Slashdot Mirror
Interesting Enemies For a Diagnostic Database
dlh writes: "Boston.com is carrying an article about Dr. Lawrence L. Weed's Problem Knowledge Coupler software. Apparently the medical profession is not exactly thrilled at the idea." Seems access to information is a positive thing, but certain doctors seem to feel threatened by this sort of database.
but certain doctors seem to feel threatened by this sort of database.
If you just payed a TON of money to goto medical school, would you then want all your education flaunted all over a network of information? Probably not, it's the fact that you know something others don't is what makes you money. This applies to specific fields, and research as well.
Things like this are why I firmly believe in having no discernible useful function within my organization other than to slack and criticise others -- lets see some computer database duplicate *that*.
Every year during my review, I just pray the words "slashdot.org" aren't mentioned.
If you control it, you have power. It's only human nature that many people fear losing power. When books were easily printable, and the masses began to read, you don't think the people who had that ability earlier felt threatened?
What a bround greaking idea.
Expert systems are *so* 1980s.
A Ph.D/M.D. colleague of mine one remarked that a doctor is nothing more than a walking database. You tell him your symptoms, he'll look up the possible problems in his head and give you a potential solution. That being said, it is only natural that some doctors might be threatened by the idea they can be so easily replaced.
Is that people tend to live the symtoms that their medical complaint suggests. That's why you have to run blind and double blind tests, to weed out people who unconciously fake what they know to be the symptoms.
Something like this could comprimise the blind tests.
[On the other hand, a lot of subtle bugs in software come from analysing the blind elements. Ie, trying to understand subtle behaviour.]
OS/2 - because choice is a terrible thing to waste.
I'm sure they're not just threatened, but some could be legitimately concerned that people will take this diagnostic database as some kind of authoritative source.
No, they shouldn't; it should be treated just like a book, but I'm just counting the days before someone sues the database for "giving them bogus information". And I'm counting the hours until we all become hypocondriacs.
If I were a doctor, that's what I'd be concerned about.
This now concludes our broadcast day.
from article:
"But, according to Cross, the neurologist who originally diagnosed the case as an REM sleep disorder had a very different reaction to the use of the software. When the plumber and his wife handed that doctor the PKC printouts, he shuffled them, left the room, and, Cross says, "returned with a very hostile, angry disposition." Viewing the results as computer-generated quackery, he refused to back down from his original diagnosis."
I read the article. This was the only example I saw...I'd say that's painting a very broad generalization. I also happen to know many doctors that EMBRACE technology.
Sounds to me like this was just one guy he was pissed because his diagnosis was proven wrong, and (like anyone) didn't like it.
Other than that, decent read.
Sent from your iPad.
Now, if they can just give this database a holographic body, and a little personality, we'll have Emergency Medical Holograms ready to go. Maybe they can even get around to giving them a name!
its only a matter of time... computers will be able to do everything better than humans eventually. its been shown that expert systems can outperform doctors in certain areas already, this one should be no different.
this is nothing but good for the patient, itll lead to cheaper and more accurate diagnoses.
Which is presumably why these naysayers are against the system. It correctly lists herbal and other alternative remedies as being both cheap and effective, kind of the Linux of the medical world. The AMA, with its vested interest in expensive, proprietary medicine, is totally opposed to any body of facts, electronic or otherwise, that would expose them for the money-grubbing reductionists that they are.
The only way to fight back to make this information widely known and of course take herbal remedies and perform chiropractic regularly to maintain a balanced chi.
Doctors need to think of this as a tool and not as a threat to their job. Just because I can try to diagnose my problems online dosn't mean I don't see a doctor. I am glad when I visit the doctor and he uses the computer or medical books to check the current best treatments or for other conditions with similar symptons - this shows the doctor is not oblivious to the fact they can't know everything.
As long as the software is properly regulated, just as docotors are, then there really shouldn't be a problem. The doctors can use the software to "help" and then make the final decision on the best course of action, as the computer cannot do that.
- HeXa
next thing you know they will make a walking reference database for all things computer, programming, networking, or database related. Ok look if you see anything labeled "Howto" delete it, we can beat this. (/sarcastic_humor off) Walking database helps you help yourself, knowledge never hurts when properly applied, but face it people will still go to doctors, just as they still hire database admins, network engineers, EE's, or CS's.
After reading this article, I am reminded of a good friend of mine, an M.D./Ph.D. student at Duke University, and some of the stories she tells me. I've heard of doctors that take advise even from an intern as a threat, much less advice from a computer.
The doctors that dismiss this type of aid out of hand are suffering from arrogance of the worst sort... they are dismissing a tool that can be used to further their patients health.
A person who has confidence in their own abilities can evaluate a tool and use the results as they see fit. While they need not use the tool as a crutch, they will use it as it is meant; as an aid to diagnosis.
They hate this because like everyone else they hate to be proven wrong let alone QUESTIONED. OTOH HMOs love this stuff because it represents one less person they have to hire.
"But now Weed believes his newest innovation, the Problem Knowledge Coupler, is finally ready for mainstream use."
No kidding. This is not really an innovation by any stretch. Rule-based diagnostic systems such as MYCIN first appead in the '70s!
I think the idea of a public medical knowledge database is an idea long overdue. However, IMHO, there is no substituting the medical doctor's long-time familiarity with both real-life cases of these symptoms/diagnosis/diseases and much of the data contained within such a database.
Also, dealing with a human being rather than a database can be rather reassuring in and of itself. Having a doctor confidently tell you a prognosis and treatment for it is alot more reassuring than seeing even those same words on a screen or piece of paper.
(* Things like this are why I firmly believe in having no discernible useful function within my organization other than to slack and criticise others -- lets see some computer database duplicate *that*. *)
In a recent slashdot forum on an AI topic, I concluded that it is easier to automate "rational" things than it is irrational [1] things, like marketing and PHB's.
Thus, techies will probably be automated out of a job before PHB's and sales. (That is if H1B's don't do it first.)
Geeks are Doomed! Eat, drink, and skydive from space, for tomarrow you are unlayable gutter meat.
[1] I don't know whether they are irrational, or just very hard or impossible to ascertain the rules for.
Table-ized A.I.
That's the beauty of the Natural Way. Your body knows what it needs. When it is replete with healing essence your desire to ingest more of Gaea's bounty will subside. There is no danger of overdose.
What's page widening, and why's it controversial? (I use a filtering proxy, so maybe I just don't see it.)
Opinions on the Twiddler2 hand-held keyboard?
As the article points out clearly and several times, doctors are (usually) humans. This means they have personality traits that affect they way they accomplish their work.
In this case, it's ego. Of course no one wants to see a printout handed to them by someone who isn't a professional in the field saying "hey, this computer said you're wrong!" For chrissakes!! I wouldn't either. Of course there should be some level of interest and consession by the professional to review the information and test its validity. A doctor with an ego problem should be avoided just like a network engineer/administrator who thinks he already knows everything he needs to know about any given subject.
So yeah, it's fun to take the immortals down a notch back to Earth reminding them that they're still human. But it should also serve as a reminder to anyone who lives in the ever-growing world of science and technology (this does include medical science) that there is always something new to learn and never to stop challenging the "facts" that have been layed out before us. Oddly, there is no "spontaneous generation" as was once suspected and those "wandering stars" (aka, planets) aren't like other stars for more reason than the fact that they don't move like the rest.
And of course, let us never forget that "science" isn't about proving anything "right" so much as it is about proving things to be wrong. It's never easy to know the truth. But we get closer every time we eliminate that which is untrue.
This could be an extremely useful tool. Why any good doctor would be opposed to it is beyond me. A truly professional doctor should be completely willing to defer to specialist or some sort of well-researched body when he is any less than 100% certain of his own work. Really, the only doctors I could imagine this would hurt are the bad doctors.
Most doctor visits that my kids and I have been to follow a rather simple algorithm:
1. Get swabs of patient mouth and ass
2. Perscribe patient antibiotics and
Codene.
3. Politely send patient away
4. Send swabs to lab
5. Play golf
Table-ized A.I.
Even if that information were detailed and free for anyone with an internet connection, part of going to medical school is to learn to accept responsibility. Any fool can read a car manual and learn how to fix his car, but if he is wrong and breaks the car, who has to pay to fix it? Also, do you think that us non-doctors can prescribe medication for ourselves? Doctors should not feel threatened at all.
Job? I don't have time to get a job! Who will sit around and bitch about being broke and unemployed then?
If I want a second opinion, do I leave the Oracle office and drive to Sybase?
Table-ized A.I.
Don't celebrate yet. Doctors are being replaced by huge/costly databases, your average /. nerd OTOH, /small/ shell script .. not even bash, but the minimal old sh!
will be replaced by a
You too trolls, you are being replaced by a one liner, written in a turing incomplete configuration
file language, no doubt.
So are jaded asshole remarks...
As a practicing physician (and software engineer since 1978, so don't get in a hissy fit), I have very little use for the program. Not that I don't find the idea of an expert system for diagnosis to be interesting, but it's clinically useless for most of us.
It may come as a surprise to most people, but diagnosis is not the hard part of medicine. Oh, sure, there are the occasional wierdies like the one in the article (and then I'd love to have the program), but mostly the diagnosis is either (a) not remotely in doubt, (b) irrelevant to the treatment (I don't care WHICH virus gave you diarrhea, I just care about hydration and mental status, and I don't need a computer program to help there), or (c) not something I need right now.
Clinical medicine is not mostly about diagnosis. It's mostly about disease management, triage, clinical efficiency, relationship building, and a huge dose of having to deal with every person that walks in the door, regardless of IQ, regardless of psychiatric diagnosis, and regardless of what I personally would like to do with them. Where excatly some peculiar expert system fits in with all that is something of a mystery to me.
(Oh, and surgical medicine is all of the above, plus time-critical eye-hand coordination, plus the routine inability to diagnose anything until you're in the OR, and the expert system is stone useless about then.)
New and better tools to solve problems that don't come up very often are interesting, but hardly something that will revolutionize medicine.
You forgot to put the rest of the song in. Which is Elton yelling saturday 94 times while dry humping his stool.
...because their expertise is knowledge based and any knowledge based profession is vulnerable to the same thing that is currently happening with the programming profession: It's being shipped to other countries in order to lower costs while raising profits.
For example, a hospital/HMO combo needs to watch costs, so has local technicians to do the local non-surgical stuff. Information on the patient is interpreted by an MD in India for low bucks, and the local technicians do the final, hands-on work if needed. Only time the hospital/HMO needs a "real" doctor/surgeon is when the patient really needs that level of hands-on work.
Hospitals/HMOs stand to make much bigger profits from this scenario and you can bet your doctor's bottom dollar they know it.
I repeat: Any and every profession which is knowledge based is vulnerable to this type of exporting.
"Sorry kid, I hate giving good people bad news." -- The Matrix
Everything in the Universe sucks: It's the law!
Your conclusion is wrong.
Automation of rational things always misses then irrational aspects that yet to be rationally discerned. Techies will always have that to do, not to mention new areas of expansion irrational things generate. After all, an observation that leads to a hypothesis is not a scientific fact but that of intuition that it may be, hence the term "discover." You can't rationalize discoveries until you automate the irrational, ad naseum.
In all Communist countries Medical Education was
free (in many of these countries still is)
In Cuba a medical student DOES NOT PAY A PENNY
FOR HIS/HER EDUCATION!
the machine take the hippcratic (sp?) oath?
what happens with l33t h4x0rs change the database so that cancer is treated with rubbing popsicles on your testicles
(or even less savory, used to assassinate someone w/ an incorrect diagnosis and treatment)
definitely technology can aid doctors, if they let it.. i don't think they will be replaced any time soon though...
once doctors realize they provide a service even if the machines make 99% accurate diagnosis people will still see doctors to make sure they're right, hear personalized advice etc.. doctors are more than just walking encylopedias of medical knowledge -- they should adapt quickly
Too much information is bad for some patients. For example there are books available to doctors which compile every medication available and what the results of the clinical trials were. Every result - from effect on symptoms to side-effects to placebo effects (the side-effects that the people given placebos developed) - in brutal detail. If you prescribe Foo(tm) for illness bar, and the patient looks and sees that a patient given a placebo Foo had a heart attack, what do you think they will do? The rare individual will say "Wow. Weird." and understand that Foo is perfectly safe. But the majority will run away screaming to another doctor and refuse treatment with Foo for the rest of their lives.
Everyone thinks that doctors are just data libraries and that anyone with the same information could do just as good a job. Not true. Most of the job is interpretation. That is why different doctors make different diagnoses. The doctors most respected by other doctors are those that consistently "see" things that others don't ("Well this looks like bar at first, but it reminds me of baz for some reason. Let's do some tests to check that out.").
Serve Gonk.
It's not at all uncommon for people to stop taking prescription drugs when they feel better. And to give the rest to friends or family members with similar symptoms, despite the fact that doing both of these can be very dangerous. Why? Because people "know what they're doing". If someone has the same symptoms as you, they must have the same illness, right?
Isn't it common for medical students, at the very start, to go looking for zebras when they hear hoofbeats? Well when you hear hoofbeats, chances are it just a horse, and doctors know that. But many times the students at the start go looking for odd diseases. All we need is for normal people to type "headache, sneezing, aches, tiredness" into a computer and see things like Bubonic Plague, Ebola, Haunta Virus, and other such things. Nothing spreads panic and fear like a little knowledge.
As the saying goes: "A little knowledge can be a dangerous thing"
Comment forecast: Bits of genius surrounded by a sea of mediocrity.
It's actually frequently worse than this. (I work currently with 8 doctors, four pediatricians, three internists, and one FP. I've worked with.... Problem two dozen over the last few years. What I say doesn't necessarily reflect on the ones I currently work with.)
Doctors have bad egos. Really bad. Many of them refuse to acknowledge the shear drudgery of their average daily workings. Like another poster said, every one of her kids visits were the same. Yeah, no kidding. 90-95% of the visits to our office are within a few categories. Colds, heart problems, diabetes, and checkups of various sorts. (There are a couple of others, but not many). Yet it is not at all unusual for doctors to rail at this sort of technology for even these cases. They cling to an absurd belief that each patient is different. That, to put it bluntly, is bullshit. Most patients are the same. This sort of tool would make the routine stuff go MUCH faster, and would help narrow down the weird stuff to where you are doing real tests to really differentiate between two different (or five, or whatever) diagnoses. Of course, when those weird cases are programmed...
Others in this topic have mentioned that docs embrace new tech. Kinda. They embrace new diagnostic tools that they can play with. But they are not as in love with decision making/helping tools. It undermines their education. It undermines the fact that most of them just have incredibly good 'wetware' databases.
I would also discount the actions/thoughts/ideas of younger docs. They frequently change by the time they hit their mid-30's. I've seen it before, I'll see it again. They love the idea when in school/fresh out, but come to believe in their own manifest godhood over time. No mere pile of silicon could be greater than I.
Another problem that I actually do sympathize with is that this is grounds for serious lawsuits. You could claim your doctor did nothing/wrong thing based on what some stupid machine said to do. Any rational person knows the doc shouldn't automatically trust what the machine spits out, but you and I also know that there will be at least one or two docs who, when these things gain wider use, will take an extra martini at lunch, counting on the machine to catch his stupidity, ignoring the fact that the man and machine have to work in concert.
Given the decision support software (the drug interaction databases are one example. The only problem is that EVERY reaction is typically flagged, so you need to know what's going on to interpret the data. Kinda like the discussion of SQUID and other NIDS the other day) I can forsee this making strides. But it will be some time. Twenty years? There are two scenarios where this will happen faster:
First, HMO's and other insurance companies use this software or something similar to find out how quickly their docs are zeroing in on diagnoses. If they find something that lets them diagnose in one visit instead of four, they'll use it. And that's good for them and good for the patient (cheaper, quicker, more accurate care). The other scenario is one wherein the government mandates this sort of testing. Likely it would manifest similar to the HMO model, and be used to cut costs of state-subsidized healthcare. Again, not a bad thing.
The better docs I have spoken with (and being raised by a physician, I've likely spoken with more physicians than the average slashdotter knows) wouldn't mind getting to deal with the tough or fringe cases. That is a challenge. That's interesting. Pap smears and kid shots are rote drudgery.
I hope we'll see this gain prevalence soon, but don't count on it. And, as the article says, docs are more likely than ANYONE to dig in their heels.
Jesus was all right but his disciples were thick and ordinary. -John Lennon
If you have to say something negative, then say it anonymously. I only use my account
when I am saying something simple. When I feel like speaking my mind, I post as anonymous.
Aslo, when you post anonymous, your karma will not be removed. The only drawback is that you have
to use search the website for your posts, to see if you have any replies, and this is hard, specially
when there are alot of posts or when you make a lot of posts to one story.
I looked at your user profile and you are not a troll. You just say things you feel like. I really
wouldn't say things you said, because I might annoy moderators. Infact, there are a couple of guys
who just hate me for what I write, even the stuff that gets modded up.
In slashdot, even if you appeal to the moderators and you oppinions are valued by them, or if you
provide informative links or tell funny jokes, still, there is someone who will hate you and stalk you.
Post anonymously, that is what I do these days. Having an account is a real hastle.
-56ker
Yet another signature block
As someone who will be graduating medical school in about a year, I can point out what my biggest hope/fear is with this kind of software -- and its not what readers have been suggesting in this thread up until now.
... time management. Most patients don't seem to realize what ridiculous time constraints we're on -- the massive patient load we need to see just to tread water and keep the HMOs/hospital adminstrators/etc happy.
The thing that makes me both intensely interested and worried about this method of diagnosis is
One of the most important parts of our training is learning how to balance diagnostic thoroughness with constant efficiency, and we learn all sorts of methods to do this. Any system like this software could seriously disrupt our breakneck pace, and its value is entirely unproven. Since the healthcare system is already stretched to its breaking point in the US, I worry that any changes that lower efficiency will send us into a tailspin.
Conversely, the idea that we could add such a powerful new tool to our arsenal seems like a dream come true. I would be thrilled to spend more time with each patient, to have a system that makes our diagnoses even more accurate and more focused, and to always be able to encompass the latest literature's suggestions and results.
The big hurdle to overcome in testing and implementing a system like this is getting the necessary volunteers. I'm not sure that I would be comfortable (when I'm about $300,000 in debt from medical school) being trained in such an unproven method of diagnostics. I suspect that most other medical students/schools, when faced with the uncertainty of the situation, would be equally reluctant to commit their money and their years to take such a risk when practicing modern medicine is already such an uncertain proposition.
I really take offense to the people here who state that "The AMA are just a bunch of money grubbing..." whatever. These people have no clue as to how much the average doctor gets paid these days.
As a resident ~ $37,000 a year for ~100 to 110 hours of work per week.
As a Primary care physician ~$180,000 for ~80 to 100 hours a week (of course this figure really depends on how much you want to work)
As a specialist ~ it really depends. Usually not above $300,000 a year
And that's after 4 years of college, 4 years of medical school, 3 years of residency, 3 years of fellowship and for some a couple of years post fellowship. And, remember that most people are in the hole ~$180,000 - $200,000 (including interest) after medical school.
So, in my particular case I'll be seeing $300,000 a year after 12 years of getting under mimimum wage. If anyone wanted to cut it more than that, well, then bye, bye medicine. You can go see the baseball players that get $5,000,000 a year (and still want to strike for more money) hooked up with a medical database.
That said, I think that the database is a good idea. Technology is our friend -- already my colleagues and I use software for the Palm platform which finds obscure drug interactions. The PKC is an extension of this kind of functionality. Change is good.
My wife has several medical problems. Each successive doctor would examine her for 1 fucking thing they "thought" it could be. When that test came back negative they'd send her on her way, "Nothing wrong here my diagnosis was negative". Pathetic fucks in my opinion. After seeing over 20 doctors a fucking eye doctor caught the problem that she said is realitively common and should have been caught by at least 1/2 the doctors (specialists for the most part).
In the end it's all about some asshole's ego because they (99.99%) lost the ability to care long ago. So in my opinion fuck all doctors because I trust my mechanic more than doctors.
Remember Pasteur? He had two PHDs, in Physics and
Chemistry, but because he was not am MD they REFUSED to accept that microbes cause ilnesses and that they have to work in a sterile environment!
Lots of beople died because of their arrogance!
Comment removed based on user account deletion
Databases are nothing new, the older forms are what we call "books". There is a reason medical students are required to do more than just memorize facts about the human body etc. They provide insight and experience in interpreting the facts/test results. I believe this could be a tool for them to use but very open to abuse. What if insurance companies and other type instituions opt for a cheaper alternative analysis simply because its plausable to reply on a computer?
thirsty*i^2
"Ya I finished that last week, it just doesn't work"
The only problem is that they track your IP address so you have to use proxies.
It's a conspiracy, Big brother is watching you.heh.
Anyway the problem is that I speak my mind about everything.
I guess that somehow talking about my water cooling case is trolling.
Microsoft.CLIT
This is not going to make you get payed less, or work harder.
Its a tool that will help you work smarter!
Like any other tool, how usefull it is to your is up to YOU.
"Consider how lucky you are that life has been good to you so far. Alternatively, if life hasn't been good to you so far
Think of it like this: Current medical diagnosis
is like proprietary software; Little 'chunks' of
high-priced, specialized knowledge scattered
across the globe. This 'Coupler' approach is
more like open-source, where people put their
efforts together for the good of society.
If so, which one do you want? Think about it.
What I hate about techies is that they think that eliminating the human part of the equation will make it flawless. "Nothing beats pure Data".
I'd bet that a very small fraction of the people on the board would trust their mother's care to a database. Of course, can you sue the database for misdiagnosing or missing something. NO, because you didn't give it the relevant data.
The issue here is that the combined use of the physician's skills and a database like this would be very powerful. Unfortunately filling out a LONG list of questions is time-prohibitive unless the patient does it for themselves.
The great thing is that most people on this board are not representative of the world. The rest are not willing to forego a physician's care because of their superior intellect.
Once the techie is in the emergency room with his twinkie-filled coronary arteries and a ten-ton elephant sitting on his chest - he'll be screaming for the best cardiologist money can buy.
Wait, wait you have to fill out the database.. the computer is better, your HMO says so...
FIX HEALTHCARE by fixing the mundane problems.
1) insurance
2) tort law
3) staffing
4) prevention
5) research
6) records / IT
7) education of doctors and patients
8) money
stop belly-aching about egotistical doctors, for every high-profile bastard physician there are twenty doctors who work very hard, destroy their own families and life to care for your families.
I hate hearing anecdotal bullshit that this database helped solve my rare sleep disorder that only 1 person in 5 million has. GREAT!
Does it make healthcare faster, more accurate and above all *CHEAPER*.... doubt it..
an Open Source project on it :-)
One problem with systems such as this (and there have been several such systems available since the 80's) is that the system can only recommend diagnoses that are in its database. If you answer all the questions appropriately and get a diagnosis with this system and the real diagnosis is not something the system knows about, then you may end up treating the wrong thing.
Additionally, the system will only be as good as the data that was used to create it and must be continuously kept up-to-date.
What I don't get it why herbal is "better." Wouldn't a chemical identified from an herbal source be a far more efficient and reliable cure than some plant that may or may not interact with other drugs you've been prescribed?
I Browse at +4 Flamebait
Open Source Sysadmin
I read the whole thing. and from what i can tell this is allready what we do in tech support (as a 3rd level tech)
get ALL the information who what when where why (that the 1st tech didnt) look at the history of the unit, what has been done, what hasent, Resolve the issue and test the resolution. I loved working for the company because it elliminated so much quess work ive seen at other places.
to me this knowledge coupler sounds awsome. i guess System Techs / Admins just dont have the ego's Dr's do, eh?
The More Knowledge you have the Luckier you Get- J.R. Ewing
I can easily picture myself querying the expert and finding out that I need a lobotomy. Without even questioning the answer, I still need someone to perform the cut, don't I? Moreover, if I am the least serious about my health, assuming that I work daily with computers/databases, I would not let the machine have the final word. But that's just me... Now, you can argue that very soon we could have the mechanical arm that would perform the operation right away... Why not? Are you a volunteer for the early tests? ;-)
10-15 years ago the same was true about Russia, lots of students from Asia and Africa went there to get free medical education. I dont know what is going on right now, though.
This is a concern for sure.
Another is privacy. Imagine your employer
getting access to your medical record or
simply noting a few things about you,
running an internet diagnosis and seeing
that there is a small probability you
got cancer/hiv/paranoia/...
Just seeing that as an option will raise
flags. Or imagine the rumors that will
circulate in the workplace behind your back
for no good reason. Anyhow, like anything
else this has its downside too.
Well, this happened over one hundred years ago!
...blind tests were pretty straightforward. Anyone who walked into the wall without first flinching, was.
Am I the only one who heard Roxette to sing "I'm gonna get blitzed for some sex"?
Who cares about Pasteur. He did not practice medicine, did not make $200k/year, therefore he was a loser!
I wonder if the software gives bad advice you could not only sure the doctor going by its recomendations but also sue the software maker. Does the software come with a EULA that would protect it. Would it stand up in a court challenge ... Trial lawyers woudl have a fieldday.
hell some of the doctors would probably cheer them on to kill the software.
just my 2 cents
How dare you!
Although Pasteur was not an MD, Dr. Pasteur did more for the progress of medicine than one thousand MDs!
But I have to point out that this is another fine example of the cult of higher education at work:
"But, according to Cross, the neurologist who originally diagnosed the case as an REM sleep disorder had a very different reaction to the use of the software. When the plumber and his wife handed that doctor the PKC printouts, he shuffled them, left the room, and, Cross says, "returned with a very hostile, angry disposition." Viewing the results as computer-generated quackery, he refused to back down from his original diagnosis. "
This is a fine example of priest-like behavior from our friend, the university graduate. The Holy Word comes only from the university, and must not be questioned. It is handed down from pries to cult member, who will become the next priest.
Do not question the priest; he doesn't want you to know everything he knows is a facade, and that he doesn't really know what's going on. It's a power play, he doesn't want to feel like he wasted 10 years at university for nothing.
It's better to perpetuate the myth of university education than to come clean.
One of the things that get me excited about this is that the PKC could (but doesn't yet) have all sorts of information that normally would be out of the realm of your average doctor's personal knowledge base. On the other hand, I would think it wonderful that the doctor could pull up normal diagnoses--and the computer also say what a person who was a trained homeopath would say, or a trained doctor in traditional chinese medicine, or someone who was an Ayurvedic doctor, et cetera. The doctor could then leverage all that knowledge into more advanced solutions--even if their training wasn't necessarily in that field.
Having said all that, I think one of the main uses of a doctor is their intuition--and that isn't exactly replaceable by a computer.
http://www.smh.com.au/articles/2002/07/14/10261851 41232.html
America, land of the free!
I am a former computer programmer, having completed medical school at a University of California and now finishing a residency at an Ivy-League university. What surprised me in reading this article is that no randomised controlled trial has been done using this program. Have 2 sets of patients, one group cared for by physicians using the "Knowledge Coupler" and another set cared for by physicians not using this program. Follow their health care for 5 years and see which group is more healthy, and also which group consumed fewest health care resources (ie, money). (Sorry to have to say that last part, but it is a fact of modern health care that it must be delivered as cheaply as possible.) At the end of 5 years, compare the groups in terms of morbidity, mortality, and expense. We may find that the Knowledge coupler does not add to the health care patients are already receiving, while increasing the expense considerably.
I would also point out that many hospitals are now routinely browsing their medical records to find out which patients are receiving sub-standard care, and also are re-educating those physicians who are delivering sub-standard care. The treatment of diabetic patients, especially, is being examined.
What was not mentioned in the article (at least not in my skimming), and what would be mentioned in any important journal article, was Dr. Weeds financial relationship with the Knowledge Coupler.
Finally, we have had Knowledge Couplers since the dawn of medicine. They are called experts. If a neurologist does not know a diagnosis, he presents the case to another neurologist. At a tertiary or quaternary medical center, the case could reach the world's expert. I suspect that the reaction of the neurologist in the article represents that individual's personality deficits and is not a truism regarding medical professionals. Everyone who has made it through medical school and residency with sometimes amazingly bright people is humbled by the experience, and painfully aware of their own shortcomings.
I have a book on removing brain tumors. Can I operate on your mother? No I've never done it before. But hey the book shows all the steps pretty in colorful illustrations.
.. get real.
.. though I thing my kidneys are in my balls)
Having a computer diagnose disease is stupid. They cant even understand handwriting or figure out basic sentences and you expect them to be able to diagnose disease
If a computer asks you "does the swelling feel hard or moderately hard?" or "Does the skin feel very rough or moderately rough?" You need to be an EXPERIENCED doctor to even understand the symptoms. Remember computers are garbage in garbage out.
Computer: does your kidneys hurt?
You: yeah it hurts (i think
Computer: Does your head hurt a lot?
You: Yeah
Computer: You have a brain tumor get chemotherapy
Give it wrong info, an you'll get a wrong diagnosis.
You'll still need doctors.
I have a book on removing brain tumors. Can I operate on your mother? No I've never done it before. But hey the book shows all the steps pretty in colorful illustrations.
.. get real.
.. though I thing my kidneys are in my balls)
Having a computer diagnose disease is stupid. They cant even understand handwriting or figure out basic sentences and you expect them to be able to diagnose disease
If a computer asks you "does the swelling feel hard or moderately hard?" or "Does the skin feel very rough or moderately rough?" You need to be an EXPERIENCED doctor to even understand the symptoms. Remember computers are garbage in garbage out.
Computer: does your kidneys hurt?
You: yeah it hurts (i think
Computer: Does your head hurt a lot?
You: Yeah
Computer: You have a brain tumor get chemotherapy
Give it wrong info, an you'll get a wrong diagnosis.
You'll still need doctors.
How many people go to Cuba (or other communist countries) to get diagnosed when they are sick?
Personally I have an immune defficency that is somewhat rare. This paticular immune defficency does not start until later on in life (20 to 30 yrs old) Most patients have a history of pnuemonia and infections in the head (ear, sinuses, etc.) I lucked out and was seen by a prof./doctor at Johns Hopkins. I went to him with one serious illness and once I was over that I was back in his office with a pnuemonia that required hospitilization. Not only did he see the obvious there must be something more to this, but he was able to guess what it probably was. This is most likely due to the fact that he writes a book for med students and is constantly re-framiliarizing himself with the rarer conditions. So after what in hindsight was about six months with this condition I was diagnosed with this immune defficency. The average patient isn't diagnosed until they have had it for more than a few years. As one of the nurses who administred the infusion to treat the immune defficency it was a miracle I was diagnosed so soon.
My new doctor, due to change in location, doesn't feel that he would have caught on to what was going on. He learned about the immune defficency back in med school, but was never seeing any cases in his practice so the knowledge never jumped to his mind while looking at patients. Luckily I saw a doctor who was looking at most of the possible problems I could have had. Hopefully this software or software like it will enable patients with rearer conditions to be able to be diagnosed a lot sooner. Which in the end prolongs life and potentially saves lives.
To put this into a perspective the /. crowd will understand (no, it doesn't involve first posting or Natalie Portman and hot grits). What doctors do today is the equivalent of reading a programming language reference manual and then coding in that language using only memory and using compiler messages to work out when you get something right. Sure, after you have been programming in a language for 10 years you could do this but you'll still need to refer to the reference manuals occasionally when venturing into unfamiliar territory.
Using computers to do this is much more effective than trying to write programs that do the diagnosis. Computers can't reason, humans can (well most can ... ok some). To quote Dijkstra, "The question of whether a computer can think is no more interesting than the question of whether a submarine can swim."
Nerd: Derogatory term typically directed at anybody with a lower Slashdot ID than you.
Not to Cuba; Russia however has good medical doctors. They were pioneers in eye surgery, etc
That's how it is with every person I know in the KC chapter of the celiac sprue support group - self-diagnosis after jacking around for a year or two with doctors.
IMHO if a computer program can put the facts together faster and explain its reasoning, I'll go to it before a I would go to a human doctor.
Stop the Slashdot Effect! Don't read the articles!
The article was completely bereft of technical information...
Naive Bayes? Pure Term Frquency/Inverse Doc Freq IR techniques? Knowledge Based?
The earliest expert systems I know of was in the medical domain (EMYCIN), yet as far as I know it was regarded as very brittle.
I'd be a little less skeptical if there was some information on its basic operation....
Winton
Anyway, of those four diagnoses, three were wrong. Based on that, it sure doesn't sound like diagnoses are easy to me! Add to that the fact that I'm pretty good at troubleshooting and I'm one of the few that I know of. Most people flail about trying things at random and, as far as I know, training isn't much help for most of those people. Yes, it's easy to memorize a few pat answers to the most common problems, which is why many people who visit the "doctor" wind up seeing a PA, who forwards to the doctor only those cases whose diagnosis is in doubt, but that's exactly why this sort of thing is important. As time goes on, doctors are going to be less and less likely to see the simple cases.
You mention psychiatric diagnosis, so I'll talk about those. A quick check of my local DMDA chapter shows that some 70% of those suffering from some serious mental illness were misdiagnosed at least once. I can't help but think that a computer program that prompts the asking questions about typical symptoms of mania and schizophrenia would reduce that because most of the misdiagnoses start as a diagnosis of depression because it's what people complain about. I know the doctors don't ask those questions because in the sample that I have (8 so far) none have asked the right questions to make what we (that is, myself and the ill person) now believe is the correct diagnosis.
In any case, since visiting a doctor (and I spend a lot of my time in doctors' waiting rooms so I know this quite well) is something like an hour waiting to see the doctor followed by maybe 10 minutes of answering questions I don't understand, filling out the forms while I wait can't do me any harm even if the diagnosis is not remotely in doubt or irrelevant to the treatment, can it? I mean, it becomes part of the patient history just like the temperature and blood pressure check you're going to do whether I come in with a fever or with a splinter, right?
Heck, I suggest you put terminals tied into that database in the ER waiting room so there'll be something to do while you're waiting the 4-6 hours (on average) it'll take to get to the head of the line.
I've been through a personal hell myself lately. I have a pain in my lower abdomen which has been mis-diagnosed twice and they still don't know what is is. For an entire week I peed through a screen and gritted my teeth thinking I was going to 'pop a rock' (turned out NOT to be kidney stones). I believe at this point I'm just fodder for the CAT lab so they can make money off my insurance company.
And 2 years ago I passed out and was taken to the emergency room where they ran a heart cath into me! Turned out I was just dehydrated. A HEART CATH!
Now I don't believe the diagnosis database should ever be a primary tool, but as a tool to get the doctors into the same neighborhood that the clues live in - I think it's valuable.
I know a few doctors and they'll never say this, but they'd use the hell outta something like that - just not while anyone was looking.
Cake or Death? Cake Please!
After reading the article, I surmise that Dr. Weed may have some ego problem as well.
I submit that most doctors and specialists are reasonably effective in their jobs because MOST of the commonly seen diseases are covered adequately in their trainings. Where Dr. Weed's system can help is in rare diseases and where the patient have a history that the doctor is unfamiliar with ( say moved from a foreign country ). Thus, the most that this system can help are the rare cases which would NOT lead to a disruptive change in a diagnostic sense.
However, the article shows a secondary effect which CAN accelerate a disruptive change that is already taking place: the increasing situations where the patient take an active role in diagnoses and treatment. Not only does this empower the patient psychologically, it makes the patient much more willing to buy into the treatment. THIS to me, is the major benefit rather than the putative diagnostic accuracy.
Of course, this does require the doctors to give up some power in the relationship. What might be the catalyst for that to happen quickyl ?
And people say that computer programming is a black art! Medicine is almost entirely guesswork based on percentages. The arrogance of the medical profession continues to astound me. You have a fever? Antibiotics. You have a cough? More antibiotics? Antibiotics don't work? It must be a virus. Let it run its course. It does not matter if they are right or wrong - they get paid for every visit and every prescription. They feel inconvenienced by your very visit. Am I bitter? I sure am. Me and the rest of the population. I'm all for computer assisted diagnosis if it will make more people well. Doctors' egos be damned.
"IAAI (I am an idiot)"
You certainly are. What were seeing here is stereotypical attacks on doctors, due to the strict way the medical profession and services are dealt with.
Imagine for a moment that there was a database created that contained almost every single set of expressions and solutions for (insert your programming language here).
So instead of having software companies and hordes or programmers, companies can get their own software by feeding in to the requirements to this database, and it spits out the necessary code.
Now imagine the outrage you would have amongst programmers and software houses around the world, since they are now effectively redundant.
Just because some doctors are highly paid, and have strict controls on the medical services, doesn't mean their views and outrage should be held contemptable, until you have fully assessed the pro's and cons. You bet your bottom dollar slashdot would give programmers the benefit of the doubt in above situation, so why can't we give doctors some leeway and a reduction of ad-hominem attacks here?
Slashbots: Jealous, selfish and unreasonable. Get over yourself.
Think nothing is impossible? Try slamming a revolving door.
"If a diagnosis is the easy part of medicine, then how come it's so often wrong?"
1) Because every single person is different. Every disease can present differently is different people.
2) Lack of time. An average family doc spends about 8 minutes per patient. This is due to a number of things. You actually have to earn enough money to pay for your practice and have a salary on top of that. There are way more sick people than there are time and resources to treat them. Obviously it would be great to meet with every patient and their family for an hour, but it's not practical, so there is a trade off. In this short span of time things will be missed. That's a shortcoming of the system not the physician.
3) Lab tests are expensive and these costs are born by the indiviual, insurance companies, or the government, all of whom have a vested interest in keeping costs low. You don't test for rare diseases, unles there is an overwhelming reason to do so, simply because the above groups cannot or will not pay.
4) There are bad physicians. Fact of life.
Personally I think that this database would be useful, although I doubt that there would be much in there that doesn't exist in the literature already.
What I object to is the portrayal of physicians as bumbling buffoons bent on preserving their undeserved elite status at the cost of proper health care.
People expect too much from a family physican. They cannot possibly know enough to accurately treat and diagnose every problem. The database described already exists in the form of medical encyclopediae and internet databases and colleague's advice. Using these resources physicans are mostly right most of the time. It is unreasonable to expect more than that.
If a doctor tries and succeeds in shifting blame onto the Machine, then the Big Coporation that made the machine would probably be open to a portion of the liability. In the end, the damage should be the same as before but shared between the parties.
Well if cars, that are very much less complex than humans, can benfit from diagnostic software, why the hell not?
Always going forward, 'cause we can't find reverse.
"You doctors usually prescribe antibiotics and a decongestant for runny noses. Stop that, it's counterproductive. The runny nose is most likely a viral infection or an allergic reaction to something so antibiotics aren't indicated and I don't like the side effects most decongestants have so I won't take them. That is, in fact, why I've long since stopped seeing doctors because of runny noses."
The reason that most doctors prescribe antibiotics when they shouldn't is not because they are so ignorant that they don't understand their ineffectiveness, but because patients DEMAND a magic pill.
Most people don't share your enlightened view of viral vs. bacterial infections and think that antibiotics will make them better regardless of the type of infection.
Although not the best decision, many doctors will prefer to keep their patient happy by prescribing something because that's what the patient has come to expect. Many people would be very unhappy about waiting for a week to get an appointment, then waiting a hour to see the doctor only to be told, "just go home and rest. There's nothing I can do."
So the physician may aquiesce so as not to lose patients and hurt relationships of trust that he has built.
Diagnosis Sheet:
X Cold
X Influenza
(Circle one, prescribe asprin or tylenol)
If you have unexplained symptoms, nowadays its better to visit the doc once and get your aspirin and maybe the decongestant that you will ALWAYS be prescribed. Then either wait until your symptoms go away by themselves (could take years), or you start developing emergency type symptoms like high blood pressure, difficulty breathing, seizures. At this point the MDs become liable and may actually try to figure out what's wrong with you. While you may feel sick and/or hurt, MDs see people DIE every day, or who have lost 95% of their skin, or whatever, and your sniffles, headaches, or dizziness are not really as big a deal to them as it is to you.
Oh yeah, on the topic of medical databases. Doctors are expected to read journals and medical studies, but many times they just stop as soon as they get out of school. Its not that they don't like new technology, they just shun everything new. New studies, new papers, new equipment, new techniques. The reasoning is, "hey I'm not in school anymore."
Most people see doctors as their last line of defense from disease, their savior. But in reality doctors are in the business of making money just like everyone else. The more $$$ you have the better the diagnosis and treatment. Not everyone gets to go Mayo or Johns Hopkins.
Mod down all you want, I'm just the messenger.
That reminds me of the Kurt Vonnegut novel with "Mandrax." Does that mean we have to learn Sweedish now?
I'm sure that part of the resistance that doctors express to software like the Coupler comes from feeling threatened; however, a good deal of the resistance also has its roots in the very nature of how doctors view technology.
/. community are generally people whose lives are intertwined in their technology and their tools. Physicians, as a whole, are generally not that way; they instinctively mistrust technology that they haven't seen tested into the ground and then some. Many doctors offices still use paper files to track cases and medical information, because they don't trust their computers to hang on to that valuable and confidential information. (Not all doctors are so technophobic; my last pulmonologist kept much of his case information on his Palm Pilot and loved playing around with the spirometry software that he loaded onto this Win2K machine; I tried convincing him of the value of OSS, but he wanted to wait until retirement before risking something like that. He's retired now, so I think he's off in the midwest doing his first Linux installation.)
I used to work pretty closely with software meant to be used by doctors, and saw many of the results of the focus groups our managers conducted with the physicians. An interesting fact emerged: most doctors see technology, especially computer software, as unreliable. Think about it: when you're mucking around in someone's head, removing a tumor from their brain, you don't want a tool that's still in 'beta testing"; you want something that has been proven accurate and reliable and absolutely perfect 100% of the time, without a single flaw. So when you're using a software tool that can diagnose conditions and even recommend treatment (including medication), you're going to be extra careful, and probably not even consider what the software has to say. At best, you might think of it as a list of possibilities, but not the final word.
Doctors trust their instincts and their education and training over technology. When a doctor purchases a piece of software like the Coupler, she has no idea who built the database behind it. Was it a trained physician who graduated top of the class at Harvard or Yale? Or some computer programmer sitting in a cubicle in some office somewhere, reading a textbook?
The folks of the
So this article doesn't take me by surprise at all. I'd be much, MUCH more surprised if I'd read that doctors all over the world are embracing a new piece of software like this whole-heartedly and without reservation.
-- The reason it's called the right wing? Irony.
I met Larry Weed when I ran Intel's Internet Health Division. He's a great and insightful man, and his systems, in my non-medical opinion, have a valuable place in medical diagnostics.
On the other hand, Larry has pissed off enough people, and is sufficiently single-minded in his endeavors, that I am afraid he won't succeed until someone else has repackaged his ideas in forms more palatable to the establishment. One very odd thing is that the "evidence-based medicine" crowd (treatments based soley on clinically provable science, vs. "this is how we've always done it") doesn't get behind his ideas.
Larry's system is clearly a component of a radically different medical system, but I don't think it's the only component. That's the thing that's missing. The MD who commented earlier has some good points, but the medical profession can't shift all the blame onto the finacing system, etc.
- gnet (I am not a Doctor) werker
The advent of the palm pilot has given birth to phalanxes of residents and students wielding their PDA's and tapping furiously with their styli when asked a question by the attending physician. Doctors are often asking them to put away their PDA's so they can't look up the answers.
I think that much of a doctor's profiency stems for the vast bulk of knowledge they have accumulated through their careers. They can use this knowlege quickly and precisely and get the job done. Unfortunately, many up and coming doctors are relying on their PDA's as a crutch, leaving on their PDA's what should be in their heads.
I submit to your consideration that a part of the reluctance to use this type of a system stems from the fear that physicians might rely too much on it. It is often said that medicine is a science (database of knowledge) and an art (use of intuition, personal experience, and good judgement.) It is important to find a balance between the two.
PDA's and the like are great resources. The database spoken of might be of use as well, (if there were the time to consult it with every patient). But I think there is a fine line between relying on a stored database of knowledge and using your own skills and intuition. Many don't know where they would put this line, so they instinctively turn to what has worked in the past and are sceptical about new unproven things.
The ego problem with physicians that has been brought up several times definately exists, but I doubt that it is the entire reason for doctors' reluctance to embrace this proposed database.
Plus by giving the patients unecessary medication, the doctor stays on the drug company's good side.
Of course that begs the question of whether or not this software is open source or not. It seems that even if the underlying softwre isn't the database itself(the facts) probably is/should be.
If Mr. Edison had thought smarter he wouldn't sweat as much. --Nikola Tesla
Indeed. But perhaps having information "in the literature" isn't terribly useful if the doctor doesn't have time to look it up. If the doctor has only 8 minutes to spend on each patient, I imagine a program like this could be very helpful -- sort of like a quick check for something on Google instead of having to trek down to the library for an hour or two.
Using these resources physicans are mostly right most of the time. It is unreasonable to expect more than that.
Given that a physician only has so much time in his work day, the less time it takes to look up things in the literature, the more queries he can make, and therefore the better quality his diagnoses will be.
I don't care if it's 90,000 hectares. That lake was not my doing.
Expert systems are nothing new. MYCIN (a drug interactions expert system) was developed in the 70's. Essentially, they're huge checklists developed by picking physician's brains, to create a system that would model a doctor's diagnosis procedure. However, it looks like only now, with the widespread use of computers, and a way of hooking them all together, is this technology getting into the mainstream.
Keep in mind though, real doctors have to keep updating the system to reflect new technology and new research (something real doctors have to do for themselves.) As such, there will still be demand for the best and brightest - and for the rest, they can use an expert system to help cover the bases (for liability reasons, I envision that final diagnosis will still need to be made by a real, certified doctor.) Too bad real AI, the kind that could make decisions and adapt to new situations (self-learning, possibly self-aware) is still a long ways off...
Personally I think that this database would be useful, although I doubt that there would be much in there that doesn't exist in the literature already.
Ummm, one of the main points is that "the literature" is so huge that no one human being can be expected to know it all and apply it, and there is lots of evidence to back that up.
What I object to is the portrayal of physicians as bumbling buffoons bent on preserving their undeserved elite status at the cost of proper health care.
I didn't see anything about "bumbling buffoons", merely human beings reacting instinctively to something new that may affect the status quo to an uncertain degree, mixed in with healthy "show me the proof/evidence" type reactions.
People expect too much from a family physican. They cannot possibly know enough to accurately treat and diagnose every problem. The database described already exists in the form of medical encyclopediae and internet databases and colleague's advice. Using these resources physicans are mostly right most of the time. It is unreasonable to expect more than that.
Now this I object to. First you say that they can't know it all and diagnose everything, then you say they can with these other resources and the literature, which evidence shows one individual can't possibly have fully covered since it becoming so extensive.
No, I don't expect a simple human being to be perfect. But I strongly expect, nay DEMAND that you adopt any proven method that increases your effectiveness, and I object to anyone who obtusely reacts with gut feelings and animal instincts to change as a "threat".
If in major case studies this tool is proven to be a significant help when used in a specific way, would you adopt it?
Or would you insist on the continued use of leeches for those with fever?
Symptoms : Headache, blurred vision, nausea, furry tongue
Patient drank gin and water till late last night
Prescribe aspirin and fluids.
Visit #2
Symptoms : Headache, blurred vision, nausea, furry tongue
Patient drank whiskey and water till late last night
Prescribe aspirin and fluids.
Visit #3
Symptoms : Headache, blurred vision, nausea, furry tongue
Patient drank rum and water till late last night
Final diagnosis
Patient is allergic to water.
Wouldn't it be nice if this kind of rich database tool were available to you when dealing with the complexities of the financial system or even government.
/. post to reply to ;^)
These other systems can be similarily as complex as the human body, and the kind of solution searching they use surely could be used in other applications.
Finance especially could benefit. Each individual is balancing their future whenever they make a financial decision, and yet the possibilities, options and permutations seem countless. To have a nice question based system that finds out about your real situation (what you have saved, where it's saved, where you live, what programs are applicable, what _could_ be applicable, etc.) could really improve one's ability to build a stronger financial future for themselves.
How about other applications like education directions/paths, job/career moves, which
And finally, it's always been a dream of mine that one day I'll be able to walk into a government office and actually be treated as a unique citizen with my own unique set of problems.
Life has many complex systems that one day will bow to our newest tools, thankfully.
Oliver's Law: Experience is something you don't get until just after you need it.
I hate to come off cold and unfeeling here -- gosh, I wouldn't want that -- but let's get real for a moment...
A whole industry exists to teach students how
to get into medical school - to exploit its
weaknesses. Medicine is a place where arrogance,
confidence, and power dominates. The "caring
doctor" is a myth.
Is this a BAD thing? Really? Given the importance of what doctors do, I personally would like to see the field attract the sharpest minds possible. People with confidence. Power. Intellect. If you are willing to accept for a moment that there is a distribution of talent/abilities out there; that certain people possess intelligence, drive, stamina in greater quanities than others...why is it so wrong to set up a system that seeks out, attracts and rewards these traits?
The "caring doctor" is a myth.
Frankly, I don't care all that much if my doctor is not selected on the basis of her caring behavior. Yes, it is nice. Yes, I feel good knowing that my sick mother is treated respectfully by her doctor. But ultimately, I want her to see a doctor who is COMPETENT.
BTW, without giving a full-blown personality
inventory to each applicant its impossible to
select for caring behaviour. Rather, schools
select for the appearance of such behaviour...
Agreed and agreed. You and I both seem to agree that it would be next to impossible to screen for this. So what do you propose? And what problem are you trying to remedy here, anyway? While the "user experience" might be less pleasant for some patients who would prefer touchy feely doctors, MEDICINE as a whole benefits from having more competent people in the profession, people who tend to display this behavior. It could be aruged either way (you obviously for, me obviously opposed) whether testing for "caring behavior" would produce better doctors...What doesn't appear to be in question is that there is no real mechanism to do this. I for one won't waste my time worrying about it...
I would have to say that explosives are the most abused technology in all of history.
Surely the point is that this is a very sophisticated index to the literature.
What I object to is the portrayal of physicians as bumbling buffoons bent on preserving their undeserved elite status at the cost of proper health care.
As a potential victim^H^H^H^H^H^Hpatient, what frightens me is that parts of the medical profession found it necessary to advance the exciting new idea of `evidence based medicine' so recently. After thousands of years, suddenly some small number of them think it might be interesting to actually base their actions on the real world, not what they were told in school.
_O_
.|< The named which can be named is not the true named
Unfortunately you are demonstrating the common fault of physicians today. At the turn of the century 2 out of 3 health care workers were physicians. Now it is 1 in 12. Instead of being the captain of the ship your field has become a small part of a large repetoire of personal. It is difficult for physicians to realize this information, but physicians usually serve one of two purposes 1) the diagnosis (all the other functions that you list are typically not done by the physician, but the nurses, the physical therapists, the pharmacist, the nurse anaethesists, and everyone else), or 2) most typically the püatients knows the diagnosis and needs the physicians agreement before they can receive the proper treatment. Unfortunately (for physicians) more and more patients are becoming educated through other means, which results with the doctor being necessary for even less than what they were needed for before! Legalize most prescription drugs and you will reduce the need for physicians!! Or more logically separate the power of diagnosising and prescribing. The physician should only diagnosis, and leave the prescribing for the knowledgeable ones, the pharmicists!
AI systems for inference or classification (as this is the case here) work either rule-based or statistical-based. In both cases, the knowledge contained in the database must be acquired somehow. Automatically training such a database is a hard thing to do, because you need valid data in machine-readable form: that is a database full of found symptoms and the diagnosed disease. Such data probably exists for the simple-to-diagnose diseases that are well-known, but not for rare diseases as mentioned in the article.
So, we end up squeezing our knowledge into the computer. But - who does that?
Can the doctors who enter their knowledge into the machine be held responsible for mistakes? Even for mistakes that occured simply because the knowledge is overcome?
In AI research, more and more people acknowledge that we can't fit our full knowledge into a database. One reason for that is that we can't even spell out 'tacit knowledge' (or: implicit knowledge) the way we need to when giving the computer rule-based knowledge to solve a problem.
A doctor learns to have a feeling about a patient: this intuition can't be replaced, at least not within the next 20 years...
One day Bill complained to his friend, "My elbow really hurts, I guess I should see a doctor."
His friend said, "Don't do that. There's a computer at the drug store that can diagnose anything quicker and cheaper than a doctor. Just put in a sample of your urine and the computer will diagnose your problem and tell you what you can do about it. It only costs ten dollars."
Bill figured he had nothing to lose, so he filled a jar with a urine sample and went to the drug store. Finding the computer, he poured in the sample and deposited the $10. The computer started making some noise and various lights started flashing. After a brief pause out popped a small slip of paper on which was
printed:
You have tennis elbow.
Soak your arm in warm water.
Avoid heavy lifting.
It will be better in two weeks.
Late that evening while thinking how amazing this new technology was and how it would change medical science forever, he began to wonder if this machine could be fooled. He decided to give it a try. He mixed together some tap water, a stool sample from his dog, and urine samples from his wife and daughter. To top it off, he masturbated into the concoction. He went back to the drug store, located the machine,
poured in the sample, and deposited the $10. The computer made the usual noise and printed out the following message:
Your tap water is too hard.
Get a water softener.
Your dog has worms.
Get him vitamins.
Your daughter is using cocaine.
Put her in a rehabilitation clinic.
Your wife is pregnant with twin girls.
They aren't yours.
Get a lawyer.
And if you don't stop jerking off, your
tennis elbow will never get better."
Go to http://www.pkc.com to find out even more about these knowledge couplers.
For one, these things are Windows software, with a web access version. Also, you subscribe to these things to get the semi-annual updates.
If Mr. Edison had thought smarter he wouldn't sweat as much. --Nikola Tesla
I work for a Medical Practice Management Group, we do outsourcing for medical offices. The reason that most of these applications (which BTW have existed for years) do not get used is that: 1) A system like this requires lots of GOOD data (remeber crap in = crap out) and 2)there is no-re-imbursement for the physician for paying to have someone input all this data into a system of this type. Its all about re-imbursement, that is what drives the system, if docs don't get paid for it from either insurance companies, medicare, or patients, then its not going to happen.
Rule of Life Number 2: Remember, it can all go to hell at any minute. --Jimmy Buffet
...is, what would have Dr. McCoy said?
:D
But if it's some old 486, just as well. At any rate, I think this is a very good idea, as long as nobody even thinks of
No, seriously. Everytime I visit a doctor, I usually have to wait up to an hour, and in that time I usually have nothing else to do but to read century-old magazines, and the same goes for most people. Most are annoyed and bored. I think if in that time you'd be spending your time on a computer answering questions, thus helping the doctor, it would be a better way to spend your time.
As a geek, of course I'd love to be working with a letter-sized tablet pc and a pen
a) replacing doctors with computers (which doesn't seem to be the case) and
b) entirely relying on the information from the database - it was compiled by humans and thus contain errors...
If a train station is a place where a train stops, what's a workstation?
"After thousands of years"
Thousands of years? The medical profession as we know it know has barely existed for 100 years let alone thousands. The medicine of today is very different than that of 10 years ago and radically different from that of 30 years ago. I don't think this fits the plodding pace you are trying to portray. The medicine I know is advancing so rapidly that a docotor must study his whole career to keep up... I think that the medical community is rather quick to emprace new things, once they have been proven.
"what they were told in school"
Have you been to medical school? Do you know what is being taught there? Is this a valid opinion or empty rhetoric?
"suddenly some small number of them think it might be interesting to actually base their actions on the real world"
Some small number? it seems to me that quite a large number favor this approach. So much so that all of medicine is converting to this approach.
"Personally I think that this database would be useful, although I doubt that there would be much in there that doesn't exist in the literature already.
Surely the point is that this is a very sophisticated index to the literature"
A very valid point
to clarify
"Ummm, one of the main points is that "the literature" is so huge that no one human being can be expected to know it all and apply it, and there is lots of evidence to back that up."
When I refer to the 'literature' I also refer to the very excellent indexing and cross referencing systems that already exist. My point is not that one is required to know everything, but the knowledge exists if you want to access it and it is very easy to do.
Now this I object to. First you say that they can't know it all and diagnose everything, then you say they can with these other resources and the literature, which evidence shows one individual can't possibly have fully covered since it becoming so extensive.
Sorry, I made two points in there that weren't very clear.
Point 1) you can't know it all and diagnose everything because the scientific community doesn't know everything yet.
Point 2) this database idea is not as radical as it seems since any physician worth his salt can already get the same information with current technology.
"If in major case studies this tool is proven to be a significant help when used in a specific way, would you adopt it?"
Yes, I'm merely saying I doubt it's as revolutionary as it seems.
If the doctor has only 8 minutes to spend on each patient, I imagine a program like this could be very helpful
But those 8 minutes are already full of spending time with the patient. Thtat 8 minutes is the bare minimum that the doctor can spare. The point I want to make is that there is little extra time to integrate this sort of thing with every patient as the story proposes.
Given that a physician only has so much time in his work day, the less time it takes to look up things in the literature, the more queries he can make, and therefore the better quality his diagnoses will be.
Very true.
Isn't this just a way of saying that for thousands of years they were so bad that physicians today are embarassed to admit kinship? No doubt a couple of generations from now when (hopefully) the majority of doctors are relying on evidence not voodoo, they will be saying that `medicine as we know it' has only existed since 2000 or so.
Some small number? it seems to me that quite a large number favor this approach. So much so that all of medicine is converting to this approach.
Doesn't it strike you as shameful that they have to convert to working based on the evidence? It's an admission that up until now they have been running on old wives tales and whatever is being advertised heavily.
As for quite a large number, if I went into some random GP in Europe or North America complaining of sneezes etc. and was prescribed the seemingly inevitable antibiotics, what do you think the odds are that the GP would be able to cite me evidence for the effectiveness of antibiotics against the common cold?
_O_
.|< The named which can be named is not the true named
Are you sure those are really antibiotics??
There are plenty of placebos that a doctor can describe, and they look exactly like antibiotics to the patient, right down to the patient information leaflet inside.
I would hope that doctors who need to give patients a prescription to keep them happy are giving them a placebo and not an antibiotic.
-----
What doctors? In only one or two more generations they'll (hopefully) be mostly out of work thanks to the "miracle" of the Artificial Immune System and self-repair nanotechnology.
Any virus, bacteria, pollen, spores, molds, drugs, unwanted sperm, smoke, etc., would be neutralized the instant it bumped into a SuperWhitey(TM) if it wasn't on the trusted whitelist (Palladium for your body--parents could even prevent their kids from getting high).
And if you break your (non-reinforced) leg? Why wait for your normal body functions to repair the damage when it can be fixed by an "intelligent swarm" on the molecular level in no time.
Another few generations and humans should have finally ditched their frail wetware anyway.
Thanks for providing the trigger for my mental masturbation. :)
--
Power to the Peaceful
I have never heard of a doctor prescribing a placebo.
Being to lazy to read the linked material (c'mon, who isn't?) my fear of computer-assisted diagnosis is self-fulfilling prognosis.
I'm sorry sir, the computer says you basically have a zero percent chance of surviving this (because last year it said 1 percent and thus we didn't bother to treat anybody). Let's discuss your affordable hospice options ...
Doesn't it strike you as shameful that they have to convert to working based on the evidence? It's an admission that up until now they have been running on old wives tales and whatever is being advertised heavily.
Not at all. When a new advance comes along one would be foolish not to use it. Saying that they should have been using it all along is pointless. There is a saying "a wise man will change his mind, but a fool never will."
non "evidence-based medicine" does not mean it is not based on evidence. It only means that it has never been formally tested in a double blind, randomized, controlled trial. They are many life saving procedures and practices in medicine today that have never undergone rigourous scientific testing. Someone tried it, it worked, and still works, and they will keep doing that until something better comes along.
Many drugs that are used to treat are there becuase they were 'stumbled upon' by accident as it were. Little is known about how they work, but they will continued to be used. Medicine is being refined and improved all the time.
There are very few 'old wives tales' out there. Much of past medicine was based on a physician's personal experince. Granted, this is not a rigourous enough criteria to apply to a therapy today, but it is a far cry from an 'old wives tale'
As for your "running on whatever is being advertized heavily," that sounds like empty rhetoric to me. I'd like to see some evidence to back up that claim.
Powered by nuclear power too cheap to meter no doubt:-).
_O_
.|< The named which can be named is not the true named
My website is down at the moment, but when it comes back up I'll be posting a new page of links for Weed and PKC: [timeline]
I'm sure many comments will start this way...
Amazing magic tricks
Computer aided diagnostics (CAD) can never replace a doctor's opinion.
. weiner.html) But when a doctor diagnoses a patient, there is so much more than measureable facts that come into play. A good doctor uses her intuition. There may also be some side-effects to the use of expert systems. MDs are human, too, you know.
For some specialized diagnostics, like looking at x-ray images and finding breast cancer, computers outperform even the best professionals. (http://www.managedcaremag.com/archives/0005/0005
Think about this:
- If the diagnosis tool is often wrong, the doctor won't trust the system, even when it is right. The system is unneeded overhead.
- If the diagnosis tool is often right, the doctor will trust the system, even when it is wrong. Eventually the doctor's diagnostic skills will fade away because they're underused.
Both situations are worse than being examined by a skilled doctor with good judgment and no expert system.
Tell your friends about xenu.net
Not for nothing, but what is this if not a condensed and easy-to-use access to the 'literature'?
"Bar." Your car is here for scheduled maintenance. Example: Oil change.
"Bar, on the face of it." While inspecting your car, I found the following condition. Example: bad brake light bulb.
"Bar, that's going to get worse." Example: That squealing means you need to have the front rotors turned and new front brake pads replaced before they start grinding.
"Bar, I've seen that a hundred times." This will fix a particular problem. Example: That grinding noise means you need to have the front rotors and pads replaced right now.
In the first example above a good AI remembers that exactly x quarts of oil are needed so the mechanic can do it as quickly as possible and the bill reflects it seamlessly. Doctors already do their accounting by computer. Results already come back from the lab with the data checked against norms and anomalies highlighted.
In the second example, we start looking for things. The better the checklist the better the inspection. A good AI list includes checking all the usual things, checking all the known odd things about that particular car, and leaving out items known not to be an issue. Example: Car model A is subject to a fuel pump recall. The first time the car comes in the item is on the list, check fuel pump. If it is old we change it, if it is new we note it, and in either case, it will not be an item again. No mechanic can remember all this.
The third example is the hardest one. This is where the human judgement factor is strongest, selling brakes preventively and talking about driving habits. There is room for AI in situations like this, but not as much. This is the customer service stuff mentioned in the third paragraph above. It isn't easy being a mechanic either.
In the fourth situation, the diagnostic part of the AI is exercised. Maybe the problem isn't the most common one. Example: The car has a bad ball joint which causes it to pull to the right when the brakes are applied and a bad brake caliper which causes it to pull to the left. Net pull is zero. If it isn't caught, an inadequate repair will be made. A good mechanic will find it most of the time. A good AI will help almost every mechanic find it almost every time. It passes on knowledge to the young and reminds the old. What I wouldn't give for a decent program like this. I think that it would reduce errors of cognition. "It looked like bar to me, boss." Who among us has always looked for and found the colons among the semicolons?
FWIW, When you take your car to the shop, make sure you describe the symptoms you are concerned about more than your theory or preferred solution. Leave a note on the passenger seat with the same information and a five dollar tip for the mechanic and you will get better service. Trust me on this.
In conclusion, a good AI assistant is useful at every step and most of the kinds of things one can do are already being done. It will make a doctor faster, more accurate and richer. From a patient's perspective the most important thing is a timely correct treatment. I don't see how this can hurt the process. What seems to be wanted is better AI and I have no doubt that writing the good stuff will require brilliant doctors. It will make me feel safer. Patience.
SingCP@yahoNOSPAMo.com
All your database are belong to U.S.
The reason that most doctors prescribe antibiotics when they shouldn't is not because they are so ignorant that they don't understand their ineffectiveness, but because patients DEMAND a magic pill.
Aren't doctors supposed to have a code of ethics?
If they're just going to cave in and give the patient what he wants, why bother having doctors at all? Just make the damned drugs OTC and let the patients treat themselves.
As the article noted, the idea behind the modern differential diagnosis is to look at the branches of the decision tree that are very highly probable or very serious and rule them out. What isn't ruled out is treated. This approach maximizes the effectiveness of the limited human memory in treating disease, and it has evolved over many years in the medical profession.
Your doctor's ability to get the diagnosis right on the first pass is dependent upon the following:
his/her knowledge of the latest research
his/her willingness to consult colleagues or books or articles when in doubt about something
that he/she didn't forget any piece of knowledge relevant to the situation
Dr. Weed's tool does several things:
it increases the probability that the diagnosis will be accurate on the first pass
it logs the specifics of the course of diagnosis and treatment taken, in order to allow the medical profession to learn from its mistakes much more quickly than before.
Imagine what mankind would learn if all of this information were documented. Everyone's medical records and the questions/answers/tests behind every diagnosis. This kind of technology has the potential to truly revolutionize modern medicine, both in terms of cost and effectiveness. Dr. Weed has created a tool that will feed this database and make its insights readily available to any physician. It is like a bionic arm or xray vision. This won't replace doctors, it will empower them like never before in the history of mankind.
Doctors: Don't worry about this replacing you, worry about how you can use it to change the world.
Amazing magic tricks
The developement of a reliable medical expert
system would be a royal pain in the ass and
totally not worth it.
Doctors ALREADY use systematic procedures for
complex conditions, e.g. the revised Jones
criteria for the diagnosis of rheumatic fever, or
the Ranson scale for the prognosis of
pancreatitis or the Glascow coma scale,
or the PORT system for evaluation of pneumonia
or the TNM system for tumour staging or the ICD
classification for psychic ilnesses or the
DSM classification etc etc (you get the
idea)
Most of these are created and revised constantly
by the experts in the field and doctors can
and do use them. However, not everything can
be put down on algorithms because it would
take a huge amount of time to do work (the
algorithms would have to be extremely thorough
and each step requires the doctor to do some
work).
In my medical school they sometimes give us
a short algorithm for the proper physical
examination. We never follow it. I did it
once and it took me 1h and 20 minutes to
examine a single patient[1]. Typical load
may exceed ~30 patients/day/doctor in some
hospitals. You do the math.
Medicine
is like computers (in a way). You have to chose
two : (a) cheap (b) fast (c) reliable
[1] Also note patient discomfort! Not everyone
likes to be poked for over 1h in order to
diagnose common cold. Imagine e.g. having
to subject every patient to a digital
rectal exam (digital as in finger) as we
are typically required to.
[2] Also note that any classification is BASED
on human experts and NOT on e.g. satellite
data or measurements. As such many human
experts are (by definition) the source
of the data for the system and therefore
superior. Would you trust some software
based on the opinions of Professor Foo
more than Professor Foo himself?
Medical science is evolving very quickly. One big problem is that by the time something is published, some of the information is already outdated. Medical textbooks are revised numerous times before they reach students' hands.
Alot of doctors would love to have a high quality database. Yet in the US, doctors are very strapped for time. They often are cramming as many patients into their schedule as possible. They have the conflict of wanting to help as many people as possible vs giving quality care (doctors are often compulsive, so wanting to work less to have a life isn't as big a deal for them as you might think). My point is that if they use this database on each patient, it will mean that they see fewer patients per day. That would definitely be a 'bad thing.'
"Never, never suspect the dreams within the dreams of dreaming children." ~The Amazon Quartet
Yes, doctors do have egos. They also study for the rest of their lives. You can't legally be a doctor in the US without taking classes etc. each year. While there are some doctors who try avoiding learning anything new, most want to keep up with the latest and greatest research... kind of like how computer nerds like to keep up with the latest and greatest in computer science.
The biggest problem with this database idea is that using it takes time. In the US, there are more patients than doctors can handle. Using this database on each patient takes up more of their time, which means that the can see fewer patients per day, which means you have to wait longer before being seen by a doctor when you need medical attention. Something like this should be used by nursing staff, not the actual doctors. Even then, the nurses are also pressed for time.
The second biggest problem is keeping the thing up to date. Such a database would be vast and rapidly changing. I am sure you grossly underestimate what this undertaking is.
So don't post wierdness when you don't even know what the issues are!
"Never, never suspect the dreams within the dreams of dreaming children." ~The Amazon Quartet
I was once complaining to my doctor that I didn't think I needed medication that he was prescribing for one of my symptoms. He replied flatly "Then don't fill it." It really hadn't occurred to me.
Deciding on a course of action based on the evidence of what is effective in such cases is hardly `a new advance'.
At least to anyone outside medicine.
It's not that not all treatments have formal trials behind them that is particularly worrying, but that the profession only recently decided to look at formal trials and so on, and demand them if they don't exist.
There are very few 'old wives tales' out there. Much of past medicine was based on a physician's personal experince.
This is, if anything, worse. At least old wives tales may contain truth tested by generations of experience. But you are right, prescribing antibiotics for colds is not based on old wives tales, antibiotics have not been around long enough. It's based on amazing levels of ignorance or stupidity or negligence.
As for your "running on whatever is being advertized heavily," that sounds like empty rhetoric to me. I'd like to see some evidence to back up that claim.
The advertising budgets of drug companies. They don't do it because it doesn't work.
_O_
.|< The named which can be named is not the true named
Making a diagnosis is usually following a decision based on observed symptoms. Expert systems excel at this, but you still need, for the time being, someone with enough skill to correctly find and identify the symptoms. That's where the human skill is needed, but studies in the 1980's showed that when fed symptoms, computers were better at identifying more uncommon problems.
A lot of medical school is learning to act like a doctor: to dog the interns and to be just appropriately arrogant with the patients, secretaries, etc. The same can probably be said for most other professional degrees - a large amount is socialization. So of course the MDs don't like it. It doesn't invalidate their actual medical knowledge, but does risk pointing out how much is theater.
Beta is broken and the link to classic doesn't work. Stop wasting our time or there won't be anybody left here.
They already do this sort of thing with the MBTI.
I'll bet they avoid iNTj's, say me, like the plague. Too bad for them I always skew such tests towards iSTj or ESTP. (Depending on my accessment of the corporate culture.) Then again, anymore, I'd just as soon not even complete the interview with a company THAT concerned with conformity and control.
As part of grad school, I did several stints as a Teaching Assistant in physics. My all-time favorite calculator story came from a friend who claimed that a student once wrote down the answer to a problem on a quiz as:
9.99999999 99 blinking
For the younger folks, the separated "99" represents the ten power part, and older calculators would blink as the result of a divide-by-zero error.
That's kind of the point. :)
The Glass is Too Big: My Take on Things
Using computers for diagnosis is not new. Work on it began in the late 1960's and the commercial results of the research can be found in PKC as well as QMR, Iliad, and DxPlain. There have been many evaluations of these systems. Most point out that the computers do as well or slightly better than the docs. So why don't we see them in your neighborhood doctor's office? Personally, I think it will happen. It's all part of the evolution of medicine and techology.
A illustrative timeline:
- First docs were the keepers of the knowledge, "Do what I say."
- Medical Knowledge get's too big for the human brain. Knowledge bases and expert systems are developed to help out docs. Docs like the knowledge bases - MEDLINE, etc. Docs don't use expert systems because it's not integrated into their workflow. They were relegated as teaching tools and for difficult cases.
- Electronic Medical Records (EMR) are developed for doctors.
- Patients get access to the knowledge. (I've seen more and more patient's walk in with more printouts from the internet over the years)
- Patients start getting access to EMR (Yes, this is happening)
- Patients get access to the expert systems
Most doctor's don't see these systems as being well integrated enough into medical practice to use them. After all, it's been relatively recent (but not pervasive) that your doctor was entering your info into an EMR. EMRs already integrate some aspects of medical decision support (particularily patient management) and yes the HMOs see this as good to reduce costs.
The negative reaction of doctors to these systems is by no means universal. I know docs who use these systems whenever they just "can't figure it out" and medical students have been using them for awhile. I think that there is less arrogance now that patients actually have decent information.
Again, giving the expert system to the patient was bound to happen. The evolution of the doctor as an integrator of information, from any source, is bound to happen as well.
Of course, some of them are hostile because the patients that question their judgment are frequently fidiots.
Bob: Doctor, I've seen a lot of ads for this "Proboscum" pill, and I think I need to start taking it. It'll make my life better.
Doctor: Bob, "Proboscum" is for pregnant women.
(That's paraphrased from a Non Sequitur strip, I think.) Especially in poor areas, doctors see a lot of people who are falling apart because they don't take care of themselves. It's quite likely that, while these people may have opinions, they're more likely to be the cause of than the solution for the problem.
This isn't to say that a good doctor isn't open to suggestions. A good doctor, if they're not sure what's going on, will send the patient to get diagnosed by the right person. This doesn't always happen, unfortunately.
--grendel drago
Laws do not persuade just because they threaten. --Seneca
Nope.
Did you ever see the "Miracle of Life" special on PBS? Remember when the blastocyst (original ball of cells) folds in at both ends? The outside becomes the skin, the folded-in parts become the gut, and what's in the middle becomes the organs.
Your digestive tract is lined with epithelial cells; it's very much like skin. It is, in a sense, actually on the outside of your body---that is, there's a path through your body where the munchies pass through, like a tube going from mouth to anus, that nutrients are absorbed through the walls of. This means that very nasty stuff can be stored in your digestive tract: hydrochloric acid in your stomach, bacteria in your intestines.
If your intestines get punctured, the bacteria that live in there, which are good when they're in your intestine, wreak havoc on your system. This kind of infection is called peritonitis (you might have heard of it) and it's life-threatening, above and beyond the "hey, I have organ damage!" level.
Hope this has been enlightening.
--grendel drago
Laws do not persuade just because they threaten. --Seneca
What if you got a CF card with your new entertainment system. You get a weird hum from your speakers after setting everything up. You plug your cf card into your "handheld coupler engine" and start answering questions. Within 5 minutes you have a short list of possible fixes. You can download an updated image for the CF card, or you put in place a system that automates updates seemlessly. Or, you check your "handheld coupler engine" to see if the manufacturer, school, govt agency, restaurant, has included a coupler for their product, curriculum, policy, or bacon cheeseburger. Wait til the coupler can be accessed by thought. It's going to be an interesting future.
The most important thing any republican needs to know.
Now, please note that, for the case in question, I did not go to the doctor in order to get some sort of magic pill. I was trying to determine whether or not I'm going to get better without treatment. It is the doctor that assumed that I want some sort of magic pill. I suppose that it's too much trouble to explain that it's really best to let some ailments run their course and then to ask me what sort of treatment I would consider appropriate. I certainly would choose to not take medication that isn't likely to help, and I'm not alone in this view.
I grew up under a father who is an eye surgeon and considering the fact that almost all of his income goes to insurance both he and I believe that this database would be greatly beneficial to both doctors and patients. A database like this could quite possibly reduce the horrendous amount of malpractice lawsuits going on in this country (many of them baseless from people wanting to win a free "lottery" yet settled anyway). After a couple of years of such a downward trend the insurance companies might let up on their terrible prices and the doctors could be able to charge a decent fee again. Medicare is another story, and I'd rather not talk about it today. Furthermore, there is an ongoing myth out there that all doctors are rich. This is not true, but I must warn everyone out there that there are MANY unscrupulous doctors in this country and not to put one damn cent worth of trust into any of them unless they prove to you otherwise. Mod this however you like.
Several people have mentioned that blindly following the recommmendations of the software could lead to a lawsuit, but few if any have mentioned how it might save you from one.
I work in the engineering profession, and one of the first things that happens when we get sued is the attorneys spend a lot of time and energy trying to figure out how what we did might be different from what engineers typically do. It's part of what stifles innovation in our profession-- no one wants to be "on the stand" explaining why they thought it might be better to do something in a "new" way when there is a long history of doing X and X has been shown to mostly work.
Similarly, it seems to me that an accused doctor's best defense would be to find 500 other doctors who would have handled a given case in the same way. Assuming the expert system does its job, the likelihood of finding those 500 doctors should be increased, and in the event that it isn't, the authors of the software will have some explaining to do. If my experience is any indicator, the lawyers will focus on whoever has the most money (or highest insurance coverage), with (it seems to me) little regard for who is actually "right" or "wrong".
One of the beautiful things about Louisiana law (yes I am being fecetious) is that someone can be held responsible for all of the debt associated with a case if they are the only one who can afford it. So if a jury finds you 5% at fault and the other defendant 95% at fault but he can't afford the multi-million dollar judgement, you get to pay it. That's why when a bus driver fell asleep at the wheel and killed a lot of people here a couple of years ago Goodyear was named as one of the defendants. If they can be found to even have a tiny little portion of the responsibility (did the tire pop too soon and contribute to a loss of control?) then they can be stuck with the whole bill once the bus line is tapped out. And believe me, there are a lot of grieving family members who think that someone should pay.
Tort reform anyone?
Yeah, a drug company bought my wife and I a steak last year. I don't quite think we're ready to sign over our first-born child to pay back that debt.
Dewey, what part of this looks like authorities should be involved?
> The advertising budgets of drug companies. They don't do it because it doesn't work.
Thank you... I was waiting for you to make that point. Last time I was in my MD's office some of the techs there showed me a room full of leftover food. I asked if they were having a "going-away" party. They said it was from a drug rep. and that almost EVERY day of the week they had a free lunch that was supplied to the office by a drug rep. Also, while in the waiting room I saw a couple of such reps... the female was, ahem, quite "tarted up" as I think you in the UK would say it.
The only thing that kills more people than this are the tobacco companies.
Doctors kill because they misdiagnose, or they misprescribe, or they leave instruments in a patient that causes infection.
I am sure that most of them don't intend to kill, but they got into the profession to work with people and make lots of money and now they get 2 minutes with each patient, are exhasted and don't have time to spend the money they do make.
A tool that would work with the doctor to create a plan of treatment and that prints out the prescriptions for the doctor would save 50,000 lives a year. The program could ensure that the medicine and dosage prescribed fit with the treatement plan.
I see us going into the doctors office just like now and filling out a top level evaluation form that would then present us with more questionaires depending on how we said we are feeling. If we said we were having a lot of head aches, then we get the headache form. If needed an assistant should help us fill out the forms.
With exert systems like this in place then we could have technicians with just 2 years of training being able to sit with us for a few hours, helping us fill out the forms, and then working with us to create a treatment plan that is then passed onto a physician for their expert opinion and final aproval.
Wouldn't it be nice to be seen immediately when you show up for your doctors appointment and to have a person spend a long time with you, asking questions about how you feel? Then to have 5 tests done on a single blood draw to exactly identify which illness you have? None of this let's try this treatment for a month and see what happens like most doctors do now. Then you walk in after a month and the doctor asks you, what am I treating you for?
I actually argued with a doctor because my wife had stage 4 ovarian cancer and I wanted to do an MRI of her brain to make sure that the cancer hadn't spread there. The doctor basically blew me and my wife off because she didn't feel like taking the extra 5 minutes to write a letter to the insurance company to justify the test. Of course we went to another doctor and got a scan and the doctor started radiation treatment that same day for the 4 brain tumors. That first doctor is soooo sued. Not to mention the 4 doctors that missed all signs of ovarian cancer for 2 years before it was diagnosed, even though my wife had every symptom you can have of ovarian cancer.
Doctors need better tools and need to work on treatment plans with their patients to achieve high levels of health.
Don't even get me started on "health maintenance." When was the last time you heard of any disease being cured? The pharmacy companies in the US relealized years ago that the real money was in treating the symptoms of a disease, and not in curing the disease itself. That is why we have all sorts of $5,000 a month treatments for aids, but no $10 vacination that is good for life. There is a vacination for dental cavities available for the past 10 years that makes you stop getting cavities. Funny that you can't seem to find any doctor to give you tht innoculation.
Twice I have tried to post with mozilla, and failed. Doesn't slashdot support this OSS browser?
Disclaimer: I am a physician, and a computer geek.
Several problems with Weed's computer program:
1) he does not disclose his financial ties with the marketer of the computer program.
2) he has not validated the use of this computer program in a patient-blinded, randomised controlled trial. Will it improve patient care? Will it save money? He offers only anecdotal evidence.
3) Many hospitals already use computer programs to improve certain types of patient care. Diabetic care, especially, is routinely evaluated an many hospitals. Are these patients getting yearly eye exams? Are they taking an ACE inhibitor? Are their HgbA1c's less than 7.0? Doctors who overlook these things are identified and re-educated on diabetic care.
4) This neurologist does sound egotistical, but I would caution against indicting the entire medical profession on the basis of 1 neurologist. Most neurologists, when confronted with a difficult case, will consult their colleagues or international experts. You would be surprised how easy it is to contact a the world's authority on sleep disorders.
5) is it FDA approved?
6) Finally, understand that undergoing medical tests is not a benign event. Many medical tests carry risks for morbidity and mortality.
It is a little distressing to hear vituperous criticisms of the medical profession. If you don't like the medical profession, become a doctor and change it. I have.
You find the drug reps at centre points for clinical trials. If your wife and friends do not exist at a major hub for clinical trials the the drug reps will not waste their time. The prescribing of drugs flows outwards from these points.
More to the point, it's called 'I didn't' syndrome.
"I didn't go to Medical School for, what, 8 years, internship, residency, all that crap, just to have some goddamn machine tell me how to do my job."
Which is, of course, silly, because these things aren't doing the Doctor's jobs; they're helping the Doctor's do their jobs. It's just as valid to say that keeping a copy of that lovely Physician's Desk Reference, or Grey's Anatomy, or any form of paper references, is 'telling them how to do their jobs.'
Vintage computer games and RPG books available. Email me if you're interested.
Let's say a computer did the same thing. It's hard to argue that anything else should be done. There are millions of diseases, so it's good to have a computer remember all of them. Unfortunatly for the computer, those diseases all exibit the same few symptoms. Uh oh, the computer now has to decide which disease really is before it or be forced to print out more information than the doctor can read, store or act on as the treatments may be diametrically opposed. The process, if perfect, may diverge because it is both over and underdetermined (imagine that!). Perfect practice is impossible and we should not expect machines to save us, despite the fondest wishes of accountants and insurance agents.
Doctors don't kill patients, disseases kill patients. Doctors do what they can to not harm and provide all aid and comfort. How many people have you comforted today?
Distractions can kill. Doctors will adopt computers as they become more practical, ie non M$ impared, better form factors and I/O, etc, so they can spend their time thinking about medicine NOT a silly program. Until then, expect doctors to rightly refuse to adopt the impractical to achieve the impossible. The results will be greater harm. Are you willing to be responsible for that harm? Are you ready to stand up to the entire medical community and force change on them that they refuse as less than best practice? If not, shut up with that "crimminally irresponsible" bullshit.
DMCA, Hollings, Palladium. What might have sounded like paranoia is now common sense.
I find the replies by my brethren physicians appalling.
Every study ever done shows ridiculous levels of variation in diagnosis and treatment. The best of us are wrong, in non-trivial cases, 20% of the time, and most of us do worse than that. But since there is no real individual negative feedback loop on clinical practice [do you know YOUR error rate -- not the pathetic sanitized morbidity/mortality rounds on the topic] you don't know when you are wrong and patients lost in follow-up erases the evidence. Would you fly with a pilot that ends up at the wrong airport 1 out of 5 times?
The simple fact is that the unaided mind, when referencing a memorized knowledge foundation, simply sucks. The idea that you WOULD NOT use a tool specifically designed to improve your abilities is like saying you would prefer to do surgery instead of putting someone in an MRI.
To top it off, fascist HMO, socialist Medicare and absurd malpractice not to mention HIPAA and bureaucracy -- are the foundational problems that if eliminated would return competition to this market and move it forward. Fee for service has yet to be surpassed. It worked.
The fact that a major institution still uses the admission process that I scribbled on a napkin for them in 1992 shows you how bad things really are within healthcare. [I'm good at business system design -- but not THAT good.]
The fact that my wife underwent 3 hours of exams in agony when I TOLD THEM it was a ascending UTI/kidney infection and could be verified within seconds by tapping her back over the kidneys -- instead she suffered because of defensive medicine. We should be using our brains! I had to literally force myself into the exam room and demonstrate to a *Harvard*-trained doctor I was right. In shock, the guy immediately prescribed antibiotics and pain med. I left fit to be tied.
Did I mention that a PKC would have diagnosed this within moments?
And you guys DON'T WANT to use a tool which increases your abilities. SHAME ON YOU.
I recently had a bad liver problem. A WORLD-EXPERT had the gaul to tell me that there was nothing to be done to improve my liver functions.
Poppycock! A trivial literature search revealed two substances that radically improve such function, my LFT's were so low the next time around that they repeated the test to be sure.
So much for going by memory... use the information technology that geniuses like Weed provide and that hard-working folk like me who know how to design functional clinical systems provide for you.
Your patients will live longer.
The day computers have common sense they will make great doctors.
Consider the task, millions of diseases with a few dozen symptoms. The problem is over determined and does not yet compute. In the best of all worlds, the computer will have to do exactly what the doctor does: treat the most probable problem and watch out for the most severe consequences. It too will make mistakes, but won't know till someone types in a big long form. It's just not there yet.
Now quit trolling the doctors. They will tell us when they see an improvement.
DMCA, Hollings, Palladium. What might have sounded like paranoia is now common sense.
You can use the wellness coupler for free there. To check it out. I would have but I don't have flash installed.
e r. html
http://www.pkc.com/understanding/wellness_coupl
The medical profession is second only to the software development profession in the number of incompetent practitioners in its ranks.
Using these resources physicans are mostly right most of the time. It is unreasonable to expect more than that.
Using that reasoning, you would be happy with a 60%* rate of success, yes? Sorry but it is perfectly reasonable to expect doctors use whatever tool is available to try and achieve 100% success. Unattainable? Perhaps but I demand that they try. If this tool gets them closer to that 100%, there is no reason it should not be used. You may be happy with 60% but I am not and doctors should not, either.
* - 60% is just being used as an example of 'mostly right'.
I live ze unknown. I love ze unknown. I am ze unknown.
Allow me to quote Drexler:
Thanks for playing! :)
--
Power to the Peaceful
So. You think it's a good idea for an expert system to make medical decisions. How about coding decisions. Sit back and ask yourself if you think that a computer would be any good at doing what most of you do -- let's say writing code well. Let's say managing a network well. Would any of you trust a computer to do these things? Now ask yourself why this bothers you (if it does).
Ultimately, the difference between a computer munging data and a human expert is a series of things -- heuristics, cognition, intuition -- computers don't have any of these things.
Physicians are highly trained -- two years of basic sciences, two years of clinical training, followed by at least three years to become an internist, family practitioner, or pediatrician -- 4 for an OB/Gyn, 5 for a surgeon. This is all after 4 years of college.
Why do you people (the average slashdotter) feel that you have the right to judge people who've spent the majority of their lives in school learning to do this? Why do you all think you know anything about medicine? I, personally, would like to see the reaction of this site to a site run by doctors suggesting that programmers be replaced by computers.
Would you honestly trust your life to the opinion of a data mining tool?
Think about it.
Consider also the other side of the coin... if the database is not as reliable as it could be (after all, any programs output is only as good as it's input, and you'll never get a lay-person who can accurately assess all the symptoms) .. who is liable then ?
- Who is liable in the case where someone _relies_ on the database for diagnosis, and it's incorrect?
- Now what if the person was going to a doctor and _he_ used the database and it was wrong ?
I treat my doctor, my mechanic, my priest and my boss the same way
Maybe, but remember who can kill you and destroy every evidence.
__
Men with no respect for life must never be allowed to control the ultimate instruments of death.
GW Bu
We (at PKC) are a bit overwhelmed by the discussion at Slashdot.com regarding our software. We have been building the philosophy, technology, and content for over 15 years now - all the while accepting the fact that the industry of healthcare didn't welcome our efforts. The most discouraging part (don't get me wrong, we are a generally very cheery and optimistic group) was the unwillingness of our detractors to offer much in the way of truly thoughtful dialog. The discussion we have seen spring instantly at Slashdot.com has been largely serious, thoughtful, and fearless. Thanks
My greatest fear of expert system dignosis is they'll more likely just mimic existing the norm.
If doctors often misdignose a disorder the expert system will continue to folow that patern.
If a rare disorder shows up often doctors misdignose it as it's well.. rare... I've read an artical about this tendency. But then doctors are only human. However they'll see the incorrect dignosis as incorrect keep trying untill they get it right OR piss off patent so much they'll go to annother doctor who might do it right.
Expert computers however will ALWAYS misdignose an NEVER give consideration for the rare.
Some times rare disorders are trendy so doctors will look for them more. It's a human thing. The computers won't. Being rare the computers continue to miss it.
The idea of expert systems is nice but right now the technology is more "folow the trend" so it can't do any better than a majority of doctors. Your better off to find a good doctor.
I don't actually exist.
I don't think anyone is suggesting that a surgeon be replaced by a database. This database is simply a tool that can be used to diagnose a problem. Some doctors are threatened by this, though they should not be. A doctor would still be needed to interpret the results, and a surgeon will still be needed to perform a surgery. It's preposterous that a human being could say "Databse? No thanks. My personal experience is better than the data collected by thousands of other doctors." Doctors should be embracing this innovation because it can only improve the care that they provide. Unfortunately, they seem more concerned with their own prestige than the welfare of their patients. Shame on them!
I'm still trying to figure out if he meant stool as in a seat or stool as in poop. It's funny either way, though.