User Tools

Site Tools


projects:workgroups:wg_meeting_11042015

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
Last revision Both sides next revision
projects:workgroups:wg_meeting_11042015 [2015/11/30 16:38]
anu_gururaj
projects:workgroups:wg_meeting_11042015 [2015/11/30 17:20]
anu_gururaj
Line 16: Line 16:
 ===Minutes=== ===Minutes===
  
 +  - Presentation {{:​projects:​workgroups:​nlp_wg_meeting_11042015_final.pdf|}}
   -Updates from Annual meeting   -Updates from Annual meeting
      * Extensive interest from the OHDSI community with reference to the text processing aspect. During the meeting, suggestions for improvements in the current projects were received.      * Extensive interest from the OHDSI community with reference to the text processing aspect. During the meeting, suggestions for improvements in the current projects were received.
Line 28: Line 29:
   -NLP tools/​pipelines for ETL   -NLP tools/​pipelines for ETL
     * The plan is to develop a set of wrappers for multiple NLP tools (currently cTAKES and MetaMap) for conversion of output to the OHDSI textual data schema.     * The plan is to develop a set of wrappers for multiple NLP tools (currently cTAKES and MetaMap) for conversion of output to the OHDSI textual data schema.
-    * In order to get an idea of the updates in cTAKESneed to invite Guergana Savova to present and do a demo of cTAKES during the January call.+    * In order to get an idea of the updates in cTAKESneed to invite Guergana Savova to present and do a demo of cTAKES during the January call.
     * In order to prioritize the work, focus on positive concepts first for high confidence extraction of NER from text.     * In order to prioritize the work, focus on positive concepts first for high confidence extraction of NER from text.
   -Use cases, e.g, phenotyping for cohort selection using NLP outputs   -Use cases, e.g, phenotyping for cohort selection using NLP outputs
 +    * To define the syntax for storing phenotypes, two aspects can be considered:
 +           - set of data elements or features on which an algorithm functions
 +           - formulation of the phenotype definition
 +    * In order to represent the NLP output, query-based phenotyping will be the first focus of the group.
 +    * For machine-learning based algorithms, the NLP output will be accessed outside of the CDM
 +    * Is ElasticSearch a good first step in this area? ES should be considered here as a tool more for cohort building and selection rather than phenotyping. For this purpose, it is a good starting point.
 +    * Finding patients for clinical trials will be used as a usecase here. The ES could serve as an explorer for feature selection in the phenotyping process.
 +    * Action item: Simple search set up for MT samples by next meeting by Min.
 +    * Use MIMICII and MIMICIII as demo  datasets for the tools being developed by the group
   -Discussion   -Discussion
projects/workgroups/wg_meeting_11042015.txt ยท Last modified: 2016/01/06 20:47 by anu_gururaj