IBM Watson supercomputer turns to medicine
(CBS/AP) After battling the flesh-and-blood know-it-alls on "Jeopardy!," IBM supercomputer Watson is getting ready for its next big challenge - helping doctors navigate the increasingly complex world of medicine.
Watson is being groomed to be a bedside medical tool - digesting medical textbooks, journals, treatment guidelines as well as information from patients' blogs to diagnose illnesses quickly and accurately.
IBM says Watson, with its ability to understand language, can absorb questions about a patient's symptoms and medical history and quickly suggest diagnoses and treatments. They envision several uses, including a doctor speaking into a handheld device to get answers at a patient's bedside or to serve as a second opinion. Watson could also link to electronic health records that the federal government wants hospitals to maintain.
At a recent demonstration, Watson was fed information about a fictional patient with an eye problem. As more clues were unveiled - blurred vision, family history of arthritis, Connecticut residence - Watson's diagnoses evolved from uveitis to Behcet's disease to being 73 percent sure the cause was Lyme disease. Watson suggested the antibiotic doxycycline for treating Lyme disease, then switched to cefuroxime when told the patient was pregnant and allergic to penicillin.
"You do get eye problems in Lyme disease, but it's not common," Dr. Herbert Chase, a professor of Medicine at Columbia University, said. "You can't fool Watson."
Chase thinks patients' blogs would give Watson a more complete picture of disease states.
"What people say about their treatment ... it's not to be ignored just because it's anecdotal," Chase said. "We certainly listen when our patients talk to us, and that's anecdotal."
Robots aren't yet ready to replace doctors. But with all the medical information out there, a resource like Watson could be a boon to medical care.
"Advances in medicine are increasing rapidly - genomics, specialized drugs, off-label uses, increasingly finer-grained classifications of disease," Dr. Carl Kesselman, director of the Health Informatics Center at the University of Southern California, said. "The ability to ask 'Jeopardy!'-style questions and get that kind of information retrieval, to sort through all the stuff out there and point you to the latest literature, would be of potentially huge value."
On "Jeopardy!," Watson gave one answer to each question and rated its confidence in the answer. For medical use, Watson offers several possible diagnoses, ranked in order of its confidence.
"In medicine, we don't want one answer, we want a list of options," Chase said. He also thinks seeing more than one choice might also help doctors move away from what he called "anchoring," or getting too attached to a diagnosis.
"If a person has a 95 percent chance of having disease X, there's still a one-in-20 chance that they have something else," he said. "We often forget what's in that 5 percent. But Watson won't."
As on "Jeopardy!" - where Watson infamously identified Toronto as a U.S. city and Picasso as an art period - the computer occasionally botches a medical question.
"I think once we were asking what type of drug we should use and the answer was a person's name," Chase said. And of course there are things Watson cannot do. It won't know a patient's appetite for risk, for example, or feelings about end-of-life treatment.
"That's why you have to emphasize that the decisions aren't coming from the computer, they're coming from the patient," Chase said.
