User Tools

Site Tools


projects:workgroups:nlp-wg

This is an old revision of the document!


OHDSI Natural Language Processing Working Group

Objective

The primary goal of the NLP working group is to promote the use of textual information from Electronic Health Records (EHRs) for observational studies under the OHDSI umbrella. To facilitate this objective, the group will develop methods and software that can be implemented to utilize clinical text for studies by the OHDSI community.

Project Lead

Hua Xu

Project Co-leads

Jon Duke, Nigam Shah, Noemie Elhadad

Plan

  1. IRB for use of clinical text
  2. Clinical text data storage and representation schema
  3. NLP tools/pipelines for ETL
  4. Use cases, e.g, phenotyping for cohort selection using NLP outputs

Ongoing Projects

2018

  1. Rules for defining term_exists – led by Stephane Meystre - COMPLETED
  2. Mapping of CUIs to standard terminology – Juan Banda - COMPLETED - https://github.com/thepanacealab/OHDSIananke
  3. Mapping of Note Types to LOINC/standard vocabulary –Karthik Natarajan, Ruth Reeves, Jon Duke and Hua Xu– Report type list discussion
  4. Landscape Analysis of section identifier systems and proposal of a standard terminology for use – Hua Xu, Karthik Natarajan
  5. Examples and rules for term_temporal – led by George Hripsack (Sunny)
  6. Standardization of term_modifiers and values – Hua Xu

2019

  1. Mapping of Note Types to LOINC/standard vocabulary –Karthik Natarajan, Ruth Reeves, Jon Duke and Hua Xu– Report type list discussion
  2. Landscape Analysis of section identifier systems and proposal of a standard terminology for use – Hua Xu, Karthik Natarajan
  3. Examples and rules for term_temporal – led by George Hripsack (Sunny)
  4. Standardization of term_modifiers and values – Hua Xu
  5. Evaluate and revise textual CDM tables by sharing practical issues and lessons learnt during ETL for processing textual data into CDM, Usecases – Ruth Reeves,
  6. Develop tools (within Atlas) to facilitate uses of NLP data for cohort building/phenotyping : Collaborate with eMERGE consortium:
  7. Conduct cross-site studies that use textual data
  8. Continue developing other NLP resources

Participants

  • Hua Xu
  • Anupama Gururaj
  • Nigam Shah
  • Noemie Elhadad
  • Jon Duke
  • Alexandre Yahi
  • Thomas Ginter
  • Olga Patterson
  • George Hripsack
  • Vojtech Huser
  • Mark Khayter
  • Karthik Natarajan
  • Min Jiang
  • Scott DuVall
  • Abraham Hartzema
  • David Sontag
  • Arnab Bose
  • Lian Hu
  • Jan A Kors
  • J van Der Lei
  • Peter R Rijnbeek
  • Vivienne Zhu
  • Bob Patterson
  • Michael Gurley
  • Xiaoling Chen
  • Hongfang Liu
  • Hong Yu
  • Stephane Meystre
  • Timothy Miller
  • Wendy Chapman
  • Feifan Liu
  • Paris Nicolas
  • Mark Dredze
  • Masoud Rouhizadeh
  • Malcolm McRoberts
  • Nishanth Parameshwar Pavinkurve
  • Carol Friedman
  • Miao Chen
  • Jianlin Shi
  • Vassilis Koutkias
  • Dan Schlegel
  • Mark V Mai
  • Todd Lingren
  • Jose Posada
  • Andrew E Williams
  • Vignesh Srinivasan
  • Yuan Luo
  • Kelly Peterson
  • Xiao Dong
  • Ning Shang
  • Nishanth Parameshwar Pavinkurve
  • Jessie Tenenbaum
  • Elizabeth Marshall
  • Kathleen Nogueira
  • Noa Palmon
  • Chris Ryan
  • Danielle Bitterman
  • Jimyung Park
  • Kate Weber
  • Alexander Sivura
  • Patrick Alba
  • Tarun
  • Xi Yang
  • Meliha Yetisgen
  • T.M. Seinen
  • Bian,Jiang
  • Xiyu Ding
  • Georgina Kennedy
  • Yaoyun Zhang
  • Rui Zhang
  • Paul Heider

Upcoming Meeting Dates

  • November 11th, 2020
  • December 9th, 2020

Repository

Proposal for concepts detected by NLP

create a new table called NOTE_NLP with the following columns

  • note_id (integer) links to NOTE.note_id (foreign key)
  • note_concept_id (integer) concept_id of a term found in the note
  • certainty (real number 0-100) how certain is the NLP pipeline that this concept is present in the note
  • offset position of where in the note was the concept detected
  • span (integer) number of characters from offset where the concept was detected
  • negation_flag (string of length 1 (or boolean)) indicates if the concept is negated

16ohdsi_nlp_schema_updated.pdf

https://docs.google.com/document/d/1ykYVJTQ5MuI7eh_Nk7xzt44EzNjVs71nq2LIsC_RlOg/edit

Start Date

August 2015

WG Agenda/Minutes/Recordings

Meetings

Schedule: Second Wednesday of every month at 2pm Eastern Time

The next meeting will be on October 9th, 2019

Meetings in 2021:

  • February 10
  • March 10
  • April 14
  • May 12
  • June 9
  • July 14
  • August 11
  • September 8
  • October 13
  • November 10
  • December 8

Call-in:

OHDSI NLP WG

Occurs the second Wednesday of every month effective 5/8/2019 from 1:00 PM to 2:00 PM, (UTC-06:00) Central Time (US & Canada)

Microsoft Teams meeting

Join on your computer or mobile app

Click here to join the meeting

projects/workgroups/nlp-wg.1612972252.txt.gz · Last modified: 2021/02/10 15:50 by firat