Hua Xu, Jon Duke, George Hripcsak, Karthik Natarajan, Anupama Gururaj, Mark Khayter, Min Jiang, Alexandre Yahi, Noemie Elhadad, Juan M Banda, Olga Patterson, Lian
Agenda
Minimal Model Presentation – Alex
Note-type mapping Presentation – Karthik
Share existing ontologies from Vanderbilt (Hua) and Regenstrief (Jon)
Share strategies for combining data from different searches – Jon
Report on WG for commenting – Hua
Wrappers for cTAKES and Metamap – Min
Improvements to search engine set up using MT samples – Min
Textual Data Representation – Discussion
Goals of 2016
Change of meeting time
Minutes
Minimal model presentation - Alex
the model is based on the SHARE-N model and adapted to the current data structure. This model incorporates other semantic types and all of the modifiers are not available in cTAKES yet.
the notes were processed from eMERGE cohort at Columbia with about 60,000 notes encompassing 1700 patients. The original patient number was 3200.
In theory, a set containing the combination of minimal modifiers can be generated. Practically, can we trust the data enough to add it into OHDSI tables? - only highest confidence data (with maximum PPV) should be added to the tables.
Next steps:
Look at the note sections to determine the errors.
Work with Sunny to generate the NLP outputs for the phenotyping data
Evaluate by comparisons with structured data
Make the system more robust
Generate a protocol and/or annotation guidelines
Share the data as a Gold standard with manually annotated CUIs
Alex's script is to be tried on different datasets and evaluated across notes from different institutions
Identify minimal set of notes to work with when recommending to the OHDSI community
Aggregate and share note-type metadata from various sources: Karthik
LOINC note type mapping would be a very useful resource. We should generate hierarchical representation of note-types as an ontology. Karthink will present his work to date at the next meeting.
Existing ontology for note types to be shared : Vanderbilt (Hua) and Regenstrief (Jon)
Simple search set up for MT samples: MinPresentation
Presentation
The interface being developed should present a summary with visualization for patients/notes.
We will add Boolean query options to improve the search
We will implement a Ranking algorithm
Assign fake patient ID's to the notes to generate the visualization portion.
Generate a program like Circe to define the patient cohort
Next steps: How to move the data from textual searches stored in a table outside of OMOP to the OMOP?
Structured searches from CDW and textual searches can be combined using existing strategies. Jon will share the slides of his presentation on combining data from different searches
Run NLP on the ElasticSearch to extract information
Wrappers for cTAKES and Metamap
Report on the WG - Hua will generate and share with the members for comments
The best ways to represent textual data need to be determined
Action Items
Minimal Model Presentation - Alex
Note-type mapping Presentation - Karthink
Share existing ontologies from Vanderbilt (Hua) and Regenstrief (Jon)
Share strategies for combining data from different searches - Jon
Report on WG for commenting - Hua
Wrappers for cTAKES and Metamap - Min
Improvements to search engine set up using MT samples - Min
Textual Data Representation - Discussion
projects/workgroups/wg_meeting_02032016.1457387628.txt.gz · Last modified: 2016/03/07 21:53 by anu_gururaj