Slashdot Mirror

← Back to Stories (view on slashdot.org)

IBM's Watson Used In Life-Saving Medical Diagnosis (businessinsider.co.id)

Posted by EditorDavid on from the damn-it-Jim-I'm-a-doctor-not-a-supercomputer dept.

"Supercomputing has another use," writes Slashdot reader rmdingler, sharing a story that quotes David Kenny, the General Manager of IBM Watson: "There's a 60-year-old woman in Tokyo. She was at the University of Tokyo. She had been diagnosed with leukemia six years ago. She was living, but not healthy. So the University of Tokyo ran her genomic sequence through Watson and it was able to ascertain that they were off by one thing. Actually, she had two strains of leukemia. They did treat her and she is healthy."

"That's one example. Statistically, we're seeing that about one third of the time, Watson is proposing an additional diagnosis."

24 of 83 comments (clear)

  1. DNA Sequencing by Anonymous Coward · · Score: 3, Informative

    Leaving aside IBM plugging Watson, which is just them trying to market a brand into healthcare, the actual Leukemia detection was DNA sequencing with abnormalities correlated to research papers.

    That in turn suggested she was pre-disposed to Myelodysplastic cancers, and needed blood transfusions, and other support drugs.

    It looks like IBM wants to perform the middle-man deception on an epic scale here. Where the 'expertise' is being presented as IBMs when in fact its just searching others research papers with a not-very good language parser to grab references to the gene from the documents.

    1. Re:DNA Sequencing by NotInHere · · Score: 2

      I fully agree. The entire gene analyzing startup industry does this though, like 23andme or others. They are basically grep inc.

    2. Re:DNA Sequencing by Comrade+Ogilvy · · Score: 4, Insightful

      What Watson did is something any intern with time on his or her hands could have achieved by looking at the data, searching in a medical database, and then a long bit of drudgery finding the wheat among the chaff. And if it were an intern, we would applaud that person for surprising tenacity and "vision" in helping a patient when seasoned doctors failed.

      Why do you need to denigrate that? Why do you need to concoct a phony baloney different standard when a computer succeeds where humans failed?

    3. Re: DNA Sequencing by Anonymous Coward · · Score: 3, Insightful

      I think some people just reduce all problems to a basic summary, then once they can feel superior by letting everyone know that if it's just such a basic thing they could do it in a few lines of perl that they're clearly winning at life and these other engineers are just faking it and deserve zero credit.

      It's a way of masking their own insecurities.

  2. Native advertising by thesjaakspoiler · · Score: 2

    .. did not know it would pop up so prominently on /.

  3. Watson is the future...and the future is good. by Comrade+Ogilvy · · Score: 5, Insightful

    My personal opinion is most doctors are probably pretty bad at diagnosing non-obvious issues. We do not actually need Watson to replace the doctors. We need Watson as another opinion who looks at the data in another way, and can usefully point to the long tail of uncommon to rare things that have a statically reasonable likelihood of being relevant. Many of these uncommon things, why would expect a doctor to actually be competent at diagnosing them? When would they have built that kind expertise?

    Taking TFA at face value, the doctors were ignoring data right under their noses. Watson found it by simply looking. It is not a matter of Watson have some magical genius. It is a matter of Watson being simply and thoroughly competent at many, many easy things that most doctors can never be expected to learn.

    1. Re:Watson is the future...and the future is good. by geekmux · · Score: 2

      My personal opinion is most doctors are probably pretty bad at diagnosing non-obvious issues. We do not actually need Watson to replace the doctors. We need Watson as another opinion who looks at the data in another way, and can usefully point to the long tail of uncommon to rare things that have a statically reasonable likelihood of being relevant. Many of these uncommon things, why would expect a doctor to actually be competent at diagnosing them? When would they have built that kind expertise?

      Taking TFA at face value, the doctors were ignoring data right under their noses. Watson found it by simply looking. It is not a matter of Watson have some magical genius. It is a matter of Watson being simply and thoroughly competent at many, many easy things that most doctors can never be expected to learn.

      In other words, we DO actually need Watson to replace the doctors, which you have quite clearly demonstrated to be incompetent of providing accurate diagnoses that include ALL variables due to the overall complexity today.

      By the way, this concept should be familiar, as years ago computers started replacing human work. It only makes sense that evolution continues where complexities are well beyond a human capability.

  4. Re:Let's see Watson get it *wrong*. by skids · · Score: 4, Insightful

    1) Why? Why would it be nice?
    2) Since it is an expert system, it probably already has an error rate. That's how expert systems work. They generate probable leads which feed into a diagnostic process as one contributing input. All IBM needs to prove here is that the leads a probabilistically worth the cost to generate them and the cost to follow up on them.

    --
    Someone had to do it.
  5. Re:That's nice and all, but by fox171171 · · Score: 4, Insightful

    Kenny says that what Watson is not just being used to cure cancer, "but to just recommend what you should watch next" and even to recommend âoewhat ad you you should watch next."

    That's what Watson is really being used for, fucking advertising. And it didn't "cure" cancer, either.

    Yes, that woman should have quietly died waiting for a human doctor to figure out what was wrong with her.

  6. "You've got leprosy, goodbye." by Joe_Dragon · · Score: 2

    "You've got leprosy, goodbye."

    1. Re:"You've got leprosy, goodbye." by Z00L00K · · Score: 3, Informative

      Considering some diseases out there it would be a relief to get that diagnosis.

      --
      If builders built buildings the way programmers wrote programs, then the first woodpecker would destroy civilization.
  7. Re:Let's see Watson get it *wrong*. by ShooterNeo · · Score: 4, Insightful

    I'm sure it gets it wrong lots of times, but so do humans. It's only a problem (with Watson) if humans wrongfully assume it to be infallible or if Watson gets it wrong so often it's useless. This does not seem to be the case.

  8. Moores Law by beckett · · Score: 2

    How much does it cost?

    Wait 18 months. If it's not cheap enough "out-of-pocket", then wait another iteration until the tech is ubiquitous.

    How much does it cost?

    And for fucks sake, get your country single payer, universal health coverage already.

    1. Re:Moores Law by yuriklastalov · · Score: 2

      I, too, want Donald Trump to pick who is in charge of the health system. What could possibly go wrong? And just think about the endless arguments about whether the single payer should cover things like birth control or abortions. Really though, isn't it just time for the government to openly declare us subjects, and quit pussy footing around pretending it doesn't own us, mind, body, and soul?

  9. Re:what is a "strain" of leukemia? by Bite+The+Pillow · · Score: 2

    Shitty reporting doesn't mean facts aren't facts. Be suspicious after reading the peer reviewed paper, or a statement directly from the team. Critique of a Dashslot summary is no art form...

  10. N=1, no details by nbauman · · Score: 5, Insightful

    There's a 60-year-old woman in Tokyo. She was at the University of Tokyo. She had been diagnosed with leukemia six years ago. She was living, but not healthy. So the University of Tokyo ran her genomic sequence through Watson and it was able to ascertain that they were off by one thing. Actually, she had two strains of leukemia. The did treat her and she is healthy.

    This is one anecdote by David Kenny, General Manager of IBM Watson, who has no medical expertise. He's a computer salesman and this is his pitch. Have you ever heard of a computer salesman making a promise that turned out to be an exaggeration?

    This is the kind of story I used to see about miracle cures from vitamins or fad diets or Burzynski's Clinic: a vague description ending in a miraculous cure that is impossible to verify.

    Kenny doesn't even describe the case. She had "leukemia." What kind of leukemia? There are at least 4 major types of leukemia, and many subtypes.

    Some of them have effective treatments, some of them don't.

    Some of them have a median survival of 6 months, some of them have a median survival of 20 years. Since she's been alive for 6 years she doesn't have the most deadly type.

    It looks as if they found a mutation which suggested that one drug would be more effective than another, which is routine these days. You don't need a supercomputer to do that. You do need a randomized, controlled trial to see if using Watson actually leads to better survival than doctors can get without Watson.

    She's healthy? What does "healthy" mean? What does "not healthy" mean? Those aren't medical terms.

    If they're serious about this, publish in a medical journal.

    1. Re:N=1, no details by nbauman · · Score: 2

      Have you ever looked up a disturbing symptom on the Internet? Have you done it not just once, but several times?

      If you do a thorough search, you'll find that most symptoms have a differential diagnosis that includes cancer. In other words, the problem with Google searches is massive false positives.

      There's a medical student's joke: If your doctor asks you what's wrong with this patient, say, "It's either cancer, an autoimmune disease, or an infection." The joke is that most symptoms could be either cancer, autoimmune disease, or infection.

      The problem with medical diagnosis is that most major diseases have overlapping symptoms. Does this patient have heart failure or lung failure? Does this patient have rheumatoid arthritis, psoriatic arthritis, or ankylosing spondylitis? Or is it Wegener's granulomatosis, which is a medical emergency and can cause blindness?

      I just read an article about lyme disease. One of the big problems with lyme disease is that it starts with an infection. Then the infection is cleared, and you're left with an autoimmune disease. If it's an infection, the way to treat it is with antibiotics. If it's an autoimmune disease, the way to treat it is with drugs like steroids, which turn the immune system down. But if you treat an infection with steroids, the immune system will be less able to fight an infection.

      In New York State (and most states), it's outside the nurses' scope of practice to diagnose disorders. If a nurse diagnoses diseases, she could lose her license. There's a reason for that. Medical students get thousands of hours training seeing patients with different diseases and learning how to diagnose them. Nursing students get hundreds of hours, and their training is not directed at diagnosis. Nurses are pretty smart. They know a lot of biology, chemistry and medicine. But most important, they (usually) know what they don't know.

      My health insurer has a nurse telephone hotline. I've tried it a few times, mostly out of curiosity. One day I had some vague symptoms including dizziness and what could be shortness of breath. (Probably from sitting at my desk all day.) I figured more advice is better. I described my symptoms and she said, you should go to the doctor immediately. Go to your own doctor or the emergency room.

      I said, what's the problem? What should I tell them when I get to the ER?

      She said, you have symptoms of heart failure.

      I said, that's impossible. I walk up 5 flights of stairs every week. How did you come to this conclusion?

      She said she was using a "decision aid."

      I said, what decision aid? I have to tell them when I get to the ER. She was evasive. Finally she admitted that she looked it up on the Internet. I said, where on the Internet? She was even more evasive. I said, is there a blue bar on the top of the page? What does it say in the blue bar?

      She said, "Medscape."

      I said, I write for Medscape. I wouldn't want people to diagnose a disease based on my stories.

      I got one thing out of it. I was able to call my doctor's office and tell them that a nurse had told me to see a doctor immediately. They gave me an appointment immediately.

      I told my doctor, I can climb 5 flights of stairs.

      He laughed and said, if you can climb 5 flights of stairs, you don't have heart failure.

      Conclusion 1: These decision guides and algorithms have been around long before the Internet. I read about them in Scientific American from the early 1970s. The futurists, and computer salesmen, in their irresponsible moments, claimed that they would replace doctors.

      They failed. Computer diagnosis has now achieved its rightful place in medicine as the place for doctors to go when they could use more information. But you can only do that if you have the medical training to understand what you're getting, how the algorithm works, and what it's doing. You need doctors, and sometimes specialists, to see whether the results make sense.

      If you have a man who can climb 5 flights of stairs, a

    2. Re:N=1, no details by cellocgw · · Score: 2

      Except that you are wrong about your own diagnosis. I have a friend who's a former Olympic rower, and competes in Senior class to this day. About 15 yrs ago he got up one morning and felt extremelydizzy and weak. Med exam revealed a heart valve failure.
      So that's nice you ran up X flights of stairs. It doesn't preclude a heart problem.

      --
      https://app.box.com/WitthoftResume Code: https://github.com/cellocgw
  11. Re:Let's see Watson get it *wrong*. by Z00L00K · · Score: 2

    Which is no different from what doctors make today. There are a lot of doctors taking guesstimates from the sampled data they have on a patient. Unfortunately they don't always listen to the patient and think that the problem is solved when they have put in a treatment. Sometimes that causes patients to get a treatment on anti-depressants when the problem is with the thyroid. So they are just hiding the symptoms.

    --
    If builders built buildings the way programmers wrote programs, then the first woodpecker would destroy civilization.
  12. Re:That's nice and all, but by Z00L00K · · Score: 2

    Not every country bills the patients.

    --
    If builders built buildings the way programmers wrote programs, then the first woodpecker would destroy civilization.
  13. Re:Me too, kinda by hidflect · · Score: 3

    I had a similar situation. I realised that doctors are just statisticians trained to pick the most likely cause regardless of hunches or suspicions. And so they also ignore you because what you say is anecdotal and not backed by statistical trial. If they waiver from that, they open themselves up to malpractice suits for ignoriing the statistically most likely cause. Only when they are sure the judgement is an error will they then move to the next most statistically likely cause, and so on.

  14. Re:Let's see a machine get it *wrong*. by geekmux · · Score: 3, Insightful

    Human superiority.

    Human superiority has brought unending amounts of narcissistic greed.

    Fuck human superiority. The truly superior human is the one who is humble enough to know when they are outmatched. We would all still be walking around with an abacus and riding horses with your mentality, fearful of anything that might make humans look weak or slow.

  15. Re:Let's see a machine get it *wrong*. by Excelcia · · Score: 5, Insightful

    This is human superiority. Watson isn't hard AI. It's not even soft AI. It's an expert system. It's a tool, like an x-ray or an MRI. Feed in genomic sequence, out pops matches with different strains of leukemia. It's a tool that will be excellent for fringe cases - when a doctor sees fifty cases that fit inside the bell curve, every case looks like one that should fit inside the bell curve. Especially if it requires actually doing something to investigate.

    Humans will never "compete" with a computer on its own turf. And people shouldn't feel like we have to try. Being less able to win at chess or come up with a fringe diagnosis than a computer is a win for human engineering and ingenuity. Feeling like humans have lost something by this is like feeling like we've lost something because we can't see into the x-ray bands to tell if someone's bones are broken.

    We build tools to expand our abilities, and that is what this is. Don't make it to be more or less than it is. It is a feat of human engineering and a tribute to those that built it. It isn't a symbol that humans are less capable or diminished.

  16. A Tale of Two Companies by QuietLagoon · · Score: 2

    IBM is crowing about saving peoples' lives. Microsoft is crowing about what is probably a couple of people switching from Mac to Surface.