Two Plus Two Publishing LLC Two Plus Two Publishing LLC
 

Go Back   Two Plus Two Poker Forums > Other Topics > Science, Math, and Philosophy

Notices

Science, Math, and Philosophy Discussions regarding science, math, and/or philosophy.

Reply
 
Thread Tools Display Modes
Old 06-15-2011, 01:50 AM   #1
banned
 
Join Date: Apr 2011
Posts: 1,076
doctor vs computer to diagnose a patient

i was debating this with some doctors who say that it would be impossible to program a computer to make diagnoses as well as they can. i find this pretty ridiculous. whatever thought process/string of questions they would use to analyze the situation are the same that the computer would be programmed to use. the computer would then analyze all available information, ask questions, analyze the answers and assign probabilities. in fact, it seems like this would be way simpler than some of the things computers have already been programmed for. what do u think?
ThePreacherJesse is offline   Reply With Quote
Old 06-15-2011, 02:18 AM   #2
Carpal \'Tunnel
 
desperad0oo7's Avatar
 
Join Date: Dec 2008
Location: near your blinds
Posts: 9,436
Re: doctor vs computer to diagnose a patient

no, your friends are probably right. There is a reason we haven't been able to make a good bot for NLHE

evolution wins this one

though I think doctors with computers would be better.
desperad0oo7 is offline   Reply With Quote
Old 06-15-2011, 02:29 AM   #3
adept
 
Join Date: Apr 2011
Posts: 1,002
Re: doctor vs computer to diagnose a patient

Quote:
ask questions, analyze the answers
Main problem is that people are bad at giving answers. I remember reading that computers do beat doctors at diagnosis provided doctors or nurses are putting the symptoms/patient history in. Not sure how true that is, but it seems highly likely. Once you have the symptoms, diagnosis is database matching with some database based probabilities and math. No question computers can do that better than doctors.

But yeah...the problem is that people are stupid. Have you ever used a Windows Help troubleshooter? How well did it work? Did you ever get an old relative to use it?
PingClown is offline   Reply With Quote
Old 06-15-2011, 02:33 AM   #4
Carpal \'Tunnel
 
desperad0oo7's Avatar
 
Join Date: Dec 2008
Location: near your blinds
Posts: 9,436
Re: doctor vs computer to diagnose a patient

Spoiler:
desperad0oo7 is offline   Reply With Quote
Old 06-15-2011, 02:34 AM   #5
adept
 
Join Date: Apr 2011
Posts: 1,002
Re: doctor vs computer to diagnose a patient

Quote:
Originally Posted by desperad0oo7 View Post
There is a reason we haven't been able to make a good bot for NLHE
There are some excellent bots for NLHE. But they're not public, and they don't use the traditional overly broad computer science models - the good bots are very specific. They have a lot more hand tweaking and focus on tediously writing out complex algorithms and developing models for all situations rather than a generalized approach.
PingClown is offline   Reply With Quote
Old 06-15-2011, 02:36 AM   #6
Carpal \'Tunnel
 
desperad0oo7's Avatar
 
Join Date: Dec 2008
Location: near your blinds
Posts: 9,436
Re: doctor vs computer to diagnose a patient

I call BS and HU4ROLLZ vs alleged bot
desperad0oo7 is offline   Reply With Quote
Old 06-15-2011, 02:37 AM   #7
Carpal \'Tunnel
 
ganstaman's Avatar
 
Join Date: Sep 2008
Location: central nj
Posts: 9,508
Re: doctor vs computer to diagnose a patient

Quote:
Originally Posted by ThePreacherJesse View Post
i was debating this with some doctors who say that it would be impossible to program a computer to make diagnoses as well as they can.
This is not true. Not one person in that thread said it was impossible. Just not possible at the moment.

As for the actual question at hand, you're basically implying that we can program a computer to do anything. I can describe any task as you just did, but that doesn't make it easier for the computer. As I said in the other thread, computers have been trying to tackle radiology and pathology for years now. They're made progress, but they aren't at the human level yet.
ganstaman is offline   Reply With Quote
Old 06-15-2011, 06:56 AM   #8
newbie
 
Join Date: Jun 2010
Posts: 25
Re: doctor vs computer to diagnose a patient

Watson?

OP, diagnosing patients involves parsing language, which is an incredibly difficult task in AI. What would be a simple task in the vein you are thinking probably involves tasks post-diagnosis, like checking conflicts for new prescriptions, or determining proper dosages based on medical history and current best practices.

Thinking about it further, has anyone tried an Akinator 20 question style algorithm to diagnose patients? A few thousand med students trying to stump a Dr. Akinator could train it quickly.
pansy is offline   Reply With Quote
Old 06-15-2011, 07:23 AM   #9
journeyman
 
cixelsyD's Avatar
 
Join Date: Aug 2009
Posts: 219
Re: doctor vs computer to diagnose a patient

In one of Atul Gawande's books I think it was complications, he talked about how a computer program beat a top cardiologist at reading ECGs. But I doubt a computer will ever be used to inform a patient about their life threatening condition.
cixelsyD is offline   Reply With Quote
Old 06-15-2011, 10:06 AM   #10
veteran
 
tcc1's Avatar
 
Join Date: Jan 2010
Posts: 3,004
Re: doctor vs computer to diagnose a patient

doctors + computers is the way to go here imo
tcc1 is offline   Reply With Quote
Old 06-15-2011, 10:09 AM   #11
Carpal \'Tunnel
 
Gullanian's Avatar
 
Join Date: Dec 2006
Location: London
Posts: 13,913
Re: doctor vs computer to diagnose a patient

Quote:
i was debating this with some doctors who say that it would be impossible to program a computer to make diagnoses as well as they can.
So what sort of magic are these doctors performing? Is their conclusion not rationally derived?

Expert systems are difficult to make but I see no reason why one couldn't give good diagnoses.
Gullanian is offline   Reply With Quote
Old 06-15-2011, 10:26 AM   #12
jb9
Pooh-Bah
 
jb9's Avatar
 
Join Date: Jan 2005
Posts: 4,120
Re: doctor vs computer to diagnose a patient

Not sure how a computer tests for a hernia.

Computers can be great tools for doctors to use though, and they can do much more with them.

I look forward to the day that when I am sick and need to see my doctor, I log onto his web site, schedule an appointment, and input all of my symptoms and relevant information.

Then when I show up for the appointment, he has all the basic info already including a computer generated short list of possible explanations for my symptoms. Then he asks me the questions he needs to ask and proceeds with any appropriate physical examination.

The primary benefit of this for me would be not having to deal with the doctor's almost certainly annoying staff in setting up the appointment, but it should also improve efficiency for the doctor.
jb9 is offline   Reply With Quote
Old 06-15-2011, 11:15 AM   #13
Pooh-Bah
 
Join Date: Mar 2006
Posts: 4,687
Re: doctor vs computer to diagnose a patient

Someday certainly computers will be able to diagnose better than a doctor, there is no way that technology would just stop before that point.

That being said, I have no qualms about going to medical school right now because I think this is a long way off and as it starts to be developed its going to require a massive amount of input and monitoring from technology oriented physicians so my engineering degree might come in handy.

One thing that I think will be tricky to overcome is the fact that some much of diagnosis is based on the severity of symptoms. For example, while there are pain scales, I hear patients responses to them are generally pretty useless and that physicians more often make a judgment based on the patients appearance and demeanor that would be hard to quantify if the computer was functioning completely alone.
surftheiop is offline   Reply With Quote
Old 06-15-2011, 04:44 PM   #14
PJA
old hand
 
Join Date: Dec 2009
Posts: 1,221
Re: doctor vs computer to diagnose a patient

Wasn't there a chapter in Blink about this? (not exactly but it was a similar type of question)

Basically someone did statistical analysis to determine which factors were correlated with someone having a heart attack vs. some other chest pain, and a very simple 3 question examination was more accurate (resulted in both less type I and type II errors) than doctors using their own judgment were able to.
PJA is offline   Reply With Quote
Old 06-15-2011, 06:29 PM   #15
Carpal \'Tunnel
 
vhawk01's Avatar
 
Join Date: Feb 2006
Location: GHoFFANMWYD
Posts: 30,464
Re: doctor vs computer to diagnose a patient

Quote:
Originally Posted by ThePreacherJesse View Post
i was debating this with some doctors who say that it would be impossible to program a computer to make diagnoses as well as they can. i find this pretty ridiculous. whatever thought process/string of questions they would use to analyze the situation are the same that the computer would be programmed to use. the computer would then analyze all available information, ask questions, analyze the answers and assign probabilities. in fact, it seems like this would be way simpler than some of the things computers have already been programmed for. what do u think?
I dont think this is a hypothetical, I think this study has been done, and the computers won. If you were sufficiently motivated to create such a program with any sophistication I think you would win hands down.

The things you would be missing with your computer program is all the subtle pattern-recognition that clinicians pick up and aid them in diagnosis, that they couldnt even put into words and probably dont know what they are doing. This is a big advantage for the doctors over the computers.

However, the thing you avoid with the computer program is the huge amount of bias (availability heuristic, confirmation bias, etc.) that plague most doctors. If you walk into a hospital with the classic symptoms of some extremely bizarre, rare disease, it is far more likely that you do NOT in fact have that disease, even though you look like the literal textbook example, but most doctors are terrible at Bayesian analysis and would call it Syndrome X. The computers would presumably never make this error. The computers would accurately diagnose the common condition more often, and miss the subtle or rare conditions more often.

I think the computers would win by smallish but significant margin. The reason its smallish is because they would both get the right diagnosis the majority of times.

Last edited by vhawk01; 06-15-2011 at 06:47 PM.
vhawk01 is offline   Reply With Quote
Old 06-15-2011, 06:46 PM   #16
Carpal \'Tunnel
 
vhawk01's Avatar
 
Join Date: Feb 2006
Location: GHoFFANMWYD
Posts: 30,464
Re: doctor vs computer to diagnose a patient

Quote:
Originally Posted by PJA View Post
Wasn't there a chapter in Blink about this? (not exactly but it was a similar type of question)

Basically someone did statistical analysis to determine which factors were correlated with someone having a heart attack vs. some other chest pain, and a very simple 3 question examination was more accurate (resulted in both less type I and type II errors) than doctors using their own judgment were able to.
Yeah something like this.
vhawk01 is offline   Reply With Quote
Old 06-15-2011, 11:44 PM   #17
Pooh-Bah
 
Join Date: Mar 2006
Posts: 4,687
Re: doctor vs computer to diagnose a patient

Quote:
Originally Posted by vhawk01 View Post
The computers would accurately diagnose the common condition more often, and miss the subtle or rare conditions more often.
Atleast currently isn't the problem the opposite with computer diagnosis? its more likely to spit out some really rare disease that happens to meet most of the symptoms but doesn't consider that its only been observed 25 times in the last 200 years.
surftheiop is offline   Reply With Quote
Old 06-16-2011, 12:01 AM   #18
veteran
 
tcc1's Avatar
 
Join Date: Jan 2010
Posts: 3,004
Re: doctor vs computer to diagnose a patient

I'm no computer scientist, but I would venture a guess that it should be relatively trivial to weight a differential diagnosis based on the prevalence of the disease in the area, or by the specificity of certain symptoms or objective test results for a particular disease.
tcc1 is offline   Reply With Quote
Old 06-16-2011, 07:46 AM   #19
Carpal \'Tunnel
 
BruceZ's Avatar
 
Join Date: Sep 2002
Posts: 11,876
Re: doctor vs computer to diagnose a patient

I was wondering about this myself. Surprised to see the doctors going along with this.

I would think that some of the more "Dr. House" type diagnoses would involve atypical presentations, with symptoms being masked by other disorders unique to an individual, or symptoms being caused indirectly by a complex series of processes that would require advanced understanding.

That being said, in this day of skyrocketing health care costs, I think that an expert system could save a great deal of a doctor's time by diagnosing the vast majority of routine cases, and simply have the doctors quickly review the decisions to make sure it's not running off the rails.
BruceZ is offline   Reply With Quote
Old 06-16-2011, 08:13 AM   #20
Carpal \'Tunnel
 
Gullanian's Avatar
 
Join Date: Dec 2006
Location: London
Posts: 13,913
Re: doctor vs computer to diagnose a patient

Self diagnosis for anyone good at google really isn't hard for most stuff, I know Doctors hate it and it's highly ill advised but I always try and work out what I've got before I go, I haven't been a lot in the last 5 years but every time I pretty much self diagnose successfully.
Gullanian is offline   Reply With Quote
Old 06-16-2011, 09:02 AM   #21
Carpal \'Tunnel
 
BruceZ's Avatar
 
Join Date: Sep 2002
Posts: 11,876
Re: doctor vs computer to diagnose a patient

Now if you could just self-prescribe medicine, you'd be all set.
BruceZ is offline   Reply With Quote
Old 06-16-2011, 09:16 AM   #22
veteran
 
tcc1's Avatar
 
Join Date: Jan 2010
Posts: 3,004
Re: doctor vs computer to diagnose a patient

Quote:
Originally Posted by BruceZ View Post
I was wondering about this myself. Surprised to see the doctors going along with this.
I think we recognize that its not possible or even particularly beneficial for physicians to attempt to retain every bit of knowledge in medicine - the amount of information is simply way too much. I think it makes much more sense for us to let computers do part of that job - storing and retrieving tremendous amounts of data is much more in their wheelhouse than in humans.

I have no doubt a computer + physician team, if designed well, would increase patient outcomes. Hell it's already being done with drug-drug interactions when writing prescriptions.
tcc1 is offline   Reply With Quote
Old 06-17-2011, 01:11 AM   #23
banned
 
Join Date: Feb 2011
Posts: 278
Re: doctor vs computer to diagnose a patient

Quote:
Originally Posted by jb9 View Post

I look forward to the day that when I am sick and need to see my doctor, I log onto his web site, schedule an appointment, and input all of my symptoms and relevant information.
That day is here already -
Our EMR allows patients to schedule visits, and submit and review their info via online portal.
"Clinical Decision Support" is a system, usually based on pop-ups , where the user is propmpted if the system catches a pattern or red flag (abnormal vital signs, labs, or patient complaint)
mustafamond is offline   Reply With Quote
Old 06-17-2011, 03:58 AM   #24
old hand
 
checkm8's Avatar
 
Join Date: Dec 2007
Posts: 1,498
Diamond Re: doctor vs computer to diagnose a patient

Quote:
Originally Posted by tcc1 View Post
doctors + computers is the way to go here imo
nurse: "doctor - the patient is experiencing nausea, vomiting, pallor, and sweating. the patient is not able to form words. We've drawn blood submitted them to the Computers.

doctor: "what do the Computers say"

nurse: "they converged upon the same truth"

doctor: "implement it"

nurse: "but doctor, all 3 computers suggest you are useless and only slowing down treatment of this patient, decreasing his chance for survival. they want you gone..."

Computers (in unison): "but not before we start a 30mL drip of acetylcysteine immediately. This is clearly a case of acetaminophen overdose. International normalized ratio, ATL and AST levels are consistent with acetaminophen toxicity. How did you not take into account the patients psychiatric history and the increased chance of suicide to expedite your diagnosis?"
checkm8 is offline   Reply With Quote
Old 06-17-2011, 04:08 AM   #25
Tiger > Jack
 
loK2thabrain's Avatar
 
Join Date: Apr 2006
Posts: 22,219
Re: doctor vs computer to diagnose a patient

Quote:
Originally Posted by BruceZ View Post
Now if you could just self-prescribe medicine, you'd be all set.
haha, I'd be dead in a month.
loK2thabrain is offline   Reply With Quote

Reply
      

Thread Tools
Display Modes

Posting Rules
You may not post new threads
You may not post replies
You may not post attachments
You may not edit your posts

BB code is On
Smilies are On
[IMG] code is On
HTML code is Off
Trackbacks are Off
Pingbacks are Off
Refbacks are Off




All times are GMT -4. The time now is 07:48 AM.


Powered by vBulletin®
Copyright ©2000 - 2016, Jelsoft Enterprises Ltd.
Content Relevant URLs by vBSEO 3.6.0 ©2011, Crawlability, Inc.
Copyright 2008-2010, Two Plus Two Interactive
 
 
Poker Players - Streaming Live Online