OHDSI Home | Forums | Wiki | Github

General Guidance for deriving clinical tables from NLP tables: [note + note_nlp] → [condition_occurance + drug_exposure + etc]

(Kieran Mace) #1

Hi there, I’m looking for some general guidance on where to get started.

I have a data set, that contains EHR text from patients clinical notes, which has:

  1. Gone through named entity (term) recognition
  2. Terms have been associated with a concept in OMOP vocabulary
  3. Term modifiers (such as certainty, timing, etc) have been identified for each entity
  4. stored all this data in the note and note_nlp tables

Now, I would like to use this data to derive entries into the standard clinical tables, such as condition_occurence, drug_exposure, measurement, and procedure_occurance.

My questions are:

  • How might I get started? Has the OMOP community developed methodologies to derive clinical tables from entities?
  • Is there any literature or tutorials you can point me to, in order to become familiar with the field (if such a field exists)
  • Are there any terms that I should be googling? Am I using the correct terms above?