Forgot your password?
typodupeerror
AI Medicine Robotics

Computers Shown To Be Better Than Docs At Diagnosing, Prescribing Treatment 198

Posted by Soulskill
from the boop-beep-you-have-cancer-boop-beep dept.
Lucas123 writes "Applying the same technology used for voice recognition and credit card fraud detection to medical treatments could cut healthcare costs and improve patient outcomes by almost 50%, according to new research. Scientists at Indiana University found that using patient data with machine-learning algorithms can drastically improve both the cost and quality of healthcare through simulation modeling.The artificial intelligence models used for diagnosing and treating patients obtained a 30% to 35% increase in positive patient outcomes, the research found. This is not the first time AI has been used to diagnose and suggest treatments. Last year, IBM announced that its Watson supercomputer would be used in evaluating evidence-based cancer treatment options for physicians, driving the decision-making process down to a matter of seconds."
This discussion has been archived. No new comments can be posted.

Computers Shown To Be Better Than Docs At Diagnosing, Prescribing Treatment

Comments Filter:
  • You might think it's funny, but Watson is still sensitive about screwing up on Jeopardy a couple years ago.

    • by Cryacin (657549)
      And will the system consider the patients age/cost to treat/insurance level/likelihood of patient paying future insurance premiums to make up for expenses?
      • by TheCrazyMonkey (1003596) on Wednesday February 13, 2013 @08:04PM (#42890035)

        And will the system consider the patients age/cost to treat/insurance level/likelihood of patient paying future insurance premiums to make up for expenses?

        It will if you program it to. Things like this are tools. As a relatively young doctor (resident) I welcome things like this. Every doctor I know uses reference material, some are printed on dead trees and some are electronic. Today, there's not much difference. But the point it is that there's too much medical knowledge for one person to keep it all in their head at one time. If something like this were to come to market it wouldn't be replacing doctors, it would be augmenting them. Machines do what we tell them to, always have and (hopefully) always will. False rivalries like this completely miss the point. I would love to have a computer algorithm that could correctly diagnose 99% of the time even if it were flagrently wrong the other 1%. That's why humans are in the loop.

        • But the point it is that there's too much medical knowledge for one person to keep it all in their head at one time. If something like this were to come to market it wouldn't be replacing doctors, it would be augmenting them.

          The attitudes towards the use of expert systems is kind of interesting. For example as long ago as the early 1970s programs like Mycin would consistently outperform medical experts, and yet they've never been adopted. There seems to be considerable reluctance by people to accept diagnosis-by-computer even when told that it's more accurate than human diagnosis. I agree with your comments that it's a support tool, but most patients won't even accept it as a support tool. One hypothesis is that if patients

      • Only doctors who operate independent practices that they own really care about that. But I don't see why we can't add that to the program. That is one of the easiest pieces you can put in that doesn't need AI.

        After the AI finds the best DX and procedures that work. You cross reference the Fee schedule and weigh the cost into the equation.

  • Modern luddites (Score:5, Insightful)

    by MPAB (1074440) on Wednesday February 13, 2013 @07:06PM (#42889381)

    An expected outcome. First machines become good and cheap at performing manual labor, then it's lowly qualified jobs such as sorting stuff or basic accounting.
    In a few years, liberal professions will fall. Our salaries (I'm a doctor) have been diving as more and more people around the world can afford a career and achieve a good enough level to perform as a doctor or an engineer.
    Creative and risk-taking careers will resist for a longer time.
    We can hope for a future of working machines and humans enjoying themselves. The other option will be cheap-ass humans with no way of earning a living whatsoever.

    • Re: (Score:3, Insightful)

      by Anonymous Coward

      except software and hardware designers. which is why i'm both. ;)

      but seriously, do you really think that's what the future will look like? all evidence from the past shows that as technology gets better, the amount of good jobs goes *up* not down. i don't see any reason why this would change. we're a LONG ways away from having machines do absolutely everything for us.

      • by NFN_NLN (633283)

        we're a LONG ways away from having machines do absolutely everything for us.

        Yeah, what happened to those Japanese sex-bots I keep hearing about?

      • Re:Modern luddites (Score:5, Insightful)

        by Garridan (597129) on Wednesday February 13, 2013 @07:38PM (#42889749)
        Meh. You can be replaced by sufficiently advanced algorithms. I'm mathematician, FFS. There are already automated theorem provers which can solve undergrad-level problems. As computers evolve, they'll be just as good as people and loads cheaper than people at everything we do, up to and including the creation of art.

        If we progress to the point where all of our jobs can be done by computers... what should we do? At the point where artificial intelligence becomes genuine intelligence, it will rapidly outpace human intelligence. This is evolution. We are breeding our replacements.
        • >> If we progress to the point where all of our jobs can be done by computers... what should we do?

          In the future cheap unprofitable or low-margin jobs that machines will do (that might include a lot of things that today's highly-paid people struggle with) will have to be run by government. No one else want to do that work anyways.

          People will want to be in control of things that matter, things that are challenging, such as finding a way to move out of the solar system. Even the computers will agree to

        • Re: (Score:2, Insightful)

          by Anonymous Coward

          OR.

          We are breeding our new bodies. Those who expected a more corporeal form of "godlike immortality" will be disappointed perhaps, but we won't be overrun by "the machines" or "robot overlords" or whatever such nonsense. We will be integrating our tools to augment our selves. The mechanical and electronic prostheses we've been perfecting will eventually cease to be separate -- by design. No dissolution a la the Borg from pulp sci-fi horror, rather, the ultimate self-actualization via liberation from the con

        • Meh. You can be replaced by sufficiently advanced algorithms. I'm mathematician, FFS. There are already automated theorem provers which can solve undergrad-level problems. As computers evolve, they'll be just as good as people and loads cheaper than people at everything we do, up to and including the creation of art. If we progress to the point where all of our jobs can be done by computers... what should we do? At the point where artificial intelligence becomes genuine intelligence, it will rapidly outpace human intelligence. This is evolution. We are breeding our replacements.

          Hmmm...what if there is an irreducibly non-algorithmic component to human intelligence? That would invalidate the Church-Turing thesis that your assertion seems to be relying on. Roger Penrose thinks it would at least, and he makes a pretty good argument [wikipedia.org] for that position, and against the Strong AI you are hypothesizing. He also defends his argument pretty well, too. [calculemus.org].

      • Yeah, I kinda predict that the jobs of doctors will move to collecting the information the computer asks for, volunteering info that they notice from experience/sight/interaction (try a computer on a mental disease patient...) And whenever the diagnosis is wrong the doctor would do research and/or try to teach the computer what other questions steps would be required to detect and treat the special case.. That way it is improving the system for everyone. Also the computer could be smart about how it prescr

      • by shaitand (626655)
        I can't see this obsoleting doctors.

        An implementation could be built that works in a manner similar to Bitcoin but instead of cracking hashes you are performing encryption and doing processing of statistical analysis and cross indexing of data in a completely decentralized manner you could build an anonymous, safe, secure, and global system that potentially could gather statistically significant data on a scale that makes FDA controls and studies look like random speculation.

        It could build a biometric finge
    • We can hope for a future of working machines and humans enjoying themselves. The other option will be cheap-ass humans with no way of earning a living whatsoever.

      Call me a pessimist, but I'd bet on the second happening before the first.

    • by shaitand (626655)
      No worries. This has the potential to reduce the impact of having controlled substances which means it will never happen in a way that doctors need to worry about.

      The problem is the most evil of all negative side effects. Euphoria! A computer AI running as a cellphone app wouldn't prescribe things without a cause but it also wouldn't police patients. That would be the excuse at least and never mind that the AI as a gateway to scripts guarantees screening for drug interactions and informed choices thus elimi
      • by shaitand (626655)
        Sorry, s/reliability/liability/ at the end there. Probably lots of other typos in that rant too.
    • When there is no way to earn a living, there will be no need to earn a living. Except maybe for neurotic economists.
      • by TheLink (130905)
        Just think of the Chinese, Vietnamese workers, etc as advanced robots. How's it working for the US workers so far? Are they having better and better lifestyles?

        Perhaps eventually what you say would be true. But I bet it'll take significant time for that to happen.

        And how much time and suffering that involves would depend on the path we choose.
        • The key, I think, is to wait till it's global. Once we've run out of non-first-world countries to make miserable, it's just a matter of time before we start running out of forms of scarcity.
          • by TheLink (130905)
            There may be zero scarcity of smurf berries and farmville farms, but despite GM etc there will be an upper bound of wheat and other food that you can produce on this planet. You might be able to survive on food produced via nuclear energy, but given that there are already significant health differences resulting from merely different diets, it's going to take quite a while before they develop cost effective artificial foods that humans like and can thrive on.

            The upper limit = 174 petawatts of sunlight hitti
            • Sustained expansion is, obviously, unnatural and unreasonable. It'll take a while for everyone to realise this, of course, but I suspect that we'll see negative population growth once the entire planet has been brought up to full development, just like we see in many first-world countries presently.
  • by Anonymous Coward

    I'm sure this is not what diagnosticians would like to consider, but I think the simple truth is that computers will negate our need for human diagnosis in the very near future. I'm sure we'll hear the same "The computers will be great *assistance* to actual doctors" but I don't think that's actually true. I know the computer is likely doing a better job, there should possibly be a few overseers but the vast majority of doctors shouldn't be needed, and frankly I wouldn't want them second guessing what's l

    • GIGO (Score:4, Insightful)

      by erice (13380) on Wednesday February 13, 2013 @07:26PM (#42889623) Homepage

      An expert system is only as good as the information it is fed. Until we get machines that can quickly scan a human body and tell us everything there is to know about it, we will still need doctors to talk to patients, vet what they say, observe what didn't mention and ask followup questions.

      • by Dunbal (464142) *
        And tell you what the patient is NOT telling you. Medicine is based more on objective observations than subjective answers to questions. While 85% of the diagnosis is usually in the medical history, do we just let the other 15% die?
    • Ha! This is just another technology that the medical industry will control to suck money out of us. Here's what's going to happen.

      Machines will "assist", but as "medical devices", only medical vested interests will have legal access to them. Our health care will improve, while we *continue* to get robbed by the medical industry through the rent seeking made possible by licensing laws.

      • by PRMan (959735)
        So, you don't want your medical diagnosis machine tested by the FDA to ensure that it's as safe as can be? You don't want to be able to sue a large, wealthy organization for malpractice leading to your death?
        • Ha ha. No, I *don't*.

          Sorry, I've worked in the medical device industry. FDA tested does not mean safe and effective. Companies work around regulations, making their products less safe, but able to pass testing. At best the regulatory process only delays medical progress a decade or so and multiplies costs ten times, and at worst it completely prevents improvements for decades.

          How is it that grown ups can think government apparatchiks colluding with corporate rent seekers is a recipe for effective health car

          • by dcollins (135727)

            "How is it that grown ups can think government apparatchiks colluding with corporate rent seekers is a recipe for effective health care?"

            Somehow socialized medicine works in every other advanced country, with better results, lower cost, and greater patient satisfaction, so that's one data point.

            Or actually it's all the data points.

            • Somehow socialized medicine works in every other advanced country, with better results, lower cost, and greater patient satisfaction, so that's one data point.

              As Thomas Sowell would ask, "compared to what?"

              I thought we had spent the last century deciding testing whether a free market or government central planning produced better goods and services. As Reagan's strategy bore out, "We win; they lose."

              At least in reality, the question was settled over which system was superior. In policy, you always can force people into an inferior system if you have the guns.

              • by dcollins (135727)

                In actual-real-reality, the answer is the same practically regardless of what data you choose to compare -- life expectancy, infant mortality rate, mortality amenable to health care, physicians available per capita, expenditure per capita, cost as a percent of GDP, percent of government revenue spent on healthcare, etc., etc., etc. It's so not even close in any of these cases (often off by a whole order of magnitude for the USA), that arguing anything else is simply delusional. Saying "we have bigger guns"

        • What does what the parent mentioned have to do with the ability to sue for malpractice?
  • Interesting (Score:5, Interesting)

    by Intrepid imaginaut (1970940) on Wednesday February 13, 2013 @07:08PM (#42889425)

    I find this interesting, I was wondering when we'd reach the point where the accumulation of knowledge available in any given field exceeded the ability of the human mind to completely grasp in a useful manner. It's going to reach a situation where multiple experts on a given subject with a fair idea about related subjects are going to be the only unit capable of actually doing anything sooner rather than later - apparently in medicine at least computers have come to the rescue.

    I suppose with the many specialisations in every area we're already there, the question is can we repeat the improved returns in areas like physics and chemistry.

    • Re:Interesting (Score:5, Insightful)

      by joh (27088) on Wednesday February 13, 2013 @07:14PM (#42889483)

      The problem is not in the decision making process, but in the fact finding process. THIS is the part computers and software are still very, very poor at.

      • Re: (Score:2, Informative)

        by Anonymous Coward

        Sadly, so are most general doctors.

      • Re:Interesting (Score:5, Interesting)

        by ColdWetDog (752185) on Wednesday February 13, 2013 @07:46PM (#42889833) Homepage

        We could start by getting some real information instead of the pair of nearly identical fluff pieces in the TFA. While it's nice they used Markov Decision Chains, as best as I can tell they did a bunch of simulations with pre existing data and came out with 'better' information than the docs who, unfortunately, were dealing with problems in real time.

        The lawyers have had this sort of thing for years. It's called a 'retrospectascope'. It tells you what you SHOULD have done after you know what the outcome is.

        Very, very helpful. To lawyers anyway, to doctors, not so much.

        I'd love to see some real computerized decision analysis that would be useful in real time medicine. I'd love to have "all" of the information about a patient in real time.

        I'd also like a Pony and one million dollars. Before I get worried about job security and before everyone goes all Star Trek, lets see if this works in a real clinical setting.

        • by PRMan (959735)
          Looking online is already more accurate than many of the poor-quality doctors that I see these days. Good doctors are, of course, much better than reading yourself online. This technology in combination with a doctor would be very powerful. It would even be better as a means of rating doctors that disagree with the machine and are right or wrong in those instances.
        • Re:Interesting (Score:4, Interesting)

          by loneDreamer (1502073) on Thursday February 14, 2013 @12:49AM (#42892417)
          I know something about machine learning, so let me tell you how it works. The input is partitioned in two sets, a training set and a test set. The training set is used to teach the algorithm, the test set to measure it's performance. So, while we know the outcome for the second set, the computer does not, he is literally seeing it for the first time, as if the patient has just came for a consultation. The decision accuracy is then computed comparing the new output with the known outcome we had reserved to ourselves to see it it matches. And it does it in real time. It IS a real clinical setting!

          So no, while I understand your fears, calling anything in ML a "retrospectascope" is completely wrong and ignorant. In fact, if you build such an algorithm it tends to have very poor behavior, since it looses the power to generalize for insight (the technical term is "overfitting").

          Truth is, it's a good think that you would love to get some of the things you mention, since the article is saying you'll get them (and I can attest to that). Very soon. Don't believe me? Look at Watson in action [youtube.com] and think deep about what the computer is doing. It might seem a game, but really think what it is going on. It is not a movie script. It does not know the answers, it is UNDERSTANDING the questions and COMING UP WITH the right answers. Faster than the best humanity has to offer. Are you smarter/more knowledgeable than them? The truth is indeed astonishing and might look like science fiction, but it is not.

          The pony though might take some time ;-)
      • I think a major problem with the current approach is communication. Doctors rarely communicate with each other and for cases where a patient is trying to figure out what's wrong with them and getting bounced around by specialists, no one really has the full picture, not even the primary.

        A computer can have the full picture, assuming there is enough data for it to churn on, and given enough population data to train on, it inevitably will arrive at evidence based diagnosis and treatment options better than an

        • A computer can have the full picture, assuming there is enough data for it to churn on, and given enough population data to train on, it inevitably will arrive at evidence based diagnosis and treatment options better than any human...for the stuff that's understood.

          Where exactly in this magical, cornocopian world, does the computer get the 'full picture'? There is this odd feeling around here that if you feed enough information into 'the computer' it will solve all sorts of difficult problems automagically. Not going to happen. Yes, it's true that data collection needs to be standardized and analyzed. That can give you suggestions where to look. But correlation is not causation and correlation is what these programs do.

          That and the fact that diagnosis isn't alwa

    • by mspohr (589790)

      Medicine has always had this problem. It is a large complex field with constantly evolving "truths".
      Computers are much better than humans at considering all of the options.
      An early pioneer in this field, Larry Weed, used to say that a good clinician could come up with a 3 item list for a differential dx and an expert could come up with 6 items. However, the computer can come up with 20 along with a list of tests to perform to make the final dx.
      Computers have consistently been shown to perform better than

  • I have 2 kids and my first one was always sick until a year ago. He was on antibiotic at least once a month

    After a while I picked up on a few things

    There is a simple 5 point check to see if the llllness is bacterial or viral
    Once he diagnoses the doctor does not choose the drug. The physicians desk reference aka pdr tells the doctor what to prescribe
    The dosage is determined by the drug companies depending on the child's weight

    The pdr will have every known disease, illness, condition and the drugs or procedur

  • Mycin (Score:5, Informative)

    by White Flame (1074973) on Wednesday February 13, 2013 @07:17PM (#42889523)

    In the early 1970s, Mycin [wikipedia.org] achieved 69% accuracy of prescribing a "correct" treatment for a patient's condition, which was deemed better than human specialists.

    The linked articles don't seem to include the absolute accuracy that it achieves, just the relative accuracy against doctors. I wonder if we've come any further than the basic expert system rules allowed 40 years ago.

    • The big difference here is in technologies.

      Mycin used a bunch of rules to arrive at medical decisions. These had to be manually entered by medical experts which is time consuming, difficult, and outdated by the time it is completed. It was a narrowly focused, brittle system that strived to emulate the logic of it's designers.

      The newer approaches (like the kind from this article) build their own probabilistic models of medical diagnosis and treatment based on statistical analysis of data. Lots and lots of da

    • by Alomex (148003)

      In fact computers have been far superior at medical diagnosis for about ten years, and there are several products commercially available. The only reason they are not routinely used is because doctors fear for their jobs.

      People have died because the doctor did not run the diagnosis against the computer. Let's face it day to day medicine is nothing like "House" were they get together and debate your case. If you are not responding, doctors usually just carry on with more of the same treatment and hope for th

      • If you are not responding, doctors usually just carry on with more of the same treatment and hope for the best, while the computer would say "patient not responding to Randomicine? then check the zootocite count for possible inflammation of the hyperbolerium" and in that case one of two things happen: we discover it's the hyperbolerium and treat you for that or we determine it isn't that and continue the normal treatment on the basis of actual evidence instead of just a hunch.

        You probably think you're being clever, but in fact your use of Hollywood-style medibabble indicates that you haven't really bothered to learn much about the subject. It's really sad, on a site like /., to see people who work in highly technical fields with lots of meaningful jargon show such contempt for other people's technical knowledge and terminology, but I guess it's not surprising.

        I'm a bioinformaticist, which means I have a pretty good idea how hard it is to model living systems in silico. A long

        • by Alomex (148003)

          but in fact your use of Hollywood-style medibabble indicates that you haven't really bothered to learn much about the subject

          The use of babble is a lame attempt at a joke and it indicates nothing. It truly shows your lack of arguments that you have to base your reply on that irrelevant detail.

          I'm a bioinformaticist, which means I have a pretty good idea how hard it is to model living systems in silico.

          Maybe you are confused by the latest, state of the art software packages that try to read radiology directly. Those are still in development.

          I'm talking about diagnostic software based on expert systems applying deduction rules over noisy data. The doctor enters the data and the computer produces all possible matches with probabilities attac

          • by nbauman (624611)

            but in fact your use of Hollywood-style medibabble indicates that you haven't really bothered to learn much about the subject

            The use of babble is a lame attempt at a joke and it indicates nothing. It truly shows your lack of arguments that you have to base your reply on that irrelevant detail.

            No, your medibabble indicates that you don't understand the subject. Doctors make jokes all the time. But a doctor's joke, like a programmer's joke or an engineer's joke, is based on an insight and understanding of the discipline. Your medibabble is based on ignorance.

            I often see lame attempts at humor about science written by people who don't know anything about science. It comes off as really stupid. Their message is, "There's all this science stuff that none of us understands. It's OK to be ignorant. Nud

            • I call bullshit. There is no such diagnostic software.

              Here are the names of some companies producing the "non existing software":

              DiagnosisPro
              Isabel Health Care

              Here's a recent article [nytimes.com] on the New York times about the subject, Isabel Health Care has been around since at least 2006, when we recommended the software to a local hospital.

              There is no complete database of every possible disease with typical and atypical presentations.

              Complete in that it contains every disease known, and no you do not need agreement about the symptoms to enter them in a database. The reasoning process handles that part, you simply enter "some reports say these are symptoms, some

    • by nbauman (624611)

      The linked articles don't tell you what a "30-35% increase in patient outcomes" is, what kind of decisions they made, or how they decided that the algorithm's decisions were better than the doctor's decisions. It seems to be strictly a simulation. They're asserting that their algorithm is better than a doctor's decision, without any supporting evidence.

      One of the tip-offs for me is that they don't give the predetermined outcome in the abstract or anyplace else. That's what medical journal articles do. How d

  • Virtual Doctor you got leprosy

  • So, who do we consult for a second opinion? HP? Oracle?

    • by Kittenman (971447)

      So, who do we consult for a second opinion? HP? Oracle?

      Well, people used to go to (the) Oracle for a second opinion in the old days (ba-dum-cha)

    • by PRMan (959735)
      It doesn't matter. They're using the same system so the second opinion is very similar to the first. Eerily similar. Deja vu, in fact.
  • Old tech (Score:5, Funny)

    by drcheap (1897540) on Wednesday February 13, 2013 @07:39PM (#42889765) Journal

    I don't care what this article says, this is nothing new. My in-home psychiatrist in the 1990s was great at diagnosing my issues. Perhaps you were a patient of his, too? His name was Dr. Sbaitso [wikipedia.org].

  • "This one goes in your mouth, this one goes in your butt."
  • by Anonymous Coward on Wednesday February 13, 2013 @07:46PM (#42889837)

    The problem with doctors is their ego. Being a nurse for quite some time Ive seen countless doctors come through the hospital that do not treat a patient properly, ignore patient complaints, dont treat problems aggresively enough, are too passive, and so on and the vast majority of them refuse to do otherwise because of their ego. They are doctors, no one should question them and they hate it when you do and when you do they dig their heels in and dont budge. Doctors are also human so they get tired of their job, they get lazy, they stop caring after awhile, they worry more about what they will do later than the problem at hand, they stay up too late.

    Ive also seen countless times people who swear by these doctors and will accuse of them of fault simply because the doctor has been nice to them. A doctor who is friendly can do no wrong in a patients eyes. Or a patient has some common problem that even a moron could treat, then when the doctor fixes them suddenly they become godlike.

    Personally I would trust the diagnosis of a machine that has more information programmed into it than a thousand doctors do collectively from allover the world.

    A machine can be a doctor because thats how doctors are trained, they are trained to be machines. They treat the problem, they do not treat the person. Treating the person is a nurses job. And treating the problem is simply nothing more than deduction. If patient has multiple problems then you take those numbers and it will lead you to the correct answer. Thats all being a doctor is, you look at the signs and symptoms, then you add them alltogether and you get the answer as to what the cause is. Its all a forumla and nothing more, there is no great mystery to it.

    • Re: (Score:2, Insightful)

      by Anonymous Coward
      Haha, spoken like a true bitter nurse. Believe me, as a physician, there are plenty of my colleagues with huge egos. Definitely. And with many diagnoses, they are indeed bread and butter, no-brainer treatment algorithms. But to generalize and say that applies to all patients, with all conditions, and there is no underlying mystery or art ever, is just well... quite far off the mark. Especially in a tertiary care referral center where all the rare and complicated cases come.
  • Same old objection (Score:5, Insightful)

    by pclminion (145572) on Wednesday February 13, 2013 @07:55PM (#42889933)
    Apart from doctors who will understandably not want to be rendered obsolete (and they won't be -- the computer can only prescribe a treatment, not administer it!), the main objection that would be raised to this is "What if the computer makes a mistake?" For some reason, people are really bad at understanding that even though the computer might make a mistake, it will make mistakes at a lower rate than a human. This is the same problem with computer-driven automobiles. Yes, the computer might screw something up and kill somebody, but this should happen at a much lower rate than caused by human drivers -- however, because the rate isn't EXACTLY ZERO it is seen as completely unacceptable, even though this is an irrational position to maintain.
    • by jmv (93421)

      And the solution to both objections (including doctors not wanting to be obsolete) is to have the machine *assist* the doctor, in a similar way that auto-pilots assist but do not replace pilots.

  • by anthony_greer (2623521) on Wednesday February 13, 2013 @08:02PM (#42890015)

    This sort of thing is just what big pharma wants, no human interaction and careful consideration, just a pill dispenser...symptom a + symptom B == Pill 2...
    How much you wanna bet this thing always prescribes expensive non generic drugs and never tries the 50-70 year old known treatments that are usually the first steps in treatment before new expensive drugs are prescribed.

    Also, anyone notice the change in medical advertising and communications, they never say "ask your doctor" any more, its ask your prescriber, or ask your provider...like they want to dis-intermediate doctors and are getting the public ready.

    • by gringer (252588)

      This sort of thing is just what big pharma wants, no human interaction and careful consideration, just a pill dispenser...symptom a + symptom B == Pill 2...
      How much you wanna bet this thing always prescribes expensive non generic drugs and never tries the 50-70 year old known treatments that are usually the first steps in treatment before new expensive drugs are prescribed.

      It's more difficult to bribe computers, so I'd doubt this is what big pharma wants. A properly designed diagnosis system (open source, or government-managed) should offer the cheapest efficacious drug, rather than the latest drug that has been shown to be more effective than a placebo (but curiously untested in effectiveness against the most effective generic drug).

      • by dasunt (249686)

        It's more difficult to bribe computers, so I'd doubt this is what big pharma wants. A properly designed diagnosis system (open source, or government-managed) should offer the cheapest efficacious drug, rather than the latest drug that has been shown to be more effective than a placebo (but curiously untested in effectiveness against the most effective generic drug).

        Don't forget, the placebo effect may also apply to doctors, who could be biased towards the latest and greatest drugs.

        A computer would not ha

    • Easy enough, let them output the diagnosis and the chemical compounds that can cure it. Provide a list of all current remedies that contain those compounds in the right quantities, sort by secondary effects, descending.
  • by CannonballHead (842625) on Wednesday February 13, 2013 @08:13PM (#42890127)

    ... is that the computer doesn't have, literally, hands-on experience.

    For example... you have stomach pain. Okay. Where? Does this hurt? Does it hurt if I poke this? Do you have a fever? How high? ("Oh, I don't know, maybe XX" ...)...

    In other words, you still need someone who *knows* what to do to help diagnose simply to *get* the information. You need someone trained to know where to poke, where to tap, where to see if something hurts. And then, of course, to try to wheedle the real information out rather than the confusing answers patients (note that I am not a doctor, I am a patient) give. :)

    As a diagnostic tool, I think it would be a huge benefit. An individual simply can't keep up to date on everything, don't know everything, and can't research everything. Having a diagnostic tool that *does* do all that would be a huge benefit. There would be options and diagnoses that perhaps the doctor had not thought about. Additionally, the diagnostic tool - I hope! - would not just say "Oh, it's this" but would perhaps say "Well, it could be this, and you need to find out this information first ... or it could be this, and for that you need to do these tests..."

    The idea that a patient, combined with a non-trained non-doctor, can somehow come up with all the right answers/information and a machine can simply diagnose it on the spot seems like a very simplistic view. Perhaps that works with colds, the flu, or warts... but for more complex things... it seems diagnoses tend to work on a "it could be this; let's do more specific tests to find out if it is" type of investigation.

  • Perhaps Drs could use a tool like this similar to how weather predictions are done. Run the model(s), and use human analysis to weigh the data.
  • by SCHecklerX (229973) <thecaptain@captaincodo.net> on Wednesday February 13, 2013 @08:19PM (#42890189) Homepage

    In my experience, most doctors don't really think about problems, but just look at historical remedies and prescribe those particular drugs. They just regurgitate what is in the books. If you have something new or multiple problems (I've been dealing with this for a year now, with no relief in sight), I think I'd rather listen to watson. These guys have cost me thousands of dollars and all of my vacation time and I'm worse than when the problems started.

  • by DarthBobo (152187) on Wednesday February 13, 2013 @08:36PM (#42890385)

    Probably because its a summary of a press release, rather than the actual paper. This was a computer simulation exercise - a model. No patients were actually treated. There was no prescribing. There were no superior outcomes. Its all hypothetical.

    Could an AI outperform an MD? Sure, could happen and probably will eventually. But this model doesn't show that. It just shows that its easier to model health care in silicon than the real world. Remember we can cure cancer in mice - models aren't the same thing as reality.

    • Of course the simulation will side with its own kind. That's why the AI won.

      (For the humour impaired, this was intended as a funny. Though, admittedly, it probably didn't succeed.)

  • I've read similar stories about set steps being better able to deal with certain medical emergencies than just 'doing what's standard', and thought the IBM Big Blue computer and the way it operates would be a boon to medical sciences...and this would have been an amazing episode of House: where he competes against something like a medical version of Big Blue. =)
  • One thing I would like to see in these AI systems is occasional variations in their recommendations (for each given symptom set) for experimental purposes. It would be easy to code, and the results could be used to help choose the best outcomes. If two different treatments appear equivalent in outcome, the AIs should prescribe them randomly in a 50/50 ratio, modifying the ratio as new evidence arrives.

    (This sort of thing is analyzed by the online advertising industry as a "multi-armed bandit")

Our informal mission is to improve the love life of operators worldwide. -- Peter Behrendt, president of Exabyte

Working...