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. The note table in the OMOP CDM has a note type field with about 10 or so note types
   7. Next steps:
      1. Comparison of what aspects of LOINC is being used across different institutions.
      2. One of the deliverable is to build a system that can map the institutional note type to the LOINC note types.
      3. Update the note type field of the note table in OMOP CDM. Should a subset of LOINC document types be used for this purpose? this would depend on the real-world data from various institutions.
      4. Ontologies such as CP, ICD-9 etc. that include more clinical terminologies should also be explored.
2. existing ontologies from Vanderbilt - Hua - document-types.zip

1. Suggestion for OMOP model regarding NLP output - Hua/Noemie
2. 2016 OHDSI symposium - plan is to present the search engine, medical record viewer (a chart review tool) from Scott; any other suggestions?
3. Share strategies for combining data from different searches - Jon
4. Wrappers for cTAKES and Metamap - Min
5. Improvements to search engine set up using MT samples - Min
6. Textual Data Representation - Discussion
7. NLP system evaluation across different sites - Discussion