,,2
+14,"Any malignancy, including lymphoma and leukemia",14|15|16|170|171|172|175|176|177|178|179|18|190|191|192|193|194|1950|1951|1952|1953|1954|1955|1956|1957|1958|2OO|201|202|203|204|205|206|207|208,,2
+15,Moderate or severe liver disease,5722|5723|5724|5725|5726|5727|5728,,3
+16,Metastatic solid tumor,196|197|198|1990|1991,,6
+17,AIDS/HIV,042|043|044,,6

pycomorb/common/CHARLSON_DHOORE.csv

@@ -0,0 +1,19 @@
+index,category,icd9_codes,icd10_codes,weights
+0,Age,XXXX|XXXX,,1
+1,Myocardial infarction,410|412,,1
+2,Congestive heart failure,398|402|428,,1
+3,Peripheral vascular disease,440|441|442|443|444|445|446|447,,1
+4,Cerebrovascular disease,430|431|432|433|435,,1
+5,Dementia,290|291|294,,1
+6,Chronic pulmonary disease,491|492|493,,1
+7,Rheumatic disease,710|714|725,,1
+8,Peptic ulcer disease,531|532|533|534,,1
+9,Mild liver disease,571|573,,1
+10,Diabetes without chronic complication,250,,1
+11,Diabetes with chronic complication,250,,2
+12,Hemiplegia or paraplegia,342|434|436|437,,2
+13,Renal disease,403|404|580|581|582|583|584|585|586,,2
+14,"Any malignancy, including lymphoma and leukemia",14|15|16|17|18|190|191|192|193|194|195|2OO|202|203|204|205|206|207|208,,2
+15,Moderate or severe liver disease,070|570|572,,3
+16,Metastatic solid tumor,196|197|198|199,,6
+17,AIDS/HIV,,,6

pycomorb/common/CHARLSON_QUAN.csv

@@ -0,0 +1,19 @@
+index,category,icd9_codes,icd10_codes,weights
+0,Age,XXXX|XXXX,YYYY|YYYY,1
+1,Myocardial infarction,410|412,I21|I22|I252,1
+2,Congestive heart failure,428|4254|4259|39891|40201|40211|40291|40401|40403|40411|40413|40491|40493,I43|I50|I099|I110|I130|I132|I255|I420|I425|I426|I427|I428|I429|P290,1
+3,Peripheral vascular disease,440|441|0930|4373|4471|5571|5579|V434|4431|4432|4433|4434|4435|4436|4437|4438|4439,I70|I71|I731|I738|I739|I771|I790|I792|K551|K558|K559|Z958|Z959,1
+4,Cerebrovascular disease,430|431|432|433|434|435|436|437|438|36234,G45|G46|I60|I61|I62|I63|I64|I65|I66|I67|I68|I69|H340,1
+5,Dementia,290|2941|3312,F00|F01|F02|F03|G30|F051|G311,1
+6,Chronic pulmonary disease,490|491|492|493|494|495|496|500|501|502|503|504|505|4168|4169|5064|5081|5088,J40|J41|J42|J43|J44|J45|J46|J47|J60|J61|J62|J63|J64|J65|J66|J67|I278|I279|J684|J701|J703,1
+7,Rheumatic disease,725|4465|7100|7101|7102|7103|7104|7140|7141|7142|7148,M05|M06|M32|M33|M34|M315|M351|M353|M360,1
+8,Peptic ulcer disease,531|532|533|534,K25|K26|K27|K28,1
+9,Mild liver disease,570|571|0706|0709|5733|5734|5738|5739|V427|07022|07023|07032|07033|07044|07054,B18|K73|K74|K700|K701|K702|K703|K709|K713|K714|K715|K717|K760|K762|K763|K764|K768|K769|Z944,1
+10,Diabetes without chronic complication,2500|2501|2502|2503|2508|2509,E100|E101|E106|E108|E109|E110|E111|E116|E118|E119|E120|E121|E126|E128|E129|E130|E131|E136|E138|E139|E140|E141|E146|E148|E149,1
+11,Diabetes with chronic complication,2504|2505|2506|2507,E102|E103|E104|E105|E107|E112|E113|E114|E115|E117|E122|E123|E124|E125|E127|E132|E133|E134|E135|E137|E142|E143|E144|E145|E147,2
+12,Hemiplegia or paraplegia,342|343|3341|3440|3441|3442|3443|3444|3445|3446|3449,G81|G82|G041|G114|G801|G802|G830|G831|G832|G833|G834|G839,2
+13,Renal disease,582|585|586|V56|5880|V420|V451|5830|5831|5832|5833|5834|5835|5836|5837|40301|40311|40391|40402|40403|40412|40413|40492|40493,N18|N19|I120|I131|N032|N033|N034|N035|N036|N037|N052|N053|N054|N055|N056|N057|N250|Z490|Z491|Z492|Z940|Z992,2
+14,"Any malignancy, including lymphoma and leukemia, except malignant neoplasm of skin",14|15|16|170|171|172|174|175|176|177|178|179|18|190|191|192|193|194|1950|1951|1952|1953|1954|1955|1956|1957|1958|200|201|202|203|204|205|206|207|208|2386,C43|C88|C0|C1|C20|C21|C22|C23|C24|C25|C26|C30|C31|C32|C33|C34|C37|C38|C39|C40|C41|C45|C46|C47|C48|C49|C50|C51|C52|C53|C54|C55|C56|C57|C58|C60|C61|C62|C63|C64|C65|C66|C67|C68|C69|C70|C71|C72|C73|C74|C75|C76|C81|C82|C83|C84|C85|C90|C91|C92|C93|C94|C95|C96|C97,2
+15,Moderate or severe liver disease,4560|4561|4562|5722|5723|5724|5725|5726|5727|5728,I850|I859|I864|I982|K704|K711|K721|K729|K765|K766|K767,3
+16,Metastatic solid tumor,196|197|198|199,C77|C78|C79|C80,6
+17,AIDS/HIV,042|043|044,B20|B21|B22|B24,6

pycomorb/common/CHARLSON_ROMANO.csv

@@ -0,0 +1,19 @@
+index,category,icd9_codes,icd10_codes,weights
+0,Age,XXXX|XXXX,,1
+1,Myocardial infarction,410|412,,1
+2,Congestive heart failure,40201|40211|40291|425|428|4293,,1
+3,Peripheral vascular disease,440|441|442|4431|4432|4433|4434|4435|4436|4437|4438|4439|4471|7854,,1
+4,Cerebrovascular disease,36234|430|431|432|433|434|435|436|4370|4371|4379|438|7814|7843|9970,,1
+5,Dementia,290|3310|3311|3312,,1
+6,Chronic pulmonary disease,4150|4168|4169|491|494|496,,1
+7,Rheumatic disease,710|714,,1
+8,Peptic ulcer disease,531|532|533|534,,1
+9,Mild liver disease,5712|5715|5716|5718|5719,,1
+10,Diabetes without chronic complication,2500|2501|2502|2503,,1
+11,Diabetes with chronic complication,2504|2505|2506|2507|2508|2509,,2
+12,Hemiplegia or paraplegia,342|344,,2
+13,Renal disease,585|586|V420|V451|V56,,2
+14,"Any malignancy, including lymphoma and leukemia",14|15|16|170|171|175|176|177|178|179|18|190|191|192|193|194|195|2OO|201|202|203|204|205|206|207|208|2730|2733|V1046,,2
+15,Moderate or severe liver disease,5722|5723|5724|4560|4561|4562,,3
+16,Metastatic solid tumor,196|197|198|199,,6
+17,AIDS/HIV,042|043|044,,6

pycomorb/common/CHARLSON_SWEDEN.csv

@@ -0,0 +1,20 @@
+index,category,icd9_codes,icd10_codes,weights
+0,Age,,YYYY|YYYY,1
+1,Myocardial infarction,,I21|I22|I252,1
+2,Congestive heart failure,,I110|I130|I132|I255|I420|I426|I427|I428|I429|I43|I50,1
+3,Peripheral vascular disease,,I70|I71|I731|I738|I771|I790|I792|K55,1
+4,Cerebrovascular disease,,G45|I60|I61|I62|I63|I64|I67|I69,1
+5,Dementia,,F00|F01|F02|F03|F051|G30|G311|G319,1
+6,Chronic obstructive pulmonary disease (COPD),,J43|J44,1
+7,Other chronic pulmonary disease,,J41|J42|J45|J46|J47|J60|J61|J62|J63|J64|J65|J66|J67|J68|J69|J70,1
+8,Rheumatic disease,,M05|M06|M123|M070|M071|M072|M073|M08|M13|M30|M313|M314|M315|M316|M32|M33|M34|M350|M351|M353|M45|M46,1
+9,(Peptic) Ulcer disease,,K25|K26|K27|K28,1
+10,Mild liver disease,,B15|B16|B17|B18|B19|K703|K73|K746|K703|K754,1
+11,Diabetes,,E100|E101|E110|E111|E120|E121|E130|E131|E140|E141,1
+12,Diabetes with end organ damage,,E102|E103|E104|E105|E107|E112|E113|E114|E115|E116|E117|E122|E123|E124|E125|E126|E127|E132|E133|E134|E135|E136|E137|E142|E143|E144|E145|E146|E147,2
+13,"Hemiplegia, tetraplegia",,G114|G80|G81|G82|G830|G831|G832|G833|G838,2
+14,Moderate or severe kidney disease,,N032|N033|N034|N035|N036|N037|N052|N053|N054|N055|N056|N057|N11|N18|N19|N250|I120|I131|Q611|Q612|Q613|Q614|Z49|Z940|Z992,2
+15,"Any malignancy, including lymphoma and leukemia",,C00|C01|C02|C03|C04|C05|C06|C07|C08|C09|C10|C11|C12|C13|C14|C15|C16|C17|C18|C19|C20|C21|C22|C23|C24|C25|C26|C30|C31|C32|C33|C34|C37|C38|C39|C40|C41|C43|C45|C46|C47|C48|C49|C50|C51|C52|C53|C54|C55|C56|C57|C58|C60|C61|C62|C63|C64|C65|C66|C67|C68|C69|C70|C71|C72|C73|C74|C75|C76|C81|C82|C83|C84|C85|C86|C88|C90|C91|C92|C93|C94|C95|C96|C97,2
+16,Moderate or severe liver disease,,R18|I850|I859|I982|I983,3
+17,Metastatic cancer,,C77|C78|C79|C80,6
+18,AIDS/HIV,,B20|B21|B22|B24|F024|O987|R75|Z114|Z219|Z711,6

pycomorb/common/CHARLSON_UK_SHMI_v1.55.csv

@@ -0,0 +1,19 @@
+index,category,icd9_codes,icd10_codes,weights
+0,Age,,YYYY|YYYY,1
+1,Acute myocardial infarction,,I21|I22|I23|I252|I258,5
+2,Congestive heart failure,,I50,13
+3,Peripheral vascular disease,,I71|I739|I790|R02|Z958|Z959,6
+4,Cerebral vascular accident,,G450|G451|G452|G454|G458|G459|G46|I60|I61|I62|I63|I64|I65|I66|I67|I68|I69,11
+5,Dementia,,F00|F01|F02|F03|F051,14
+6,Pulmonary disease,,J40|J41|J42|J43|J44|J45|J46|J47|J60|J61|J62|J63|J64|J65|J66|J67,4
+7,Connective tissue disorder,,M05|M060|M063|M069|M32|M332|M34|M353,4
+8,Peptic ulcer,,K25|K26|K27|K28,9
+9,Liver disease,,K702|K703|K717|K73|K74,8
+10,Diabetes,,E101|E105|E106|E108|E109|E111|E115|E116|E118|E119|E131|E135|E136|E138|E139|E141|E145|E146|E148|E149,3
+11,Diabetes complications,,E102|E103|E104|E107|E112|E113|E114|E117|E132|E133|E134|E137|E142|E143|E144|E147,-1
+12,Paraplegia,,G041|G81|G820|G821|G822,1
+13,Renal disease,,I12|I13|N01|N03|N052|N053|N054|N055|N056|N072|N073|N074|N18|N19|N25,10
+14,Cancer,,C0|C1|C2|C3|C4|C5|C6|C70|C71|C72|C73|C74|C75|C76|C81|C82|C83|C84|C85|C86|C88|C90|C91|C92|C93|C94|C95|C96|C97,8
+15,Severe liver disease,,K721|K729|K766|K767,18
+16,Metastatic cancer,,C77|C78|C79|C80,14
+17,AIDS/HIV,,B20|B21|B22|B23|B24|O987,2

pycomorb/common/ELIXHAUSER.csv

@@ -0,0 +1,32 @@
+index,category,icd9_codes
+0,Congestive heart failure,39891|40211|40291|40411|40413|40491|40493|428
+1,Cardiac arrhythmias,42610|42611|42613|4262|4263|4264|42650|42651|42652|42653|4266|4267|4268|4270|4272|42731|42760|4279|7850|V450|V533
+2,Valvular disease,0932|3940|3941|3942|3949|3950|3951|3952|3959|3960|3961|3962|3963|3968|3969|3970|3971|4240|4241|4242|4243|42490|42491|7463|7464|7465|7466|V422|V433
+3,Pulmonary circulation disorders,416|4179
+4,Peripheral vascular disorders,440|4412|4414|4417|4419|4431|4432|4433|4434|4435|4436|4437|4438|4439|4471|5571|5579|V434
+5,Hypertension uncomplicated,4011|4019
+6,Hypertension complicated,40210|40290|40410|40490|4051|4059
+7,Paralysis,3420|3421|3429|3430|3431|3432|3433|3434|3438|3439|3440|3441|3442|3443|3444|3445|3446|3448|3449
+8,Other neurological disorders,3319|3320|3334|3335|334|335|340|3411|3412|3413|3414|3415|3416|3417|3418|3419|3450|3451|3454|3455|3458|3459|3481|3483|7803|7843
+9,Chronic pulmonary disease,490|491|4920|4928|49300|49301|49302|49310|49311|49312|49320|49321|49322|49381|49382|49390|49391|494|495|496|500|501|502|503|504|505|5064
+10,Diabetes uncomplicated,2500|2501|2502|2503
+11,Diabetes complicated,2504|2505|2506|2507|2509
+12,Hypothyroidism,243|2440|2441|2442|2448|2449
+13,Renal failure,40311|40391|40412|40492|585|586|V420|V451|V560|V568
+14,Liver disease,07032|07033|07054|4560|4561|4562|5710|5712|5713|5714|5715|5716|5718|5719|5723|5728|V427
+15,Peptic ulcer disease excluding bleeding,53170|53190|53270|53290|53370|53390|53470|53490|V1271
+16,AIDS/HIV,042|043|044
+17,Lymphoma,200|201|2020|2021|2022|2023|2025|2026|2027|2028|2029|2030|2038|2386|2733|V1071|V1072|V1079
+18,Metastatic cancer,196|197|198|199
+19,Solid tumor without metastasis,140|141|142|143|144|145|146|147|148|149|150|151|152|153|154|155|156|157|158|159|160|161|162|163|164|165|166|167|168|169|170|171|172|174|175|179|180|181|182|183|184|185|186|187|188|189|190|191|192|193|194|195|V10
+20,Rheumatoid arthritis/collagen vascular diseases,7010|710|714|720|725
+21,Coagulopathy,286|2871|2873|2874|2875
+22,Obesity,2780
+23,Weight loss,260|261|262|263
+24,Fluid and electrolyte disorders,276
+25,Blood loss anemia,2800
+26,Deficiency anemia,2801|2802|2803|2804|2805|2806|2807|2808|2809|2810|2811|2812|2813|2814|2818|2819|2859
+27,Alcohol abuse,2911|2912|2915|2916|2917|2918|2919|3039|3050|V113
+28,Drug abuse,2920|29282|29283|29284|29285|29286|29289|2929|3040|3052|3053|3054|3055|3056|3057|3058|3059
+29,Psychoses,295|296|297|298|2991
+30,Depression,3004|30112|3090|3091|311