Skip to content

Transformer based NLP for extracting SNOMED-CT from Electronic Health Records.

Notifications You must be signed in to change notification settings

fcggamou/ML_SnomedTermsNLP

Repository files navigation

Codical

Transformers powered REST API for encoding EHRs into SNOMED-CT medical standard terms.

IMAGE ALT TEXT HERE

  • Encode arbitrarely long EHRs written in natural language into SNOMED-CT formal concept model expressions.
  • Identify terms and relations between them, including qualifiers, observable entities, body structures, findings, substances, numeric values and more.
  • Achieved 0.91+ F1-Score on novel spanish EHR texts from a variety of medical specialties.
  • State of the art NLP techniques based on Transformers like Semantic Textual Similarity and relations extraction.
  • Robust encoding of terms regardless of typos, acronyms or abbreviations.
  • Fully exposed as REST API.

About

Transformer based NLP for extracting SNOMED-CT from Electronic Health Records.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages