Sunday, September 21, 2014

The Mayo is getting its own version of Watson

Mayo Clinic
Mayo Clinic (Photo credit: Wikipedia)
Clinical trials provide patients with access to new and emerging treatments, but matching patients with trials is one of the more difficult parts of clinical research.
This is a huge task that until now has typically been carried out manually by thousands of people processing records around the world. Now the clinic is to get some help from IBM’s Watson supercomputer, wwhich will use its cognitive computing capability to sift through thousands of pages of information available about Mayo clinical trials in a fraction of the time.
"With shorter times from initiation to completion of trials, our research teams will have the capacity for deeper, more complete investigations," said Nicholas LaRusso, a gastroenterologist at the Mayo and the project lead. "Coupled with increased accuracy, we will be able to develop, refine and improve new and better techniques in medicine at a higher level."
The Mayo is getting its own version of Watson that has been especially designed for the clinic's purposes. According to the clinic, as the machine goes through its tasks it will mature and learn and become better at matching patients and trials. The researchers are hoping that in due course, Watson will be able to find patients for hard-to-fill trials such as those involving rare diseases and conditions.

As the centre points out, many clinical trials at the Mayo and elsewhere are not completed because of a lack of sufficient numbers of people to enrol in trials. Even the publicity around the involvement of Watson in the process could help, the clinic hopes. At the Mayo Clinic, just five percent of patients take part in studies and nationally, the rate is even lower, at three percent, a spokesperson for the clinic said.
Post a Comment

Interactive City Search Maps, Tools & Guides

Interactive City Search Maps, Tools & Guides Chances are, even if you’re a lifelong resident of a particular city, you don’t know ever...