ctakes-dev mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From John Green <john.travis.gr...@gmail.com>
Subject Sundry
Date Tue, 22 Oct 2013 21:00:17 GMT
Hey all, a couple of things:

1) Ill polish off those example notes as I push through the final lap of my
clinical experiences of medical school. It should leave a very
representative set across disciplines.

2) I work for the DoD and have latched on to several IRB approved projects
within that community where Ill be using cTakes, though minimally at first.
This is just a statement, a bug in the ear of the community of what people
are up to.

3) As was stated in other threads, Im a former computer programmer who's
now putting himself through med-school. However, my computer programming
experience, while broad (python, java, c, etc) was not formal comp-sci.
E.g. I'm pretty new to machine learning, and part of my intention in
joining this project it to contribute/learn. That's a long preface to: has
anyone considered (and maybe the components already do this in some way I
haven't explored yet - time is ever limited) adding an OPQRST classifier?
This is an acronym that many clinicians use to systematically describe a
diseases's course or some symptom like pain. It is a great tool and I find
that even advanced clinicians use it everyday, though they may not run
through the acronym in their head. As I continue to read about ML in my
spare time (ha!), this is a theme that continues to occur to me as an
additional component, specifically with an eye on future projects that
build on top of cTakes, clinical applications that use its NLP for
functionality. Im just curious what more experienced people think of the
feasibility/usefulness of this.

John

Mime
  • Unnamed multipart/alternative (inline, None, 0 bytes)
View raw message