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.
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.
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.
Doctors are just technicians that happen to work on people. They are no more perfect than the grease monkey at the car dealership. Using a computerized database of information to research the very complex organisms we are is just common sense and is perhaps why computers became popular in the first place. Sure, some doctors will manage to make mistakes using a tool like this, just as some high school kids still can't seem to use a calculator correctly.
Suing for bogus information? One always has to consider the source of information. A dabase like this can be considered only as a helpful tool. Tools help find a working solution, but it takes experience to make it happen. A good doctor is someone who is responsible for using his tools properly, not pushing buttons.
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.
Even herbal treatments in the absense of a proper amount of research can be troublesome. People tend to let themselves think that because it is natural, it can't be dangerous.
(* 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.
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.
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.
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.
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
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.
Comment removed based on user account deletion
Doctors used to taste urine to diagnose diabetes. No kidding!
There was also a well-developed technique of thumping parts of your body while listening with a stethoscope. A skilled practicioner could learn a surprising about about what was going on inside your body from this (very valuable in the days when there were no CAT scans, or even X-rays, and exploratory surgery meant almost certain death from massive infection).
New diseases would presumably be entered in the database the same way that they get into the wetware databases that doctors use now. Patients present with symptoms that don't quite fit anything they know about. They try a treatment, then another, then another.... Over time the pattern of symptoms gets recognized as a new disease, and the treatment becomes standardized.
The difference is that with an expert system this process could be much, much faster than it is with the old-fashioned word of mouth method, or even with journal publications.
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..
I'm not surprised that your friend made an off the cuff remark like this which portrays physicians simplistically as a walking database. But I think it would be closer to the truth to call them walking neural networks which are constantly learning and which use databases (reference books) to affirm their suspicions, and also who are cerified by a board and licensed by the state to be responsible, ethical, and competent.
Doctors must also take into account that the person describing the symptoms may have more than one condition simultaneously, that the patient may be exagerating something common or normal as a symptom because he believes it is related to the other actual symptoms. As others have pointed out in this discussion people can unconsciously pick up symptoms based on information they have read. It is rare to have a doctor these days that knows you for very long and who has treated you and your family for many years but that would give the doctor more insight into what the problem could be.
The article starts off with an example where Dr. Cross had an unusual case for which he did not recognize the symptoms and which turned out to be a condition he hadn't even heard of before. This is a situation where using this program makes sense; it merely computerizes the literature search. But I disagree with you that doctor's could easily be replaced. This program can only be a helpful tool used in conjunction with all the physicians other tools.
The doctor must be the one who diagnoses. He can not become just a technician asking the patient questions and entering the response into a computer form. Physicians are licensed for the same reason that Professional Engineers are licensed. When human life hangs in the balance, someone must be accountable to make sure things are done right.
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.
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.
"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.
You hit on two very important things (IMO):
1. Obscure/remote health issues. People who have spent even a week in a different part of the Unites States than where they live may contract illnesses that a doctor back in their local hometown may never have heard of, and hence can't diagnose.
For example, here in the SouthWest (Arizona, So. Cal, Nevada) there is a soil/dust borne fungus that when inhaled can cause flu like symptoms. Unless you are from the area a doctor is very unlikely to diagnose Valley Fever properly. If left untreated the fungus can disperse to other tissues, the blood and bone. Death is not uncommon if left untreated. A computer system would be able to take travel history in to account and offer Valley Fever as a possible diagnosis. The doctor then steps in and orders the proper labs for a complete diagnosis. As a partner to the health professional such a database/expert system could 'save' many lives.
2. Doctor's power issues. I can't tell you how often a doctor grimmaces when I call them by their first name instead of "Dr. Important". They are people and I am people, I refuse to cower to their concentrated training in a particular field. I certainly don't expect them to call me Mr. Important when I meet them in a business meeting in my field of expertese.
Not all doctors are like that I know. All of the docs I see on a rgular basis are well grounded and have no problems with a first-name basis relationship. In my personal experience they are also much more likey to make me an interactive part of the heath care process instead of treating me as an object or a mere disease to be cured. The catalyst for more doctors to give up that power-centric relationship is for the patients to not tolerate it. Either explain to your existing doctor what relationship you want to have, or find another doctor.
I've just about gone to court several times with doctors. I'd (for example) have a 2pm appointment. I'd show up at 1:50pm, sign in and wait. At 2:15pm if I was not being seen by the doctor I got up and left. Often the office attemtped to charge me for the appoitment, or a cancelled appointment fee. I told them I had a 2:00 appointment and that the doctor was the one who cancelled the appointment by not showing up on time. If they don't respect my time, they don't respect me and I don't do business with them.
Article X: The powers not delegated... by the Constitution...are reserved...to the people
"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.
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.