<snip> >Ian R Cheong,said > It seems likely to me that computers will conquer natural language > processing faster than clinicians en masse can navigate a controlled > vocabulary with accuracy and speed. > To take a cue from Ian's comments: we have proposed that the best way to implement Snomed CT is to hide it from interrrupting the clincians workflow. That is make it live below ordinary view. It seems the obvious way to do that is to build a processor that converts natural english text to SCT on the fly. Such an approach doesn't require the clincian to learn anything new for the purpose of data capture, doesn't get in their way if don't want any analytics of their work practices, but with an SCT-Aware Analytics engine would provide a comprehensive investigative tool ( which would carry a learning load) for the curious. I wonder if anyone has any alternative proposals for implementing SCT? thanks jon
---------------------------------------------------------------- This message was sent using IMP, the Internet Messaging Program. _______________________________________________ Gpcg_talk mailing list [email protected] http://ozdocit.org/cgi-bin/mailman/listinfo/gpcg_talk
