Xref: utzoo bionet.software:963 sci.med:24344
Path: utzoo!utgpu!news-server.csri.toronto.edu!rpi!zaphod.mps.ohio-state.edu!ub!csn!ccncsu!purdue!mentor.cc.purdue.edu!noose.ecn.purdue.edu!samsung!cs.utexas.edu!bcm!bionet!bio.embnet.se!sunic!mcsun!ukc!icdoc!qmw-cs!sayyad
From: sayyad@cs.qmw.ac.uk (Mohiddin)
Newsgroups: bionet.software,sci.med,uk.ikbs
Subject: Re: Looking for AI/RHEUM
Message-ID: <3544@sequent.cs.qmw.ac.uk>
Date: 12 Apr 91 09:48:04 GMT
References: <9104021957.AA17618@darwin> <4185@stl.stc.co.uk> <1991Apr8.145927.3357@dsl.pitt.edu>
Followup-To: bionet.software
Organization: Computer Science Dept, QMW, University of London, UK.
Lines: 19


 In early 80's K.P Adlassnig developed a CADIAG-2/RHEUMA using
fuzzy logic. Authors claim there is 94.5% success rate with
their system in diagnosing Rheumatoid, gout, Bechterew's,
Sjogren's disease, systemic lupus erythematous, Rieter's
disease etc.,  The above is from reference

"Fuzzy set theory in medical diagnosis", KPA, IEEE Tr. Systems,
man and Cybernetics, Vol 16/2 Mar/April 1986.

 Recently John Yen (while he was at Univ. of California, Berkeley)
built a system with CADIAG-2's data and it is called GERTIS
(based on Evidential reasoning). JY claims (I not sure where I read)
it became a commercial product.

JY is now with Texas A&M Univ., College Station, TX 77843.

--------
Sayyad