medical diagnosis software

Video games, electronics and gadgets, elf ears and more
Post Reply
User avatar
ZAffer
Stew Ingredient
Posts: 24336
Joined: Sat May 20, 2006 8:47 pm

medical diagnosis software

Post by ZAffer » Sun Aug 31, 2014 5:53 pm

http://en.m.wikipedia.org/wiki/Clinical ... ort_system

I'm surprised there isn't more of this around. Doctors seem to have to learn an awful lot of stuff, and, from some of the posts here, and my own experience, mis-diagnosis isn't exactly uncommon. The best use is obviously drug interactions: how different drugs can produce bad results. Eg warfarin and asprin. Equally, many conditions present very similar symptoms: TB and pneumonia, but the treatment may differ. One intern who had to diagnose me got it wrong: pneumonia instead of TB, but she 'caught' it, by specifying a specific test.

Just medical profession resistance?

Eta

2005 systematic review by Garg et al. of 100 studies concluded that CDSSs improved practitioner performance in 64% of the studies. The CDSSs improved patient outcomes in 13% of the studies.
sce to aux

User avatar
NorthAmerican
Stew Ingredient
Posts: 18634
Joined: Tue Jun 11, 2013 4:15 pm

Re: medical diagnosis software

Post by NorthAmerican » Sun Aug 31, 2014 6:31 pm

That was too technical for me, and too much to read in any case, but my records are in an electronic file like the one described at your link. You can see the results of various tests performed, records of infections and how they were treated, etc.
I enjoy reading NorthAmerican's posts. So well-written and interesting except for the dull parts.--Nines

User avatar
ZAffer
Stew Ingredient
Posts: 24336
Joined: Sat May 20, 2006 8:47 pm

Re: medical diagnosis software

Post by ZAffer » Sun Aug 31, 2014 7:37 pm

But a human still makes the call, based on those tests. A dr sees lots of people, usually for brief periods, and has to (initially) base his diagnosis on what the patient says, later, from test results. Which can actually be misleading. Why not just plug everything into a computer, and let it provide a range of possibilities?
sce to aux

User avatar
ZAffer
Stew Ingredient
Posts: 24336
Joined: Sat May 20, 2006 8:47 pm

Re: medical diagnosis software

Post by ZAffer » Sun Aug 31, 2014 8:04 pm

Long read. http://mobile.nytimes.com/2012/12/04/he ... d=all&_r=0

Dr. Martin Kohn, chief medical scientist for I.B.M. Research, is careful to point out that Watson for Healthcare is intended to be “neither omniscient nor omnipotent.” Yet, Dr. Kohn noted, most physicians set aside five hours or less each month to read medical literature, while Watson can analyze the equivalent of thousands of textbooks every second. The program relies heavily on natural language processing. It can understand the nature of a question and review large amounts of information, such as a patient’s electronic medical record, textbooks and journal articles, then offer a list of suggestions with a confidence level assigned to each.

For physicians, Dr. Kohn said, one problem is what he calls “the law of availability.”

“You aren’t going to put anything on a list that you don’t think is relevant, or didn’t know to think of,” he said. “And that could limit your chances of getting a correct diagnosis.”

Dr. Dhaliwal agreed, citing the recent outbreak of hantavirus at Yosemite. Ten people contracted the virus, and three died. “It’s a febrile illness that looks like the flu,” he said. “It’s so rare, the last time you might have seen it was your medical school classroom.”

Had Isabel or a similar program been used, the deaths might have been prevented, Dr. Dhaliwal said. “You might think you’re in familiar territory, but the computer is here to remind you there are other things.”
sce to aux

User avatar
NorthAmerican
Stew Ingredient
Posts: 18634
Joined: Tue Jun 11, 2013 4:15 pm

Re: medical diagnosis software

Post by NorthAmerican » Sun Aug 31, 2014 9:40 pm

ZAffer wrote:...For physicians, Dr. Kohn said, one problem is what he calls “the law of availability.”
“You aren’t going to put anything on a list that you don’t think is relevant, or didn’t know to think of,” he said. “And that could limit your chances of getting a correct diagnosis.”
I agree. Years ago, there was an occasional article in the New Yorker called Annals of Medicine. In a column titled "Two Blue Hands," the author dealt with the difficulty that doctors had in diagnosing the cause of a man's blue hands. They had run various tests without getting anywhere.

The man in question worked outdoors in an occupation that required him to be out in all kinds of weather with his fingers free to work with wires or cables. To warm his hands, he put them in his armpits for a minute or so. The doctor who diagnosed the problem put two and two together by asking about the man's work and, if I'm not mistaken, seeing the man put his hands in his armpits while in the examining room. Maybe he also saw a blue-flannel shirt among the clothing the man had removed before being examined. That's the odd kind of case that should go into the computer with all the other, more normal ones.
I enjoy reading NorthAmerican's posts. So well-written and interesting except for the dull parts.--Nines

User avatar
ZAffer
Stew Ingredient
Posts: 24336
Joined: Sat May 20, 2006 8:47 pm

Re: medical diagnosis software

Post by ZAffer » Mon Sep 01, 2014 12:08 am

I really doubt that is something a computer would pick up!

I mean, I've had TB for over a year. 2 different doctors missed it. The 2nd did more tests; everthing normal, except "some kind of infection". It didn't seem to occur to either of them that white people could GET TB!
sce to aux

User avatar
ZAffer
Stew Ingredient
Posts: 24336
Joined: Sat May 20, 2006 8:47 pm

Re: medical diagnosis software

Post by ZAffer » Tue Sep 16, 2014 8:37 pm

Probably won't come from here, altho it should. Got examined by a whole lot of students the other day: one medical facility is introducing a new rank: medical diagnosis technician, which seems to be somewhere between a nurse and a doctor. They're very good, quite amazing what they can diagnose without any tools. (eg stethescope) I'm the perfect case, having been mis-diagnosed twice, and, after 95+ days, they STILL don't know what is wrong with me!
sce to aux

Post Reply