User Tools

Site Tools


projects:workgroups:nlp-wg

Differences

This shows you the differences between two versions of the page.

Link to this comparison view

Both sides previous revision Previous revision
Next revision
Previous revision
projects:workgroups:nlp-wg [2021/02/10 15:22]
firat
projects:workgroups:nlp-wg [2023/05/10 01:37] (current)
vipina [Ongoing Projects]
Line 5: Line 5:
 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. 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 ====+==== Workgroup ​Lead ====
  
-Hua Xu+[[https://​www.ohdsi.org/​who-we-are/​collaborators/​hua-xu/​|Hua Xu]]\\
  
-==== Project Co-leads ==== 
  
-Jon Duke, Nigam Shah, Noemie Elhadad 
  
-==== Plan ====+==== Project Coordinator ​====
  
-  - IRB for use of clinical text  + [[vipina.kuttichikeloth@yale.edu | Vipina KKeloth ]]
-  - Clinical text data storage and representation schema  +
-  - NLP tools/​pipelines for ETL  +
-  - Use cases, e.g, phenotyping for cohort selection using NLP outputs+
  
-==== Ongoing Projects ​====+==== OHDSI NLP WG Monthly Meeting ​==== 
 +**When:** Second Wednesday of every month at 1 PM - 2 PM CT
  
-===2018===+**Where:** [[https://​teams.microsoft.com/​dl/​launcher/​launcher.html?​url=%2F_%23%2Fl%2Fmeetup-join%2F19%3Acd9841fec6df4f3d8eb6a6bf49ea305f%40thread.tacv2%2F1610663053273%3Fcontext%3D%257b%2522Tid%2522%253a%2522a30f0094-9120-4aab-ba4c-e5509023b2d5%2522%252c%2522Oid%2522%253a%252200626e72-b11c-482a-9dc4-d8eff51c5e5f%2522%257d%26anon%3Dtrue&​type=meetup-join&​deeplinkId=42431bac-788d-4a7b-8531-5eb2612224a6&​directDl=true&​msLaunch=true&​enableMobilePage=true&​suppressPrompt=true|Click here to join the meeting]]
  
-  ​Rules for defining term_exists – led by Stephane Meystre ​COMPLETED +**Monthly Meeting:** Upcoming ​May 9, 2023 
-  - Mapping of CUIs to standard terminology – Juan Banda COMPLETED ​[[https://​github.com/​thepanacealab/​OHDSIananke]] + 
-  ​Mapping ​of Note Types to LOINC/​standard vocabulary –Karthik NatarajanRuth ReevesJon Duke and Hua Xu– Report type list discussion +**Agenda** 
-  - Landscape Analysis of section identifier systems ​and proposal of standard terminology for use – Hua XuKarthik Natarajan + 
-  - Examples and rules for term_temporal – led by George Hripsack (Sunny) ​ + 1) Presentation ​**Nic Dobbins** (Principal Solutions Architect at UW Medicine Research IT; PhD Candidate in biomedical informatics at the University of Washington)\\ 
-  - Standardization of term_modifiers and values – Hua Xu+**Title:** LeafAI: query generator for clinical cohort discovery rivaling a human programmer\\ 
 +**Abstract:​** ​ Identifying study-eligible patients within clinical databases is a critical step in clinical research. However, accurate query design typically requires extensive technical and biomedical expertise. We sought ​to create a system capable of generating data model-agnostic queries while also providing novel logical reasoning capabilities for complex clinical trial eligibility criteria. We incorporated hybrid deep learning and rule-based modules for these, as well as a knowledge base of the Unified Medical Language System (UMLS) and linked ontologiesTo enable data-model agnostic query creation, we introduce a novel method for tagging database schema elements using UMLS concepts. To evaluate our system, called LeafAI, we compared the capability ​of LeafAI ​to a human database programmer to identify patients who had been enrolled in 8 clinical trials conducted at our institution. We measured performance by the number of actual enrolled patients matched by generated queries. LeafAI matched a mean 43% of enrolled patients with 27,225 eligible across 8 clinical trialscompared to 27% matched ​and 14,587 eligible in queries by human database programmer. The human programmer spent 26 total hours crafting queries compared to several minutes by LeafAI. Finallywe introduce a novel multimodal user interface for interaction with LeafAI.\\ 
 + 
 +2) Updates on the progress of ongoing studies 
 +  - SDoH 
 +  - Psychiatry 
 +  - Oncology 
 +3) NLP book chapter 
 + 
 + 
 +==== Ongoing Projects ====
  
-===2019===+  * Note type normalization 
 +  * Social Determinants of Health 
 +  * Psychiatry - NLP for capturing administration of neuropsychiatric scales and their scores 
 +  * Oncology - NLP for getting oncology data using Tumor Reg data as a gold standard for assessing the information obtained through the NLP algorithm 
 +  * Book of OHDSI NLP Chapter
  
-  - Mapping of Note Types to LOINC/​standard vocabulary –Karthik Natarajan, Ruth Reeves, Jon Duke and Hua Xu– Report type list discussion +==== Past Projects ====
-  - Landscape Analysis of section identifier systems and proposal of a standard terminology for use – Hua Xu, Karthik Natarajan +
-  - Examples and rules for term_temporal – led by George Hripsack (Sunny)  +
-  - Standardization of term_modifiers and values – Hua Xu +
-  - Evaluate and revise textual CDM tables by sharing practical issues and lessons learnt during ETL for processing textual data into CDM, Usecases – Ruth Reeves,  +
-  - Develop tools (within Atlas) to facilitate uses of NLP data for cohort building/​phenotyping : Collaborate with eMERGE consortium:​ +
-  - Conduct cross-site studies that use textual data +
-  - Continue developing other NLP resources+
  
 +  * Note_NLP table
 +  * COVID-19 testing normalization (TestNorm)
 +  * Note type
 +  * NLP tools: NLP Wrappers; THEIA; Ananke
 ==== Participants ==== ==== Participants ====
  
-  * Hua Xu +noncomprehensive list of participants:​ [[ Click here ]]
-  * 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 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 +==== Upcoming Meeting Dates (2023) ==== 
-  * December ​9th, 2020+ 
 +  * June 14 
 +  * July 12 
 +  * August 9 
 +  * September 13 
 +  * October 11 
 +  ​* November ​8 
 +  * December ​13
  
 ==== Repository ==== ==== Repository ====
Line 125: Line 68:
   * OHDSIananke [[https://​github.com/​thepanacealab/​OHDSIananke]]   * OHDSIananke [[https://​github.com/​thepanacealab/​OHDSIananke]]
  
-==== 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 
  
-{{:​projects:​workgroups:​16ohdsi_nlp_schema_updated.pdf|}} 
  
-[[https://​docs.google.com/​document/​d/​1ykYVJTQ5MuI7eh_Nk7xzt44EzNjVs71nq2LIsC_RlOg/​edit]] 
  
 +==== Past WG meetings (Agenda/​Minutes/​Recordings) ====
 +**2023**\\
 +  -[[WG_meeting_may_10_2023]]
 +  -[[WG_meeting_apr_12_2023]]
 +  -[[WG_meeting_mar_08_2023]]
 +  -[[WG_meeting_feb_08_2023]]
 +  -[[WG_meeting_jan_11_2023]]
  
 +**2022**\\
 +  -[[WG_meeting_dec_14_2022]]
 +  -[[WG_meeting_nov_09_2022]]
 +  -[[WG_meeting_sep_14_2022]]
 +  -[[WG_meeting_aug_10_2022]]
 +  -[[WG_meeting_jun_08_2022]]
 +  -[[WG_meeting_may_11_2022]]
 +  -[[WG_meeting_apr_13_2022]]
 +  -[[WG_meeting_mar_09_2022]]
 +  -[[WG_meeting_feb_09_2022]]
 +  -[[WG_meeting_jan_12_2022]]
  
-==== Start Date ====+**2021**\\ 
 +  -[[WG_meeting_dec_08_2021]] 
 +  -[[WG_meeting_nov_10_2021]] 
 +  -[[WG_meeting_oct_13_2021]] 
 +  -[[WG_meeting_sep_08_2021]] 
 +  -[[WG_meeting_aug_11_2021]]
  
-August 2015 +**2019**\\ 
-==== WG Agenda/​Minutes/​Recordings ====+  ​-[[WG_meeting_10092019]] 
 +  -[[WG_meeting_09112019]] 
 +  -[[WG_meeting_08142019]] 
 +  -[[WG_meeting_07102019]] 
 +  -[[WG_meeting_05082019]] 
 +  -[[WG_meeting_04102019]] 
 +  -[[WG_meeting_03132019]] 
 +  -[[WG_meeting_02132019]] 
 +  -[[WG_meeting_01092019]] 
 +**2018**\\ 
 +  -[[WG_meeting_11142018]] 
 +  -[[WG_meeting_09122018]] 
 +  -[[WG_meeting_06132018]] 
 +  -[[WG_meeting_05092018]] 
 +  -[[WG_meeting_04142018]] 
 +  -[[WG_meeting_03142018]] 
 +  -[[WG_meeting_02142018]] 
 +  -[[WG_meeting_01102018]]
  
-  -[[projects:​workgroups:​minutes|WG_meeting_10072015]] +**2017**\\
-  -[[WG_meeting_11042015]] +
-  -[[WG_meeting_01062016]] +
-  -[[WG_meeting_02032016]] +
-  -[[WG_meeting_03092016]] +
-  -[[WG_meeting_04132016]] +
-  -[[WG_meeting_04202016]] +
-  -[[WG_meeting_06142017]] +
-  -[[WG_meeting_07122017]] +
-  -[[WG_meeting_09132017]] +
-  -[[WG_meeting_10112017]]+
   -[[WG_meeting_12122017]]   -[[WG_meeting_12122017]]
-  -[[WG_meeting_01102018]] +  -[[WG_meeting_10112017]] 
-  -[[WG_meeting_02142018]] +  -[[WG_meeting_09132017]] 
-  -[[WG_meeting_03142018]] +  -[[WG_meeting_07122017]] 
-  -[[WG_meeting_04142018]] +  -[[WG_meeting_06142017]]
-  -[[WG_meeting_05092018]] +
-  -[[WG_meeting_06132018]] +
-  -[[WG_meeting_09122018]] +
-  -[[WG_meeting_11142018]] +
-  -[[WG_meeting_01092019]] +
-  -[[WG_meeting_02132019]] +
-  -[[WG_meeting_03132019]] +
-  -[[WG_meeting_04102019]] +
-  -[[WG_meeting_05082019]] +
-  -[[WG_meeting_07102019]] +
-  -[[WG_meeting_08142019]] +
-  -[[WG_meeting_09112019]] +
-  -[[WG_meeting_10092019]] +
-==== Meetings ====+
  
-Schedule: Second Wednesday of every month at 2pm Eastern Time +**2016**\\ 
-     +  ​-[[WG_meeting_04202016]] 
-The next meeting will be on October 9th, 2019 +  ​-[[WG_meeting_04132016]] 
-     +  ​-[[WG_meeting_03092016]] 
-Meetings in 2020: +  ​-[[WG_meeting_02032016]] 
-     +  ​-[[WG_meeting_01062016]] 
-  ​March 11 + 
-  ​April 8 +**2015**\\ 
-  ​* May 13 +  ​-[[WG_meeting_11042015]] 
-  ​* June 10 +  -[[projects:​workgroups:minutes|WG_meeting_10072015]]
-  ​* July 8 +
-  ​* August 12 +
-  ​* September 9 +
-  October 14 +
-  ​* November 11 +
-  ​* December 9 +
-     +
-Call-in+
  
-OHDSI NLP WG+===== Microsoft Teams meeting =====
  
-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**
  
-Join on your computer or mobile app 
  
-Click the link below to join the meeting ​+[[https://​teams.microsoft.com/​dl/​launcher/​launcher.html?​url=%2F_%23%2Fl%2Fmeetup-join%2F19%3Acd9841fec6df4f3d8eb6a6bf49ea305f%40thread.tacv2%2F1610663053273%3Fcontext%3D%257b%2522Tid%2522%253a%2522a30f0094-9120-4aab-ba4c-e5509023b2d5%2522%252c%2522Oid%2522%253a%252200626e72-b11c-482a-9dc4-d8eff51c5e5f%2522%257d%26anon%3Dtrue&​type=meetup-join&​deeplinkId=42431bac-788d-4a7b-8531-5eb2612224a6&​directDl=true&​msLaunch=true&​enableMobilePage=true&​suppressPrompt=true|Click here to join the meeting]]
  
-[[https://teams.microsoft.com/dl/​launcher/​launcher.html?​url=%2F_%23%2Fl%2Fmeetup-join%2F19%3Acd9841fec6df4f3d8eb6a6bf49ea305f%40thread.tacv2%2F1610663053273%3Fcontext%3D%257b%2522Tid%2522%253a%2522a30f0094-9120-4aab-ba4c-e5509023b2d5%2522%252c%2522Oid%2522%253a%252200626e72-b11c-482a-9dc4-d8eff51c5e5f%2522%257d%26anon%3Dtrue&​type=meetup-join&​deeplinkId=42431bac-788d-4a7b-8531-5eb2612224a6&​directDl=true&​msLaunch=true&​enableMobilePage=true&​suppressPrompt=true]]+[[https://aka.ms/JoinTeamsMeeting|Learn More]]
  
  
projects/workgroups/nlp-wg.1612970574.txt.gz · Last modified: 2021/02/10 15:22 by firat