IBM Install Supercomputer in 14 Cancer Centers in the USA.

Medscape Medical News > Oncology
14 Cancer Centers, IBM Install Supercomputer in Clinic
Nick Mulcahy
May 11, 2015

Fourteen North American cancer centers and molecular medicine organizations are collaborating with the tech giant IBM to use advanced computing to help guide the treatment of cancer patients, the company announced last week.

The institutions will use IBM's Watson supercomputer, which has been deployed on a developmental basis at a few other high-profile cancer centers in the United States.

IBM is now making some big claims about Watson, which operates using cloud computing.

The advanced computing platform will "reduce from weeks to minutes the ability to translate DNA insights, understand a person's genetic profile, and gather relevant information from medical literature to personalize treatment options," according to a press statement.

Such claims are modest compared with those made by the American Society of Clinical Oncology earlier this year, which reported that its CancerLinQ big data program will "revolutionize" cancer care.

However, the Watson initiative appears to be further along than any other in the oncology big data field.

Fourteen Participating Centers
Ann & Robert H. Lurie Children's Hospital in Chicago
BC Cancer Agency in Vancouver, British Columbia
City of Hope in Los Angeles
Cleveland Clinic in Ohio
Duke Cancer Institute in Durham, North Carolina
Fred & Pamela Buffett Cancer Center in Omaha, Nebraska
McDonnell Genome Institute at Washington University in St. Louis, Missouri
New York Genome Center in New York City
Sanford Health in Sioux Falls, South Dakota
University of Kansas Cancer Center in Kansas City
University of North Carolina Lineberger Cancer Center in Chapel Hill
University of Southern California Center for Applied Molecular Medicine in Los Angeles
University of Washington Medical Center in Seattle
Yale Cancer Center in New Haven, Connecticut



Genetic sequencing is increasingly used in oncology care, according to IBM, but the utility of the information is hampered by its complexity.

An expert at one of the newly enlisted centers echoed these ideas.

"Determining the right drug combination for an advanced cancer patient is alarmingly difficult, requiring a complex analysis of different sources of big data that integrates rapidly emerging clinical trial information with personalized gene sequencing," said Norman Sharpless, MD, director of the University of North Carolina Lineberger Comprehensive Cancer Center.

Watson's "cognitive technology" aims to "improve the decisions we make with our patients to maximize their chance for cure," Dr. Sharpless explained.

But, as reported Medscape Medical News last year, Watson and other big data initiatives have critics and skeptics.

Not everyone is sold on the idea that more data is better data, or that it is transformative, including a pre-eminent cancer researcher.

There has already been a great deal of mining of cancer data," said Robert Weinberg, PhD, from the Massachusetts Institute of Technology in Cambridge, who is credited with discovering the first human oncogene (RAS) and the first tumor-suppressor gene (Rb). However, he noted in a 2014 interview, "relative to the effort that's been put into it, there's been little in take-home lessons" for clinicians.

"The promise of big data has been greatly oversold," Robert Carlson, MD, chief executive officer at the National Comprehensive Cancer Network, told Medscape Medical News last year.

In the initial phase of the IBM program, organizations will apply Watson to the DNA data of all types of cancer patients, including those with lymphoma, melanoma, and pancreatic, ovarian, brain, lung, breast, and colorectal cancer.

The participating cancer centers will use Watson genomic analytics, which "looks for variations in the full human genome and uses Watson's cognitive capabilities to examine data sources such as treatment guidelines, research, clinical studies, journal articles, and patient information," the company explains.

Next, a list of medical literature that is relevant to the case is provided by the software, along with drugs that have been identified in the literature. Clinicians review the information and any other relevant evidence to make treatment decisions.