Please create an account to participate in the Slashdot moderation system

 



Forgot your password?
typodupeerror
×
Math Medicine Science

Algorithm Contest Aims To Predict Health Problems 138

databuff writes "The April 4 launch of the $3 million Heritage Health Prize has been announced by the Heritage Provider Network, a network of doctors. The competition challenges data hackers to build algorithms that predict who will go to the hospital in the next year, so that preventative action can be taken. An algorithm might find that somebody with diabetes, hypertension and high cholesterol is a 90 per cent risk for hospitalization. Knowing this, it might be cheaper for an HMO to enroll them in an exercise program now rather than pay the likely hospital bill. The competition takes the same approach as the $1 million Netflix Prize, but solves a far more significant problem."
This discussion has been archived. No new comments can be posted.

Algorithm Contest Aims To Predict Health Problems

Comments Filter:
  • by Anonymous Coward on Friday February 04, 2011 @05:42PM (#35107678)

    Just label them as a 'High Risk Candidate' and jack up their premiums 2-3x so they can no longer afford healthcare by the point at which they need service :P

    • How does this fit in with Obamacare?
      • by geekoid ( 135745 )

        The Government Health Care policy will stop them from doing it anymore.

        • "The Government Health Care policy will stop them from doing it anymore."

          ON the other hand...the feds just might use it...to decide on your method and amount of care you will get...?

      • by AHuxley ( 892839 )
        It depends who is paying and why.
        If your shareholders are paying, better to steam the sickest away from your care. Everyday they stay sick with you is a real loss.
        If your shareholders can bill the US gov, steam the sickest to extra care that makes a profit and improves 'positive outcome' stats.
        If your a gov, steam the sick bright young people to extra care that protects future tax payers and skills base.
        If your a gov, steam the sick old people to less care that protects tax payers.
    • Safeway (Score:5, Interesting)

      by MrEricSir ( 398214 ) on Friday February 04, 2011 @05:49PM (#35107740) Homepage

      That's likely what will happen, but not necessarily the only result.

      To lower company premiums, Safeway bribes employees to quit smoking and/or lose weight:
      http://online.wsj.com/article/SB124476804026308603.html [wsj.com]

      • I'm 6'3" 155lbs and I've never smoked more than the occasional cigar. My doctor is always surprised to see me for an annual physical, in his clinical opinion he doesn't need to see me more often than every 3 years.

        Whats in programs like this for me? Do I get rewarded for being healthy or should I take up smoking and then quit to get my prize for doing what I'm supposed to do to take care of myself?

        • The same thing applies to non-smokers with regard to smoking breaks. You'd be an idiot to take up smoking just for that incentive.
        • Re:Safeway (Score:4, Insightful)

          by MrEricSir ( 398214 ) on Friday February 04, 2011 @06:30PM (#35108058) Homepage

          Your reward is a long, healthy life. That's more valuable than money, IMO.

          • Or until you get run over by the a school bus being driven by a drunk, overweight, chain-smoking loser who will spend the rest of his long, unproductive life behind bars.
        • Read the article. Yes, you do get rewarded for being healthy. They discount the employee-paid portion of health care premiums if you elect to take, and pass, various physical tests. Eg. nonsmokers pay $312 less annually than smokers.

          • How is being a "nonsmoker" taking, and passing a "physical test"?

            • It proves that, during the interview with your company's healthcare rep, the overwhelming cologne was just bad taste rather than covering for lying about your tobacco addiction.
          • But how common is that? This is more or less the first time I've ever heard about that, more generally if you're taking care of yourself the only reward is possible good health in the future, even as you subsidize the care for people that don't care about how they take care of themselves. People who have genetic risk factors benefiting doesn't bother me at all.

        • By my algorithm you'd be forced to get another doctor that wasn't a waster or pay more. Okay, maybe it's simple, but it is effective which I can prove with personal experience.

          Here's the algorithm:

          If ((you can pass your doctor on the street) && (they don't recognize you)){
          you = in trouble;
          }else{
          you = good;
          }

          Here's the anecdotal proof:

          A few years ago life seemed to be really coming together. Happily married, just bought my favorite house in the area, was coding like a rock s
      • That's interesting, because Americans are always telling us that universal healthcare is bad because it means people interfering with their lifestyle choices. Yet here in the land of the free, we have people being fined for smoking and being fat, something which doesn't happen in socialist healthcare systems.

    • Don't worry, other countries will make proper use of that technology to safe money _AND_ provide better health care at the same time.

  • then print "Not good"

    • Oh come on, I know some Sumo Wrestlers that are in great shape!
      • Along those lines, I'd like to point out that "egg-shaped" is, per definition, a shape. A good shape, even, for selected applications. (Like for an egg.)

        "I'm not out of shape. This (gestures at rotund body) is a shape, you Sesame Street failure."

        • It's idiomatic in nature, as is most of the language. Or are you one of those people who gets asked out and immediately leaves the room?

  • sounds like a way to cheat the system on something LasVegas probably has a line on already...have you seen what they are betting on for the Superbowl? How long will it take Christina Aguilera to sing the National Anthem, Will Fergie be dressed as a Dallas Cowboys Cheerleader at any point during the Halftime show...

    -Tm

    • Yeah, I am out in Sin City, and you do not even want to know what I bet on, but if there is another nipple slip, I will be one rich man
  • by Anonymous Coward

    ... I am sparing my mad skills for the 'predict the next to commit a crime' contest.

  • Might be a good thing for our health-care system, but I doubt that it would be implemented - too much red tape around privacy and the data is not centralized, so it could be hard to have access to this data.
    • the data is not centralized

      Actually a solid argument could be made that the data is centralized, you just don't have access to it because your insurance company makes more money by not allowing you to access it. Insurance companies have plenty of centralized data on plenty of people in this country; enough to make very solid models - particularly models for the types of people that the insurance companies are most concerned about.

      If you could get the data from just one big insurance company or HMO - like perhaps the one that is advertising on this story - you could get plenty of data to build your algorithm. You just have to convince them that you are worthy of access to it (even if it has the personal identifiers removed).

      • Well, typically until you get to the hospital insurance company doesn't know much about you - may be your age, sex, may be height and weight, but they don't typically ask for this info when you sign up for insurance. And even after you get into hospital the information about you is in hospital records and not in the insurance company possession - they just know the procedures performed. So, the initial data about you is in the hospital (blood pressure, sugar level, weight, etc.) And in the hospital it could
        • by praxis ( 19962 ) on Friday February 04, 2011 @06:28PM (#35108028)

          You've never enrolled in insurance have you? They don't ask this for employer-provided insurance, since that's a different kind of coverage (where they have models for the type of employees that employer tends to employ, etc). For those cases, they rely on the principles insurance is suppose to rely on, for individual buyers, they give you an anal probe and only enroll you if you are not likely to need their services.

          • Smart individual buyers join a professional or other organization that has their own group.

            IEEE makes you wait a year to get into their health insurance group. It's worth joining while you have a job so you have backup group insurance available.

            • by praxis ( 19962 )

              That's very good advice. My point was that for groups of "known" quantities they ask for far less information than for random individuals. Not everyone falls into the "they hardly know anything about you" camp.

        • Well, typically until you get to the hospital insurance company doesn't know much about you - may be your age, sex, may be height and weight, but they don't typically ask for this info when you sign up for insurance.

          When I applied for private health insurance (as opposed to company-provided insurance), part of the application was six pages of "Have you been treated by a medical professional for such-and-such in the past one year, three years, or ten years?". This was in addition to things like age, sex, sm

    • uhh, the health care incentives that are part of ARRA will have moved nearly the entire health system to a completely electronic patient record that has the ability to share data between providers by 2016. I say nearly only because I am sure some providers will not be able to meet the incentives deadline and will start getting penalized for not being there, but with in a few years of the deadline, everyone will have gotten there.

  • The Netflix Prize was sponsored by the company who gained the most from it. In the same vein, this should then be sponsored by an HMO.
  • The purpose of insurance is cover random catastrophic expenses, not to let a person cost-shift known expenses to his or her neighbors. If your body is breaking down because you spend decades being fat and never did anything about it then foot the bill yourself. If you can't afford the cost of fixing a problem caused by your own lifestyle decisions then tough shit.

    • by Locke2005 ( 849178 ) on Friday February 04, 2011 @06:06PM (#35107882)
      Very few medical conditions are caused purely by lifestyle choices. Genetics play a big role. Many catastrophic expenses are due to catastrophic events, like car accidents. Even HIV is not always caused by life style choices -- millions of babies are born with it, and there is no way of determining whether a health care worker contracted it because of their job or because of their choice of sex partners.

      That being said, I agree with you in principle. Public health care should be targeted at prevention and diagnostics. Catastrophic health care should be covered by insurance; if you don't pay for insurance, you're out of luck. That still doesn't change the fact that 90% of most people's health care expenses are incurred in the last 5 months of their lives, but cutting off funding for that would amount to a real version of the "death panels" the Republicans have falsely associated with the new Health Care act. Health insurance is so expensive because we simply refuse to let people die in peace.
      • by geekoid ( 135745 )

        When does there 5 months begin. you sick and in your twenties, how do you know that's not the last 5 months of your life?

        And by the way, Fuck dying in peace. I want to live as long as possible. Preferable forever, even if it's on a machine.

        • > I want to live as long as possible. Preferable forever...

          We can cover this by continuing to grow tissue samples of you for experimental purposes. Would you care to contribute your genome to science? [tvtropes.org]

        • I want to live as long as possible. Preferable forever, even if it's on a machine.

          If you can afford that, I'm happy to support you in your quest for immortality.

          But please don't make me, and my children, and their children (and so on) pay just because you refuse to die gracefully at some point.

      • by Wonko the Sane ( 25252 ) * on Friday February 04, 2011 @06:52PM (#35108222) Journal

        That still doesn't change the fact that 90% of most people's health care expenses are incurred in the last 5 months of their lives, but cutting off funding for that would amount to a real version of the "death panels" the Republicans have falsely associated with the new Health Care act.

        This problem will be solved shortly when Medicare melts down. Then people will get exactly as much end of life care as they can afford and no more.

        Which, in the end, is how it should have been done from the beginning. When there aren't enough resources to give everybody what they want then some kind of rationing will occur no matter how much people complain and protest about it. The only decision to make is whether to have rationing by price or rationing by fiat. Rationing by price is the superior solution because then market forces will provide incentives to bring the costs down to increase the number of potential customers. Rationing by fiat puts everybody at the mercy of unelected bureaucrats.

        To see how this works compare the prices of procedures that people normally pay out of pocket vs procedures that people normally pay for with OPM. Laser eye surgery has been getting cheaper over the years. Anything covered by Medicare or private health insurance has been getting more expensive.

        • by Xyrus ( 755017 )

          Rationing by price is the superior solution because then market forces will provide incentives to bring the costs down to increase the number of potential customers.

          Now how the hell is that going to work with insurance? Insurance companies make money when they take your premiums and then GIVE YOU NOTHING BACK. Then add in the primary driver for insurance rates are the ODDS, and the whole market-driven mantra falls apart. No amount of market competition is going change the underlying odds the insurance companies are betting with.

          Healthcare by price as you describe in your "superior solution" will screw over everyone who is not healthy or wealthy. Insurance companies DO

          • Now how the hell is that going to work with insurance?

            It doesn't.

            End of life care is not something that should be covered by health insurance. There's a reason that collision insurance for your car doesn't cover replacing engine components when they start to wear out due to age.

        • The only decision to make is whether to have rationing by price or rationing by fiat.

          You forgot rationing by fist, which is what will happen if Medicare breaks down. In the end the mob is far more efficient than the market.

          • if Medicare breaks down

            How many years in a row do you think the US government can get away with borrowing nearly 50% of the budget? They're going to try to borrow another $2 trillion in calender year 2011, up from $1.7 trillion last year. What would it do to your finances if you charged a sum equal to your income on credit cards for four years in a row?

            • You're not addressing my point.

              • What point? The fact that there's probably going to be riots when the US Government loses the ability to hand out free shit? That's a given.

                Mobs don't really loot services though. When civil order breaks down people will break into the liquor stores and run off with as much booze as they can carry but they can't really do that with an appendectomy.

      • Public health care should be targeted at prevention and diagnostics. Catastrophic health care should be covered by insurance; if you don't pay for insurance, you're out of luck. That still doesn't change the fact that 90% of most people's health care expenses are incurred in the last 5 months of their lives, but cutting off funding for that would amount to a real version of the "death panels" the Republicans have falsely associated with the new Health Care act. Health insurance is so expensive because we simply refuse to let people die in peace.

        Given that people who are most likely dying, but possibly not -- terminal cancer patients, who spend unbelievable amounts of money on the slight chance they'll beat cancer -- have zero incentive to die in peace and an extremely high incentive to spend every penny they have on the slight chance they'll beat cancer, especially if the money actually belongs to their insurance company, and given that the health care industry, who makes money off providing health care, also has absolutely zero incentive to let p

        • Just remember that the religious right considers every life sacred, and that "letting grandma die in peace" is tantamount to murder. In fact, I think if they had there way, they would execute you for not doing everything possible to prolong your grandma's life, just to prove to you how sacred life really is!
      • You wrote, "Health insurance is so expensive because we simply refuse to let people die in peace."--- Where you get that from?

        I thought it's so expensive because it's a rip-off / blackmail industry. And regulated on top of that. Then, in the US add a little bit of racism to the reasons

      • This is where the cultural differences comes into play...

        You Americans call it "death panels" and denying people's right to try everything to stay alive, while over here we like to see it as a "dignified end" and use scares resources to help those who actually have a chance of a life worth living.

    • Re: (Score:2, Interesting)

      If you can't afford the cost of fixing a problem caused by your own lifestyle decisions then tough shit.

      Says the conservative who couldn't give a piss about anybody until it's about him.

      Since you're apparently not fat there's no chance you'll ever be in need of medical attention, but - just hypothetically - I'd love to be your insurance adjuster, playing by your own rules, if you ever did. The look on your face as we explain that we're denying your claim because of some arguably sub-optimal "lifestyle choice" you once made would be priceless. Eat meat? Play sports? Work a stressful job? Drive a car? You're on

      • If I was in the market for health insurance I would have no problem disclosing any of those factors and paying a premium appropriate to the risk. It's no different that a person who lives next to a river paying more for flood insurance than someone who lives on the top of a hill.

    • The purpose of insurance is whatever the insurers and insured agree it is.
      • They can try but certain classes of expenses by their nature aren't insurable. A contract to do an impossible thing is no contract at all.

    • by Xyrus ( 755017 )

      I never said anything about cost-shifting Fat Bastard, nor was that the point of the GP. I was refuting the inane logic that market forces would somehow magically lower insurance premiums so that everyone can afford it. In fact, I believe I stated that insurance companies play the odds and don't make stupid bets (i.e. taking on coverage for Fat Bastard without an increase in premium).

      The health insurance industry is not about getting people adequate health coverage, nor should it be. It's about making money

      • I was refuting the inane logic that market forces would somehow magically lower insurance premiums so that everyone can afford it. In fact, I believe I stated that insurance companies play the odds and don't make stupid bets

        Market forces will lower the cost of medical procedures, not insurance premiums. But this will only happen with medical procedures that are paid for out of pocket. The problem is excessive "insurance", not insufficient insurance.

  • OR (Score:4, Insightful)

    by Anonymous Coward on Friday February 04, 2011 @05:54PM (#35107782)
    "Knowing this, it might be cheaper for an HMO to enroll them in an exercise program" OR DROP THEIR COVERAGE!
    • Thankfully, under Obamacare, that's not legal.

      If they can't kick you to the curb, they've got to try Plan B, which is improving your health before you cost them money.
    • by the way ( 22503 )

      "Knowing this, it might be cheaper for an HMO to enroll them in an exercise program" OR DROP THEIR COVERAGE!

      They're a network of doctors and specialists, not an insurer - so this is completely irrelevant to the company sponsoring this. All they can do with the results (and they'll be the one that gets the algorithm, and it's using their data) is use it to tell their docs which of their patients need more (or different) help.

  • by CrazyJim1 ( 809850 ) on Friday February 04, 2011 @05:56PM (#35107794) Journal
    Contest judge,"Why I'm perfectly healthy, why would you pick me?"
    Fat Tony: *punch to the face of contest judge*
    Contest judge,"Well I see your point, but that isn't exactly going to send me to the hospital."
    Fat Tony: *draws a gun*
    Contest Judge,"Ok ok, I'll go to the hospital, here's your money."
    Fat Tony,"Who says I want your money?"
  • In a way, doctors are trained to ignore teh science. They start with someone who already has a problem, and treat the symptoms as best they can. Science has determined many of the causes, but they are not profitable for the oligarchy, so they train our doctors to sell us pills for the symptoms.

    somebody with diabetes, hypertension and high cholesterol is a 90 per cent risk for hospitalization. Knowing this, it might be cheaper for an HMO to enroll them in an exercise program now rather than pay the likely hospital bill.

    The Lipid Peroxidation [wikipedia.org] chain reaction is a large part of what causes the diabetes, hypertension and [oxidized] cholesterol problems.

    Lipid peroxidation is such a huge problem today because the western world switched it

    • "In a way, doctors are trained to ignore teh science. They start with someone who already has a problem, and treat the symptoms as best they can. Science has determined many of the causes, but they are not profitable for the oligarchy, so they train our doctors to sell us pills for the symptoms"

      that is completely false. While may Dr.s are not scientists, they still prefer to cure someone. It's a lie perpetrated by people whose own 'belief' aren't born out scientifically. Since they are so attached to them they invoke conspiracy that are nonsense.

      "The Lipid Peroxidation [wikipedia.org] chain reaction is a large part of what causes the diabetes, hypertension and [oxidized] cholesterol problems.":
      That is complete nonsense.

      speaking of doctors and science:

      http://www.sciencebasedmedicine.org/ [sciencebasedmedicine.org]

      • by nido ( 102070 )

        While may Dr.s are not scientists, they still prefer to cure someone.

        Of course, but their training is deficient. If you spend years learning the minutia of pharmacology and surgery, it's easy to "miss the forest for the trees". If your doctor's training only gives a cursory overview of the role of nutrition, AND the conventional wisdom about certain nutritional concepts is wrong (e.g. saturated fats were vilified so A.D.M. [wikipedia.org] can make billions selling seed oils), your doctor is going to be biased for the things that he spent the majority of his training learning about.

        The Lipid Peroxidation [wikipedia.org] chain reaction is a large part of what causes the diabetes, hypertension and [oxidized] cholesterol problems.

        That is complete nonsense.

        Are you d

  • The competition challenges data hackers to build algorithms that predict who will go to the hospital in the next year, so that they can be dropped.

    fixed.

    • by geekoid ( 135745 )

      "Do your own research. Draw your own conclusions. "

      That , my friend, is the basics for a disaster.

      Most people don't known how to do research, don't know a well done study vs a poorly done study. Most people will only cherry pick data that confirms their own bias.

      Plus it will be done in a manner without review.

      Learn how to read a study, learn what makes an actual expert, and pay attention.

  • Why don't they just build a lottery machine to approximate it and sell another lottery game at convenience stores? Let people pay to run around going to all of the stores to find the algorithm which most correctly approximates the data.

  • Probability of visiting a hospital in the next year P

    P = R

    Where R = 1 if

    - you ride a motorbike
    - you're one of (bullfighter, boxer, lumberjack, cheerleader)
    - you consume more than 30 hamburgers per week
    - you consume more than 1 bottle of whiskey a day or equivalent

    Now where's my 3 million?

  • "Health Insurance company offers $3 million dollar bounty for technical-sounding excuse to raise premiums"
    • That's what they're hoping for. I'm fortunate enough to live in a state where the insurance commissioner has to approve rate increases. Which means that when an insurance company wants to raise premiums they have to provide the commissioner's office with the data that shows that it's reasonable from an actuarial stand point. Fortunately, this is now much more widespread as of the beginning of the year now that all insurance companies have to spend at least 80% of their premiums on care or improving the heal

  • Just measure carbohydrate intake. That correlates with all of the "diseases of civilization", like obesity, diabetes, heart disease, cancer, alzheimer's and other chronic diseases.

    • Just measure carbohydrate intake. That correlates with all of the "diseases of civilization", like obesity, diabetes, heart disease, cancer, alzheimer's and other chronic diseases.

      Of course! It's just that simple. Why didn't anybody think of that sooner?

      You need to read up on human diseases a bit more. And no, you cannot jump from rodent longevity using caloric restriction to broad brushing carbohydrates as the boogyman for western health care issues.

  • I like how everyone and their uncle suddenly runs a competition with a grand prize for the lucky one who meets the goal.

    Need a new company logo? You could hire a graphic designer. Or you run a design competition, first prize an iPad. Much cheaper than paying someone, and the blogs will pick it up for free advertisement. Then you shell out the shinny gadget and look charitable.

    Anyone interested in a basement-cleanup-competition?

    • by geekoid ( 135745 )

      Depends, what's the prize?

    • Yeah, if it's a sizable prize it can be worthwhile, but most of the time they're giving out trinkets in exchange for a potentially large amount of wasted effort. The fame is really the only worthwhile prize from some of these competitions. And even then you'd be better off just giving the product away or selling it after you've finished it.

  • Population - Population that will die = Chances of them making an algorithm that predicts Health Problems Correctly for Individuals.

  • From TFA

    "There are two problems with the healthcare reform law," said Jonathan Gluck, a senior executive at HPN. "We pay for quantity, not quality. The more services provided, the more the provider gets paid."

    The second is that we can't count to two.

The "cutting edge" is getting rather dull. -- Andy Purshottam

Working...