8000 GitHub - Mikaela-G/Clinical_NLP_575: Extracts medical concepts (problems, treatments, tests) from unstructured discharge summaries and progress notes.
[go: up one dir, main page]
More Web Proxy on the site http://driver.im/
Skip to content

Extracts medical concepts (problems, treatments, tests) from unstructured discharge summaries and progress notes.

Notifications You must be signed in to change notification settings

Mikaela-G/Clinical_NLP_575

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

35 Commits
 
 
 
 
 
 

Repository files navigation

Clinical_NLP_575 - 2010 i2b2 Concept Extraction Task

Abstract

This project reproduces Gurulingappa et al.'s (2010) challenge paper for the 2010 i2b2 Concepts Task. In order to extract medical concepts (problems, treatments, tests) from unstructured discharge summaries and progress notes, we train a CRF on various combinations of features (morphological, context-based, grammatical, and MetaMap-based) extracted from the data using sklearn-crfsuite in Python. Our data was downloaded from the DMBI Data Portal and consists of 170 training documents and 256 test documents from Partners Healthcare and Beth Israel Deaconess Medical Center. Our usage of MetaMapLite is courtesy of the U.S. National Library of Medicine.

Contributors

  • Mikaela Guerrero
  • Nitya Sampath

About

Extracts medical concepts (problems, treatments, tests) from unstructured discharge summaries and progress notes.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published
0