No announcement yet.
  • Filter
  • Time
  • Show
Clear All
new posts

  • Categorizing ICD-10 codes into major categories


    I work with ICD-10 codes regularly. I'm currently involved in a project where several thousand ICD codes are relevant. I use the icd10cm commands for generating category and description, but I'm hoping to find some higher-level categorization schema - like at the level "Diabetes", "Heart disease", "STDs", etc. E.g., the current icd10 cm reduces it to "Type 1 diabetes mellitus", "Type 2 diabetes mellitus", "Other specified diabetes mellitus", "Diabetes mellitus due to underlying condition", etc., whereas I'd prefer just a single category called "Diabetes."

    I've been doing manual work with it using string matches and such, with validation after, but it's a rather lengthy and involved process. I was wondering if anyone has found either any Stata code for quickly reducing it to major categories or knows of any datasets that match the ICD codes to these more top-level type of categories.

  • #2
    The broad categories are defined in the following WHO page.
    Last edited by Andrew Musau; 29 Apr 2019, 15:20.


    • #3
      Also, an organization in the US called the Chronic Conditions Warehouse maintains definitions (in ICD-9 and -10) for a number of chronic conditions.

      I know you already at least skimmed the manual for the icd10 commands, but just to remind you, the icd10 can also generate condition flags, and they can accept a code range as an argument, rather than inputting each code. With that sort of operation, you need to be aware of potential exceptions in code ranges, e.g. for schizophrenia, the definition includes all codes from F20.0 to F25.9, and it includes the non-adjacent codes F06.0 and F06.2.

      If you want something more specific, you'll have to explain what sort of groupings you want.
      Please use the code delimiters to show code and results - use the # button on the formatting toolbar, between the " (double quote) and <> buttons.

      Please use the command -dataex- to show a representative sample of data; it is installed already if you have Stata 14.2 or 15.1, else you can install it by typing

      ssc install dataex