Small medical query parser

[John Green <jo...@gmail.com>]

Hi all, been silent awhile but not for lack of work. Recently pushed a
project to github that some on this list might find interesting. Its a
small NER program suitable for one line inputs. A use case is highly
variable one line inputs that need cui's mapped for searching against say a
larger corpus annotated with cTAKES. I've found that for small phrases its
very good. I'd love to hear feedback.

*https://github.com/jtgreen/SMPP <https://github.com/jtgreen/SMPP>*

Best JG

Re: Small medical query parser

[John Green <jo...@gmail.com>]

Pei - Id love to. My contributions to this wonderful project (cTAKES) have been minimal at best. Ill see what I can do before intern year starts and if not ill chip at it when the daily grind of medicine needs a pause! 


Best,

JG

On Fri, Apr 17, 2015 at 11:51 PM, Pei Chen <ch...@apache.org> wrote:

> Hi John,
> It looks pretty straightforward.  Were you thinking of contributing
> something like this as an alternative/simplified pipeline- for those who
> may not want to always extract deep knowledge but just map terms to codes?
> Perhaps it can be even simpler if it can read the same existing bundled
> hsqldb cTAKES dictionaries (that way folks won't have to worry about
> UMLS).  Something for the sandbox if others think it will be useful for
> their use cases and especially if you're willing to help maintain it...
> --Pei
> On Fri, Apr 17, 2015 at 10:22 AM, John Green <jo...@gmail.com>
> wrote:
>> Hi all, been silent awhile but not for lack of work. Recently pushed a
>> project to github that some on this list might find interesting. Its a
>> small NER program suitable for one line inputs. A use case is highly
>> variable one line inputs that need cui's mapped for searching against say a
>> larger corpus annotated with cTAKES. I've found that for small phrases its
>> very good. I'd love to hear feedback.
>>
>> *https://github.com/jtgreen/SMPP <https://github.com/jtgreen/SMPP>*
>>
>> Best JG
>>

Re: Small medical query parser

[Pei Chen <ch...@apache.org>]

Hi John,
It looks pretty straightforward.  Were you thinking of contributing
something like this as an alternative/simplified pipeline- for those who
may not want to always extract deep knowledge but just map terms to codes?
Perhaps it can be even simpler if it can read the same existing bundled
hsqldb cTAKES dictionaries (that way folks won't have to worry about
UMLS).  Something for the sandbox if others think it will be useful for
their use cases and especially if you're willing to help maintain it...

--Pei

On Fri, Apr 17, 2015 at 10:22 AM, John Green <jo...@gmail.com>
wrote:

> Hi all, been silent awhile but not for lack of work. Recently pushed a
> project to github that some on this list might find interesting. Its a
> small NER program suitable for one line inputs. A use case is highly
> variable one line inputs that need cui's mapped for searching against say a
> larger corpus annotated with cTAKES. I've found that for small phrases its
> very good. I'd love to hear feedback.
>
> *https://github.com/jtgreen/SMPP <https://github.com/jtgreen/SMPP>*
>
> Best JG
>