
We all know IBM’s Watson is smart enough to win Jeopardy and beat the world’s best chess players. But will oncologists trust its cognitive abilities enough to rely on it as an advisor? It’s likely they will if the supercomputer proves it can produce in seconds actionable information about an individual’s cancer that would take a dozen doctors weeks or months to discover.
Scientists at the New York Genome Center announced Wednesday that they would collaborate with IBM to test “a unique Watson prototype designed specifically for genomic research” that has been under development for the past decade in IBM’s Computational Biology Center at IBM Research.
The partners will test the cloud-based thinking, speaking machine for its ability to recommend treatments for cancer patients. As it encounters new patient scenarios and takes in new information from research, journal articles, and the outcomes of clinical studies, Watson will continually learn and enlighten oncologists about the drugs available that could target the genetic mutations in their patients’ tumors.
NYGC President Bob Darnell, who calls the Watson project the “most ambitious” his center has taken on since opening its downtown Manhattan headquarters in September 2013, explained in a post on IBM’s Building a Smarter Planet blog:
“There has been a mismatch between the amount of data generated and powerful analytical tools capable of making sense of that vast amount of genetic information—the Big Data of human biology.
So, now comes a new wave of innovation. The New York Genome Center and IBM are working together to harness the power of IBM Watson to help doctors find the patterns that cause diseases and discover the best treatments for individual cancer patients. In this way we are building a foundation that can lead to breakthroughs in how clinical genomics can improve patient care today.”
Darnell explains that his team will supply Watson with genomic data, electronic medical records, pharmacological information, and medical literature related to an individual patient’s cancer. The computer, in collaboration with NYGC tools and analysts, will assess the “cause-and-effect trail of the cancer,” he writes.
The joint NYGC-IBM study will initially help oncologists provide personalized assessments for patients with glioblastoma — an aggressive brain cancer that kills more than 13,000 people in the U.S. each year. Darnell said in a press conference that the trial would sequence the tumors of about 20 patients to generate an “absolute gusher” of information, including 1 trillion DNA base pairs.
“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,” NYGC announced in a press release. “This joint NYGC 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.”