IBM and the Cleveland Clinic have been working for the past year on a
Watson-related project with the goal of co-developing a diagnostician
supercomputer capable of supporting medical training and patient care.
That effort has resulted in two new products that IBM will spend the
next three years field testing at Cleveland Clinic. Watson is a pizza
box-sized, artificially intelligent supercomputer created by IBM that
uses natural language processing, a database of more than 200 million
pages of structured and unstructured content, and sophisticated
algorithms to solve complex problems. Watson rose to fame in 2011 when,
during a three-day appearance on Jeopardy, it beat former Jeopardy
champions Ken Jennings and Brad Rutter.
In February, IBM announced
that it had partnered with Memorial Sloan Kettering to add 600,000
pieces of medical evidence, 1.5 million patient records, two million
pages of text from medical journals, 25,000 medical training cases,
1,500 lung cancer cases, and nearly 15,000 hours of clinician-led fine
tuning of its medical decision accuracy. The effort was undertaken in
preparation for Watson’s first foray into healthcare.
Shortly after, Watson was implemented at the Maine Center for Cancer
Medicine and WestMed in New York, where researchers worked to refine its
algorithms so that it could begin supporting oncologists by creating
probability-based lung cancer treatment plans. For this project, Watson
was taught to analyze treatment options and present them to physicians
in order of their probability for curing the patients cancer, and with
the option of excluding treatments that the patient’s insurance would
not cover. During this time, researchers were also teaching Watson how
to scan through EHRs and pull out important information.
Now, IBM researchers are expanding Watson’s footstep in healthcare at the Cleveland Clinic. The Watson program at Cleveland will focus
on validating two new products: Watson EMR Assistant and WatsonPaths.
The Watson EMR Assistant project will provide researchers an opportunity
to further refine Watson’s ability to comb through electronic medical
records and mine them for valuable diagnostic information.
WatsonPaths is a project focusing on showing clinicians how Watson
came to the conclusion that it did so that clinicians can easily
understand the information in the broader context of medicine. Eric
Brown, IBM Research Director of Watson Technologies explains, "On
Jeopardy! it was not necessarily critical to know how Watson arrived at
its answer. But doctors or domain experts in any field will want to
understand what information sources Watson consulted, what logic it
applied, and what inferences it made in arriving at a recommendation."
Over the next three years Watson will gain the ability to support
diagnostic decision-making at the bedside. The goal of the program at
Cleveland Clinic is to build a digital assistant that can present
doctors with key information from within a patient’s medical record and
propose a diagnosis based on probability and science.
If successful, Watson may prove to be a valuable tool in helping
address the physician shortage because doctors would likely be able to
see more patients if relevant data was able to be automatically
extracted from the chart, analyzed, and presented in this way.
Optimizing Watson to be able to integrate with the myriad of EHR systems
installed across the nation is one major roadblock researchers have
identified in scaling Watson commercially. Another is earning the trust
of patients and physicians alike.
By : Lt. Dan
Link : http://histalkmobile.com/watson-goes-live-at-cleveland-clinic/
Aucun commentaire:
Enregistrer un commentaire