Giter Club home page Giter Club logo

Comments (4)

mart-r avatar mart-r commented on September 25, 2024

Hi,

The SNOMED preprocessing procedure expects that you pass it one of the following:

  1. The folder to the SNOMED release
  • E.g /path/to/SnomedCT_InternationalRF2_PRODUCTION_20230731T120000Z
  1. The folder that contains multiple SNOMED releases
  • E.g the parent folder
  • In this case, the multiple releases will be combined
  • All folders that contain "SnomedCT" will be considered

If this is a UK extension or a UK Drug extension, you would also need to specify uk_ext=True or uk_drug_ext=True in the constructor, respectively.
Other flavours of SNOMED are not currently fully supported. The naming conventions of files differ somewhat between different flavours which is why we need to know which one you're attempting to use.

The other assumption is that the files in the release folders are in the standard folder structure (e.g SnomedCT_InternationalRF2_PRODUCTION_20230731T120000Z/Snapshot/Terminology/sct2_Concept_Snapshot_INT_20230731.txt and similar files exist).

So the error you've received means that the preprocessor was unable to figure out the Snomed version for one of the releases you're trying to work with. This could be because you didn't specify the correct flavour. Or it could be that we don't support the flavour you're trying to use. Or it could be that the file structure differs from the default. Or perhaps the parent folder had a folder that contained "SnomedCT" within it that didn't correspond to a Snomed release.

What Snomed release are you trying to use exactly?

from medcat.

saskia-lawson-tovey avatar saskia-lawson-tovey commented on September 25, 2024

Hi,

I'm using the most recent release (38.0) of the SNOMED CT UK Monolith Edition, RF2: Snapshot from NHS TRUD.

I've followed the instructions here: https://htmlpreview.github.io/?https://github.com/CogStack/MedCATtutorials/blob/main/notebooks/specialised/Preprocessing_SNOMED_CT.html

I skipped the load the data section as the SNOMED file isn't zipped.

Load the data

Assign a path to the zipped SNOMED CT release download. (skip this step if the folder is not zipped)

snomed_path = "SnomedCT_InternationalRF2_PRODUCTION_20210131T120000Z.zip" # Enter your zipped Snomed folder here
!unzip snomed_path

Preprocess the release for MedCAT

Initialise

snomed_filename = "SnomedCT_InternationalRF2_PRODUCTION_20210131T120000Z" # The unzippedSNOMED CT folder
snomed = Snomed(snomed_filename)

Skip this step if your version of snomed is not the UK extension released >2021.

Note: this step will only work with MedCAT v1.2.7+

snomed.uk_ext = True

from medcat.

mart-r avatar mart-r commented on September 25, 2024

Unfortunately we don't currently fully support the Monolith edition. Again, its file naming conventions are different from the other releases.

I would recommend using the UK Clinical Edition and/or the Drug extension.

With that said, if you do wish to use the Monolith edition, the changes to the concept snapshot should be doable on your side.
I.e you should be able to change the concept_snapshot = "sct2_Concept_MONOSnapshot_GB" in code. You could copy the code from the repo and change this yourself.
EDIT: The above has not been tested. There may be other changes to the release as well.

PS:
Supporting as well as making it easier for others to use any edition is on our radar. But there is no ETA on this on our side, unfortunately.

from medcat.

saskia-lawson-tovey avatar saskia-lawson-tovey commented on September 25, 2024

Noted - I'll try with the clinical edition.
Thanks for your help :)

from medcat.

Related Issues (20)

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. 📊📈🎉

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.