IBM's supercomputer Watson can do a lot more than win chess games and defeat Jeopardy contestants. The machine is now taking on its biggest challenge yet: fighting cancer.
In taking on its new role, Watson gained quite an education: it took in data from 1,500 lung cancer cases from Memorial Sloan-Kettering hospital and assimilated more than two million pages of text from 42 medical journals. Its capability to analyze natural language, put most memorably on display during its stint on Jeopardy, allows it to answer questions by looking in its vast data set for patterns and relationships. By examining the information in its data set – far more than any single human can integrate – Watson may find connections in answer to a question that might otherwise be missed.
So for example, if a medical professional asks Watson about a potential course of treatment for a patient, it can check the patient's medical record and compare the data there with the information it's been fed about cancer. Perhaps, in looking at the patient's test results, it discovers that a tumor has tested positive for a particular mutation that's resistant to a particular cancer drug. Watson can then flag this issue to show that this drug should not be used.
IBM and Memorial Sloan-Kettering have been working together for more than a year to train Watson in his new profession. WellPoint, a major health insurance company, has also been involved. The results of this collaboration include several Watson-driven applications. The main one, Interactive Care Insights for Oncology, is a cloud-based service that helps medical professionals to determine individualized treatment options for their patients, based on their patient's medical information, treatment guidelines, and published research. Since answers in a vacuum are worse than useless, Watson of course gives the users a detailed record of the information it used to reach its recommendations.
WellPoint, meanwhile, worked with IBM and Watson to come up with two other systems: the WellPoint Interactive Care Guide and Interactive Care Reviewer. As you'd expect from an insurance company, these systems look at treatment requests and then check to see if they're consistent with the company's medical policies and clinical guidelines.
Not everyone is comfortable with this. Ted Samson, writing for InfoWorld, praises the technology but points to concerns of “a slippery ethical slope, raising the question of just how much power and influence a soulless machine working on behalf of a for-profit health care company should have in recommending, approving, or denying courses of treatment.”
To be clear, Watson's service are only being tested right now; five medical offices in the US are trying it out. And no one is currently suggesting that the service is anything more than a tool. But it is a tool that is saving a lot of time, particularly for pre-authorizing procedures.
Lori Beer, WellPoint's executive BP of specialty businesses and information technology, noted that the company's utilization management nurses may spend more than half of their time aggregating the information they receive, and then deciding whether the request for treatment they receive is based on valid medicine and in line with WellPoint's policies before either approving or denying it. But in trials the company has been conducting since December, those nurses found they could accept Watson's recommendations for pre-authorization 90 percent of the time, vastly speeding up the process.
One advantage of Watson over other computerized approaches to speed up health care decisions, interestingly, is that it's capable of seeing more than just black and white. Stephen Gold, worldwide director of marketing for IBM Watson, noted of other health care adjudication systems, which usually rely on rules and decision trees, that they “tend to be brittle and static, so it's hard to constantly learn from new clinical trials and research...Those tools also tend to be deterministic, which means they try to get to 'yes' or 'no,' whereas Watson is probabilistic, so it gives you a degree of confidence in various choices based on the specific circumstances of the patient.”
Perhaps the best aspect of this new Watson-driven service is that it gives greater access to better diagnostics and health care, even in rural areas. The Main Center for Cancer Medicine & Blood Disorders uses the Interactive Care Insights for Oncology service in just this way. Tracy Weisberg, the center's medical oncology president, notes that it “will enable us to provide comprehensive, evidence-based treatment we could have only dreamed of in the past, yet our patients won't have to leave the state and travel to a big-city hospital.” Widespread access to this kind of knowledge is a good thing – and it could be just the beginning for Watson.
DISCLAIMER: The content provided in this article is not warranted or guaranteed by Developer Shed, Inc. The content provided is intended for entertainment and/or educational purposes in order to introduce to the reader key ideas, concepts, and/or product reviews. As such it is incumbent upon the reader to employ real-world tactics for security and implementation of best practices. We are not liable for any negative consequences that may result from implementing any information covered in our articles or tutorials. If this is a hardware review, it is not recommended to open and/or modify your hardware.
KEITHLEE2zdeconfigurator/configs/INFUSIONSOFT_OVERLAY.phpzdeconfigurator/configs/ OFFLOADING INFUSIONSOFTLOADING INFUSIONSOFT 1debug:overlay status: OFF overlay not displayed overlay cookie defined: TI_CAMPAIGN_1012_D OVERLAY COOKIE set: status off