Just Months After Jeopardy!, Watson Wows Doctors With Medical Knowledge

195 18 Loading

Try to make him feel welcomed. Reigning Jeopardy! champion and IBM robot, Watson, is devouring the material in medical textbooks and journal articles in hopes of landing a job as a physician's assistant.

The trainee was sequentially presented the details of a fictitious patient: there’s an eye problem; vision is blurred; the family, living in Connecticut, has a history of arthritis. The trainee’s initial response was uveitis. More clues and the diagnosis was changed to Behcet’s disease until finally the trainee settled on Lyme disease. How sure was this seemingly hasty student of medicine? Seventy-three percent sure.

Medical trainees and doctors are not typically in the habit of quantifying their assessments with such Commander Data-like precision, but this trainee happens to share more qualities with the Star Trek android than the rest of the medical staff. Following its resounding victory on Jeopardy!, IBM’s Watson has been working hard to learn as much about medicine as it can with a steady diet of medical textbooks and healthcare journals. The mock case described above was part of a recent demonstration to the Associated Press showing just how much Watson has learned. The robot’s diagnosis was correct and it identified a link between symptom and cause that was “not common,” as one participating physician called it. After being told the patient was pregnant and allergic to penicillin, Watson suggested treating her with cefuroxine. Its human colleagues agreed. The demonstration was a success, and it is the hope of IBM and many medical professionals that Watson will one day soon lend doctors a helping hand as they perform their daily rounds.

The need for efficient use of medical information becomes more pressing as the amount of information amasses at an exponential rate. Dr. Herbert Chase, a Columbia University medical school professor, tells the Associated Press that it has been 30 years since doctors were last able to keep pace with the growing body of medical knowledge. With only so many hours in an often overwhelming day, doctors are hopeless to keep up with a body of knowledge that doubles every five to seven years. In addition to the struggles of keeping pace, the sheer volume of information presents a separate challenge to share that information effectively. Michael Yuan, a scientist that has worked with IBM, cites a 1999 study that found doctors field more than 1,100 questions a day and fail to answer 64 percent of them. The inefficient exchange of information leads to mistakes in any field. In the medical field, those mistakes could cost lives. A widely-noted–and hotly debated–report published in 2000 estimated that as many as 98,000 people die in a given year from medical errors occurring in hospitals. As the report notes, “that’s more than die from motor vehicle accidents, breast cancer, or AIDS.”

Now imagine Watson on the job. Never one to nap in the library, Watson’s database would be updated daily with the latest in research from potentially all online journals. The director of Health Informatics Center at the University of Southern California, Carl Kesselman, points out the need to track advances in genomics, specialized drugs, off-label uses, and the increasingly finer-grained classifications of diseases. Of course the physicians themselves can find the information, but the online searches would be labor-intensive and time-consuming. A physician’s assistant like Watson with realtime updates could simply be asked Jeopardy!-style questions to find answers or get second opinions. To make the interactions Jeopardy!-style, speech solutions developer Nuance is currently working with IBM to provide Watson speech recognition software customized with medical jargon. Doctors could query Watson’s database on the go by speaking into a handheld device.

Not to be confused with Sherlock Holmes' sidekick, Watson is named after IBM founder Tom Watson.

At this early stage in its medical education Watson understandably, still makes mistakes. A team of medical students are working with Watson to catch mistakes and try to identify what causes them.

Its knowledge is not limited to science. Watson can also keep an eye on complex treatment guidelines that are often updated so the physician doesn’t have to. It can access medical records as well. However, for access to be completely streamlined they need to be digitized. Unfortunately the medical record digitization seems to be a change hospitals are thus far slow to adopt. Progress is being made, however, by companies like Practice Fusion, a maker of electronic health records (EHR) systems. Combining the latest medical knowledge with the patient’s medical history would give Watson the best chance to catch those rare cases that doctors might be slow to diagnose or miss altogether.

A major break from previous practice is IBM’s plan to include patient blogs among Watson’s data set. Much as they do now on websites such as carepages.com, patients can share symptoms, drug efficacy, drug side effects, relevant family histories, etc. Like a medical wikipedia, the data cloud that amasses could be mined by Watson to pull out obscure relationships that would normally pass under the radar of doctors concerned only with their patients. For example, cross-reactivity between two types of drugs that aren’t taken together very often. In essence, Watson would be conducting its own studies without a priori goals or limitations.

But the data is anecdotal, you say? Dr. Chase agrees, but argues that doctors are already using anecdotal data when they take medical histories. The patients’ descriptions are anecdotal, and the doctors don’t listen any less.

To me the patient blogosphere is the most exciting of Watson’s resources. What sort of insights into medicine and disease will we gain simply by blogging about our own experiences? As Wikipedia shows us, there’s truth in numbers. A major challenge to mining those insightful gems is blogs that are easily understandable to Watson. It’s one thing for a doctor to have a one-on-one conversation with Watson and refine his query when he inevitably runs up against misunderstandings. But it’s quite another thing to glean underlying facts from thousands of blogs from all over the world. A universal format for the patients would help, perhaps including a basic list of yes or no questions.

C'mon, admit it. You can hear the heart beat: "boomp...boomp...boomp..."

A know-it-all robotic physician’s assistant that you can talk to from anywhere with a handheld device. Reminds me, again, of Star Trek, “Computer, across how many worlds has the epidemic spread?” (Yes, that’s two Star Trek references in the same blog!). But one company would argue that it is years ahead of IBM in bringing AI to the forefront of medical diagnosis support–and her name is Isabel. Isabel Healthcare’s founder Jason Maude’s named the database program after his daughter who as a child was misdiagnosed with chicken pox (instead, she had two rare chickenpox-related complications). Created a decade ago, the company’s mission is to decrease misdiagnoses, and it performs essentially the same functions as Watson: symptoms are entered and the computer sifts the database to produce a list of the most likely causes. Isabel asks questions that the doctor might not think to ask, indicates the gold standard treatment, and lists relevant medical literature.

So, what do we need Watson for?

IBM executives point out that Watson is much faster than Isabel and much better at understanding terms that it hasn’t memorized from a textbook. Watson would know, for instance, that “difficulty swallowing” is “dysphagia.”

Watson has a ways to go before it makes the grade. IBM estimates that they are still a couple years away from making a marketable Watson. Doctors, IBM execs say, should not feel threatened by their fast learning student. The clinician’s role is to practice medicine and Watson’s role is to support the clinician, to act as a library. I have to admit, I’m skeptical. Medical students are a pretty ambitious lot. It may just be that beating two of the world’s best at Jeopardy! on primetime television isn’t enough for Watson. Maybe its done playing games and wants to contribute in a meaningful way to society.

Or, maybe Watson just wants to be called Doctor.

[image credits: modifed from Asset Protection Law Journal; Wikipedia; scoreforsale.com]
image 1: modified
image 2: Tom Watson
image 3: sickbay

Discussion — 18 Responses

  • Homer June 6, 2011 on 7:34 pm

    This is one of the most exciting topics being covered on futurist websites. It’s interesting that IBM is always careful to reassure physicians that they shouldn’t feel threatened by Watson. Why is Big Blue so eager not to alarm the docs?

    Google is developing automated cars, and we never hear them try to console cab drivers or chauffeurs. Makers of factory robots don’t reassure the UAW that their jobs will remain intact. And yet IBM can’t just come out and predict that in 5-10 years, Watson’s descendants will begin to displace physicians.

    It will happen, and it will improve health care while lowering costs. Automation is inevitable, and doctors, like everyone else, will have to learn to accept it.

    • Kristof Homer June 7, 2011 on 10:06 am

      I fully agree with you Homer, this tech cannot be developed fast enough and once it proves its worth in real life scenarios Drs will be, and should be, looking over their shoulders. Before I’m berated for that comment please know that for better or worse it just way it’s going to be.

      In time, automating intellectual jobs… physicians, attorneys, politicians, scientists (any job that requires determining probabilities based off of databases) may prove easier than automating complex manual tasks. Construction and mechanic type occupations maybe the last jobs to be eliminated.

    • Rob Riedel Homer June 7, 2011 on 10:14 am

      You can’t just compare the role of a doctor to a cab driver. A cab is easy to drive, there’s go, stop, turn left, turn right, not that complicated, whereas a doctor does much far more than just diagnose disease. Of course doctors will come to rely on a system like watson, but all it does is help free up the doctor to do more important things that they’re are better at than a computer. Sure, i can see in the far future computers replacing people physicians, but by the time that is possible there will pretty be no job in which a human can do a better job than a machine.

      • Homer Rob Riedel June 7, 2011 on 1:12 pm

        “Of course doctors will come to rely on a system like watson, but all it does is help free up the doctor to do more important things that they’re are better at than a computer.”

        Rob, you’re making my point for me. In any industry, when machines come in and “free up” a human to do something else, then less of that human’s time is required. A company that once employed 100 folks to achieve a certain level of production now may only require 20, plus machines. As a result, their production (and therefore product) costs will decrease.

        A physician’s tasks currently include some medical-grunge work and some medical-elite work. If Watson comes in and picks up the grunge work, the doc can then devote himself solely to the elite tasks. If his productivity thereby increases by 40%, then (as administrators like to think) he could see 40% more patients weekly. And therefore the number of doctors required for a fixed number of patients will decrease.

        It happens in every industry, and medicine is no exception.

    • Dr. Ed Homer June 7, 2011 on 8:04 pm

      Personally, I am not alarmed. MDs are losing patients to chiropractors and holistic practitioners because patients want more human contact (“laying on of the hands”). There is skill in diagnosis and treatment, and there is skill in caring for people. A computer will eventually diagnose and manage treatment better than I can, but it will never **care** for people as well as I can…

      • Homer Dr. Ed June 9, 2011 on 9:26 am

        Dr. Ed, thanks for your perspectives from the MD side of things. It’s interesting that you mention “caring” for patients, because that’s traditionally been the realm of nursing.

        Once a computer can diagnose and prescribe treatment better than a flesh-and-blood doctor, what will remain for a human to do is deliver that treatment (in a caring way, as you stated). Will that person even be called a doctor, and require years of medical school and training? Or will he be more like a nurse of today?

  • krunkster June 7, 2011 on 7:09 am

    I think Microsoft would probably sue them if they started referring to it as “Dr. Watson”.

  • jasonmaude June 7, 2011 on 9:21 am

    I don’t know on what basis that IBM claims that Watson is faster than Isabel (www.isabelhealthcare.com) and doesn’t understand that “difficulty swallowing” is the same as “dysphagia”. Previous articles have reported that Watson took 3 seconds to answer a Jeopardy question. Isabel provides a response in around 2.5 seconds over household broadband. Isabel has understood for many years that “difficulty swallowing” is not only the same as “dysphagia” but also several other phrases.

    • Dr. Ed jasonmaude June 7, 2011 on 7:59 pm

      I am not familiar with Isabel, but there have been several decent differential diagnosis (DDx) programs developed over the years. For example, Caduceus (http://en.wikipedia.org/wiki/CADUCEUS_%28expert_system%29) and DXplain (http://en.wikipedia.org/wiki/Dxplain). Caduceus can look at the DDx list and suggest the lowest cost (both in $$$ and patient discomfort/risk) test to distinguish between the possible choices, while DXplain can tell you how it arrived at its choice(s), thereby being a teaching tool at the same time.

      The biggest challenge is “knowing when you don’t know”. When I am faced with a set of symptoms or findings that stumps me, I get a second opinion from a specialist; for a computer program, it has to realize that there are possibilities for which it has not been programmed and thus has no knowledge of. If it just uses the “best fit”, it will assess and recommend incorrectly…

    • Peter Murray jasonmaude June 11, 2011 on 4:34 am

      I was taking their word for it. But upon further digging, IBM offers more details on their website. They talk about Watson’s ability to use context to extract meaningful information from ambiguous input. They also mention Isabel, saying it’s “often too slow,” and reference a 2008 simulated study.
      http://www.ibm.com/developerworks/industry/library/ind-watson/
      Head-to-head comparisons will inevitably happen (and would be fun to watch!) when programs like Watson and Isabel become more widely used.

  • Dr. Ed June 7, 2011 on 7:50 pm
    • Peter Murray Dr. Ed June 11, 2011 on 4:01 am

      It wasn’t the actual demonstration, just the AP link. But I found another that worked. Thanks!

  • Alan Eisen June 7, 2011 on 8:04 pm

    I think you have the wrong Tom Watson. Tom Watson Sr. died in 1956.

    • Peter Murray Alan Eisen June 11, 2011 on 3:59 am

      Good catch. I’ve updated with the much more menacing looking senior. Thanks!

  • Matthew C. Tedder June 8, 2011 on 5:32 am

    What IBM applies Watson to law, they will be almost undefeatable in court. The ethics of only one-side having this technology is very not good. On the other hand, it\’d be nice if IBM began use by establishing a lot of useful legal precedent. I\’d love to use a technology like this for good, such as to read various legal materials plus lexus-nexus and then wipe out a lot of bad patents, establish better government transparency, privacy, democracy, etc. Think of all the legal precedent that becomes possible.

  • Eric June 9, 2011 on 3:02 am

    So – will Dr. Cuddy have a cow if Dr. Watson consults with Dr. House?

  • ascenda July 7, 2011 on 12:35 pm

    Hi Peter,

    Thanks for writing this article. You mention that there is a team of medical students working to catch mistakes that Watson makes. I myself am a second year medical student and would like to know where you got information on this team and perhaps how I can get in touch with the group – I’d love to contribute to refining Watson.

    Thank you,
    Hassan