There is something called "Evidence Based Medicine" that is in the
works. In the book "Super Crunchers" Ian Ayres devotes a chapter(4) to
such systems and the reaction of doctors.
Diagnostics by examination of huge databases is evidently pretty far
along. The book points out that it is the electronic collection of
things like medical records that is enabling the crunching of data and
the "improved" diagnosis.
from the book -
" A bunch of medical schools and private corporations are developing the
first generation of "diagnostic-decision support software. A diagnostic
program named 'Isabel' allows physicians to enter a patients symptoms
and receive a list of the most likely causes. It will even tell the
doctor whether a patient's symptoms might be caused by the use of over
4,000 drugs. The Isabel database associates more than 10,000 specific
illnesses with a host of clinical findings, lab results..."
I'm not arguing anything here, just suggesting that there are powerful
systems being developed that might be worth investigating. The general
principle might be that if one has tons of data, he can derive pretty
good predictions.
Mike Tintner wrote:
Steve/MT:
My off-the-cuff thought here is that a central database,
organised on some open source basis getting medical
professionals continually to contribute and update, which would
enable people to immediately get a run-down of the major
possible causes (and indeed minor possible ones - anything that
has been proposed) - for any given illness or set of symptoms,
would be a great thing - assuming somesuch doesn't already
exist. That would leave the user to make his choices.
Those words could have come from my own fingers ~3 years ago. Since
then I have come to realize just how profoundly insecure these guys
really are. Several attempts to sell this into various settings have
run into insurmountable people-problems, though there has been no
significant technical problems.
Steve,
I can loosely appreciate the problems of persuasion, but, given your
enthusiasm for this field, I would urge you to keep trying - there
has to be a way round them.
Surely, the angle has to be something like a
super-medical-wiki-but-with-professional-standards has to be of
universal use to MEDICAL PRACTITIONERS as well as the layperson,
(and the layman will still need professional advice on the info.
provided). The immediate marketing angle that occurs to me is: this
will keep you, the medico, up-to-date and ensure you don't give
out-of-date unprofessional advice (and will give your advice an
imprimatur in that you will always be able to say you checked the
most reliable source). [No doubt there may be many other angles].
My guess is an awful lot of medicos WON'T be up-to-date. For
example, last year there was a discovery re CFS & how it's down to a
stomach virus - which looks right, and fits the symptoms. I'll bet
an awful lot of medicos aren't up-to-date on that yet but the
sufferers still looking for a reasonable treatment, will sure as
heck appreciate the info.
And if you could work out a super-pro-wiki framework, it would
probably be applicable to many fields.
Re the general problem-solving issue, I was groping for an
essentially philosophical discussion [because that's what it has to
be] of some kind of general problem-solving language/
set-of-concepts, such as we already have - "problem", "idea,"
"theory", "evidence," etc. I think this is the sort of area
AGI-ers take for granted but is actually majorly difficult.
P.S. Wouldn't medical insurers have the greatest interest of all in
establishing a super-medical-wiki?
*agi* | Archives <http://www.listbox.com/member/archive/303/=now>
<http://www.listbox.com/member/archive/rss/303/> | Modify
<http://www.listbox.com/member/?&;>
Your Subscription [Powered by Listbox] <http://www.listbox.com>
-------------------------------------------
agi
Archives: http://www.listbox.com/member/archive/303/=now
RSS Feed: http://www.listbox.com/member/archive/rss/303/
Modify Your Subscription:
http://www.listbox.com/member/?member_id=8660244&id_secret=103754539-40ed26
Powered by Listbox: http://www.listbox.com
