Ian Cheong <[EMAIL PROTECTED]> wrote:
> Do you have....
>   or any chance you can get staff/students to build....
> 
>   an open source cross-platform standards-based SNOMED browser??
> 
> Presently, there is only one the UK people have built in MS Access.

I agree - the UK "CLUE" SNOMED-CT browser is OK as far as it goes, but yes, its 
a bit naff, its Windows only, and it is a "thick client" application.

A Web-based browser, incorporating some slick new "Web 2.0" AJAX technology, 
with the back-end running on Linux, Mac OS X or Windows, would be useful (and 
would attract international acclaim if it were better than the CLUE browser, 
which is not difficult).

I had the pleasure of attending presentations by Jon's summer students this 
morning, and gee, they were impressive (both the quality of the presentations 
and the nature of the work). Many of the students' projects related to 
SNOMED-CT (including the Web-based text-to-SNOMED-CT coder - even more 
impressive when you can see the actual SNOMED-CT concepts it identifies in the 
text, and also a way-cool XML-based electronic forms system which presents 
replicas of existing paper forms on a tablet PC and does handwriting 
recognition of the text and data entered, and then does a background look-up of 
SNOMED-CT concept codes and annotates the entered text accordingly, all in 
near-real-time). One of the students (might have been by Ming Zhang) presented 
some very interesting work on both the explicit ontological/data model 
structure of SNOMED-CT (which is kind-of represented in the CLUE browser) but 
also the implicit structure of SNOMED-CT (which the CLUE browser completely 
ignores)

My suggestion would be:

a) build on the work already done (just the code which one of the students 
wrote to load SNOMED-CT into MySQL is really useful stuff) by developing a set 
of structure- or ontology-aware classes in Python and/or Java through which 
SNOMED-CT can be accessed (searched and/or browsed) via a range of applications 
(and for research projects) - a bit like, say, Oliver Steele's Python classes 
which wrap around the WordNet API (or put more simply, build a WordNet-like API 
for SNOMED-CT).

b) design and build a slick Web interface for these classes, with some way of 
visualising or browsing the implicit relationships and structure which is 
present in SNOMED-CT, as well as the explicit stucture. That would 
exercise/hone the students'  user interface design skills as well as AJAX/Web 
2.0 software engineering skills - all of these are hot commodities in the job 
marketplace right now. 

c) Fold this Web-based SNOMED-CT browser into the free-text SNOMED-CT term 
encoder which is already working in prototype form, thus enablingend users or 
reviewers to browse SCT when they refine or correct the concepts it assigns to 
their text.

These are not trivial projects, but Jon has shown that a small group of bright 
and keen students, with good supervision and leveraging a pool of existing 
academic expertise for advice, can acheive a great deal in a brief time at very 
modest cost, and everyone benefits.

Tim C


> >At 8:49 am +1100 21/2/06, [EMAIL PROTECTED] wrote:
> >>hi Ian, Yes I have a research licence as an advisory member of NCCH 
> and
> >>academic at USyd, which NCCH belongs to. I would love to give you the 
> SCT
> >>codes and my contact at NCCH is working to be help that happen. I will
> >>discuss your type of situation today with her and your proposal.
> >>thanks
> >>jon
> >>Quoting Ian Cheong <[EMAIL PROTECTED]>:
> >>
> >>>  At 4:21 am +1100 21/2/06, [EMAIL PROTECTED] wrote:
> >>>  >We have now launched the web page that converts
> >>>  >clinical notes to SCT codes which is available at:
> >>>  >
> >>>  >http://www.it.usyd.edu.au/~clinnote/gpnotes.cgi
> >>>  >
> >>>  >Pls use it to give us examples of the notes you record in your 
> daily
> >>>  >practice. You can select to get instant reporting or delayed 
> reporting
> >>>  via
> >>>  >email (reccommended for lengthy text > 5 full lines).
> >>>  >Please give us feedback on what we have missed which you think 
> should
> >>>  be
> >>>  >describale in SCT - it may that SCT doesn't have it.
> >>  > >Our analysis is by no means perfect and any feedback will help us 
> to
> >>>  >improve it.
> >>>  >You can play with it to scan what it does by inserting any medical
> >>>  related
> >>>  >text. We were using some published articles and discovered that 
> SCT
> >>>  knows
> >>>  >"postmenopausal" but doesn't know "post-menopausal".
> >>>  >
> >>>  >In a new initiative we are developing a prototpye variant of this
> >>>  system to
> >>>  >do a pilot study in the ICU at RPA which should be in test mode by 
> next
> >>>  >week. If anyone is interested in this area let me know.
> >>>  >thanks
> >>>
> >>>  John
> >>>
> >>>  I presume you have a SNOMED research licence. Is it possible that 
> the
> >>>  terms of that would cover some of us being able to view the
> >>>  codes/terms/hierarchy for the text for the purposes of that 
> research
> >>>  (providing feedback on accuracy of conversion) providing that we
> >>>  don't use them for day-to-day clinical notes.
> >>>
> >>>  (I have a SNOMED research licence from the NCCH already.)
> >>>
> >>>  For others, I presume they would need to sign something as members 
> of
> >>>  the "research team".
> >>>
> >>>
> >>>  Ian.
> >>>  --
> >>>  Dr Ian R Cheong, BMedSc, FRACGP, GradDipCompSc, MBA(Exec)
> >>>  Health Informatics Consultant, Brisbane, Australia
> >>>  Elected Member, GPCG Management Committee
> >>>  Internet: [EMAIL PROTECTED]
> >>>  (for urgent matters, please send a copy to my practice email as 
> well:
> >>>  [EMAIL PROTECTED])
> >>>
> >>>  PRIVACY NOTE
> >>>  I am happy for others to forward on email sent by me to public 
> email
> >>>  lists.
> >>>  Please ask my permission first if you wish to forward private email
> >>>  to other parties.
> >>>
> >>
> >>
> >>--
> >>Jon Patrick
> >>Chair of Language Technology
> >>School of Information Technologies
> >>University of Sydney
> >>Sydney, NSW, 2006, Australia
> >>
> >>----------------------------------------------------------------
> >>This message was sent using IMP, the Internet Messaging Program.
> >
> >
> >--
> >
> >Dr Ian R Cheong, BMedSc, FRACGP, GradDipCompSc, MBA(Exec)
> >Health Informatics Consultant, Brisbane, Australia
> >Elected Member, GPCG Management Committee
> >Internet: [EMAIL PROTECTED]
> >(for urgent matters, please send a copy to my practice email as 
> >well: [EMAIL PROTECTED])
> >
> >PRIVACY NOTE
> >I am happy for others to forward on email sent by me to public email 
> lists.
> >Please ask my permission first if you wish to forward private email 
> >to other parties.
> 
> 
> -- 
> Dr Ian R Cheong, BMedSc, FRACGP, GradDipCompSc, MBA(Exec)
> Health Informatics Consultant, Brisbane, Australia
> Elected Member, GPCG Management Committee
> Internet: [EMAIL PROTECTED]
> (for urgent matters, please send a copy to my practice email as well: 
> [EMAIL PROTECTED])
> 
> PRIVACY NOTE
> I am happy for others to forward on email sent by me to public email 
> lists.
> Please ask my permission first if you wish to forward private email 
> to other parties.
> _______________________________________________
> Gpcg_talk mailing list
> [email protected]
> http://ozdocit.org/cgi-bin/mailman/listinfo/gpcg_talk

_______________________________________________
Gpcg_talk mailing list
[email protected]
http://ozdocit.org/cgi-bin/mailman/listinfo/gpcg_talk

Reply via email to