Hua Xu, Jon Duke, George Hripcsak, Anupama Gururaj, Min Jiang, Alexandre Yahi, Noemie Elhadad, Olga Patterson, Scott DuVall, Lian Hu, Thomas Ginter

nlp_wg_meeting_04132016.pdf

1. Discussion of NLP_TERM_TABLE – Hua/Noemie
2. Share existing ontologies Regenstrief (Jon)
3. Share strategies for combining data from different searches – Jon
4. Improvements to search engine set up using MT samples – Min
5. Wrappers for cTAKES and Metamap – Min

1. NLP term table presentation – Noemie nlp_wg_meeting_04132016.pdf
   1. The note type concept ID is not very useful and should be replaced with a more standardized terminology such as LOINC ontology
   2. Replace the current single element with 5 elements (pls see presentation for details)
   3. Extend the note source value field to 255 varchar
   4. In terms of the type of service, LOINC ontology is very complicated, A flat architecture would be better for the current purpose. Comparison with another institution should be carried out.
   5. Date is to be added to the table -
   6. Include all NLP concepts into one table called Note_NLP/Term_mention Table. This is an intermediate table that can then be linked to other tables in the CDM such as concept
   7. Next steps:
      1. Schedule another meeting in the following week to continue the discussion

1. Meeting next week to continue discussion
2. Share strategies for combining data from different searches - Jon
3. Wrappers for cTAKES and Metamap - Min
4. Improvements to search engine set up using MT samples - Min
5. Textual Data Representation - Discussion
6. NLP system evaluation across different sites - Discussion