|
From: | sjtan |
Subject: | re: [Gnumed-devel] need assessment from fellow clinicians |
Date: | Thu, 01 Jul 2004 17:38:22 +1000 |
User-agent: | Mozilla/5.0 (X11; U; Linux i686; en-US; rv:1.6) Gecko/20040113 |
I realise that : the idea is that the user configures the parser to his particular idiosyncratic style of rushed note entry during consultation, so that the parser picks up most of the items, e.g. how many times can a note p/ script atenolol 50mg 1 daily , enalopril 10mg daily, chlorthalidone half daily , be written.You'll get into a quagmire that decades of natural language processing and AI have failed to make easy even with specialized vocabularies/ontologies as in medicine.
and then
I can imagine, however, a free-text box that let's me select text parts and press <Alt-S/O/A/P> to make them such.
the user has this option, or directly editing the tree.Another thing that might be useful here is hidden markov model training ; as the user corrects the tentative tree updates, a hmm is trained to make a better parse next time . The problem here might be , hmm are being used to classify only 2 categories in practical use for spam nowadays, but can gnumed
use it to classify multiple categories ?
[Prev in Thread] | Current Thread | [Next in Thread] |