Clinical pipeline with multiple dictionaries

[Masoud Rouhizadeh <mr...@jhu.edu>]

Dear all,

I'm using cTAKES default clinical pipeline with the following dictionary to extract the following:

- Signs and symptoms (Human Phenotype Ontology)
- Disorders and disease (ICD 10 CM)
- Medications (RxNorms)

Given the processing time of the annotation steps, it would be best if I don't have to run cTAKES clinical pipeline three times for each of the dictionaries.

What would be your recommendation? Does merging all of the dictionaries make sense? If not, is there a way to run the fast dictionary lookup three times (for each dictionary) in the same pipeline and collect CUIs?

Thanks,
Masoud

Re: Clinical pipeline with multiple dictionaries

[Remy Sanouillet <re...@foreseemed.com>]

Sure thing, Masoud!

We have done just that. No need to merge the dictionaries. You only need to
merge your dictionary config files into one and have the resulting XML file
point to your three dictionaries.
Then a single run will process the documents and collect all the data.

*Rémy Sanouillet*
NLP Engineer
remys@foreseemed.com <xx...@foreseemed.com>


[image: cid:347EAEF1-26E8-42CB-BAE3-6CB228301B15]
ForeSee Medical, Inc.
12555 High Bluff Drive, Suite 100
San Diego, CA 92130

NOTICE: This e-mail message and all attachments transmitted with it are
intended solely for the use of the addressee and may contain legally
privileged and confidential information. If the reader of this message is
not the intended recipient, or an employee or agent responsible for
delivering this message to the intended recipient, you are hereby notified
that any dissemination, distribution, copying, or other use of this message
or its attachments is strictly prohibited. If you have received this
message in error, please notify the sender immediately by replying to this
message and please delete it from your computer.


On Thu, Feb 20, 2020 at 12:36 PM Masoud Rouhizadeh <mr...@jhu.edu> wrote:

> Dear all,
>
> I'm using cTAKES default clinical pipeline with the following dictionary
> to extract the following:
>
> - Signs and symptoms (Human Phenotype Ontology)
> - Disorders and disease (ICD 10 CM)
> - Medications (RxNorms)
>
> Given the processing time of the annotation steps, it would be best if I
> don't have to run cTAKES clinical pipeline three times for each of the
> dictionaries.
>
> What would be your recommendation? Does merging all of the dictionaries
> make sense? If not, is there a way to run the fast dictionary lookup three
> times (for each dictionary) in the same pipeline and collect CUIs?
>
> Thanks,
> Masoud
>
>
>