Print“We will have an impact on disease,” IBM’s Kelly says. “It is not a matter of if, it is a matter of when—and I think it will be soon.”
Despite advances in the speed and lower cost of genomic sequencing, analyzing and making use of the information is an expensive and painstakingly time-consuming process. It can take a team of scientists working non-stop for two to three weeks to come up with information that may be useful in directing the course of treatment. It’s too slow for patients with glioblastoma, an aggressive and deadly brain cancer that kills more than 13,000 people in the United States each year, often within a year after the initial diagnosis.
That could soon change. The New York Genome Center and its consortia of research hospitals throughout New York have partnered with IBM to enlist the help of IBM’s Watson cognitive system to speed the translation of genomic data so that oncologists can deliver timely personalized care to cancer patients. IBM unveiled Watson to the world two years ago when it pitted the system against humans on game show Jeopardy, after it had fed it the entire Wikipedia. Watson beat the humans. Watson also beat chess masters at chess, a game of strategy.
It is a cognitive system, says John Kelly, senior vice president and director of IBM Research, built on technology that can continually ‘learn’ as it encounters new patient scenarios, and as more information becomes available through new medical research, journal articles and clinical studies. Given the depth and speed of Watson’s ability to review massive databases, the goal of the collaboration is to increase the number of patients who have access to care options tailored to their disease’s DNA.
“We believe we can collapse the time it takes clinicians from weeks and months to seconds,” Kelly says. “It can suggest outcomes quickly.”
That is what Robert Darnell, president and CEO of the NY Genome Center hopes it will do. Using a Watson prototype designed specifically for genomic research, NY Genome Center and its medical partner institutions will initially evaluate Watson’s ability to help oncologists develop more personalized care to patients with glioblastoma, an aggressive and malignant brain cancer that kills more than 13,000 people in the U.S. each year.
In a first-of-its-kind clinical study designed by Darnell, the consortia of research hospitals will sequence the genomes, tumors, and RNA of an initial 20 to 25 patients with brain cancer using Illumina sequencers. All glioblastomas are different, and each can have thousands of mutations, says Darnell. Doctors need time to think about the information.
That is where Watson steps in. “We propose to have Watson help us in a constructive way for the physician scientist to understand the meaning of those mutations,” says Darnell.
The data will be fed to Watson, which has already been fed more than 23 million scientific abstracts and complete papers related to oncology, plus pharmaceutical data. It can read millions of scientific papers in seconds. “Having Watson pour through the data will give physicians time to think about the mutations and what they mean,” says Darnell. Watson can also search through pharmaceutical data for both approved and experimental drugs and suggest potential treatments targeting specific mutations.
Despite groundbreaking discoveries into the genetic drivers of many cancers, few patients benefit from personalized treatment that is tailored to their individual cancer mutations. Current analysis methods can’t be scaled. Clinicians lack the tools and time required to bring DNA-based treatment options to their patients and to do so, they must correlate data from genome sequencing to reams of medical journals, new studies and clinical records — at a time when medical information is doubling every five years.
The joint NY Genome Center/Watson initiative aims to speed up this complex process, identifying patterns in genome sequencing and medical data to unlock insights that will help clinicians bring the promise of genomic medicine to their patients.
“Since the human genome was first mapped more than a decade ago, we’ve made tremendous progress in understanding the genetic drivers of disease. The real challenge before us is how to make sense of massive quantities of genetic data and translate that information into better treatments for patients,” Darnell says. “This exercise is not academic. It is an experiment to establish a working prototype.”
IBM has spent the last two years educating Watson in healthcare and biology, and moving it to be cloud-based so that it can be accessed globally. “We will have an impact on disease,” IBM’s Kelly says. “It is not a matter of if, it is a matter of when—and I think it will be soon.”
The New York Genome Center is an independent, nonprofit consortium of renowned academic, medical and industry leaders across the globe, with a mission to translate genomic research into clinical solutions for serious disease. IBM is the NY Genome Center’s founding technology member.
March 23, 2014
http://www.burrillreport.com/article-ibm%e2%80%99s_watson_to_help_clinicians_tackle_brain_cancer.html
