Filter the list of jargon to remove any non-medical terms

higgood / med-jargon-explain-inator

Forking this so that we can associate tasks with the relevant repo. The ownership of this project belongs to all team members, and not to HIGG. HIGG is only sponsoring to facilitate project management.

2 stars 1 forks source link

Filter the list of jargon to remove any non-medical terms #10

Closed jonjiang1 closed 5 months ago

jonjiang1 commented 6 months ago

Note: Can be done either manually or through prompt-tuning

AC:

[x] Document the data sources (for definitions) and steps for processing it in one of the MD files.
[x] Alter committed list to remove non-medical jargon
[x] List updated in the repo
[x] Acronyms should be preserved with their full expansion in a separate file

Potentially useful resource: giant list of medical abbreviations: https://github.com/imantsm/medical_abbreviations

wammar commented 6 months ago

Melody's update: Now using a variety of medical references to check each term in the list of ~1700 terms, including abbreviations. About 150 lines were excluded.

The source of this list is the April 24, 2024 version of this file: https://medlineplus.gov/xml/mplus_topics_2024-05-03.xml

wammar commented 6 months ago

Emma is almost done with her part of this. The remaining piece is to add the list of categories we're filtering on.

Melody is actively working on this.