- IBM and the New York Genome Center announced a joint project at the White House Precision Medicine Initiative Summit.
- The joint project will build a comprehensive cancer data repository with genomic and clinical data.
- IBM's Watson AI system will learn to identify promising personalized treatments for cancer patients.
In his 2015 State of the Union address, President Obama announced a bold new research effort - the Precision Medicine Initiative - to accelerate a new era of medicine focused on delivering more tailored health care. "Doctors have always recognized that every patient is unique, and doctors have always tried to tailor their treatments as best they can to individuals," said the President. "You can match a blood transfusion to a blood type - that was an important discovery. What if matching a cancer cure to our genetic code was just as easy, just as standard? What if figuring out the right dose of medicine was as simple as taking our temperature?"
In response to the President's call, at the White House Precision Medicine Initiative Summit, IBM (NYSE:IBM) and the New York Genome Center announced a partnership to create a comprehensive and open repository of genetic data to accelerate cancer research and scale access to precision medicine using cognitive insights from IBM Watson.
Watson is IBM's Artificial Intelligence (AI) system - an open cognitive computing technology platform, where "cognitive computing" indicates computer systems that understand the world in the way that humans do. Watson continuously learns and adds to its knowledge base, gaining in value and knowledge over time.
IBM has two dedicated business units: Watson, dedicated to the development of cloud-delivered cognitive computing technologies that represent the commercialization of AI across a variety of industries, and Watson Health, dedicated to improving the ability of doctors, researchers and insurers and other related health organizations to surface new insights from data to deliver personalized healthcare. The first commercial applications of Watson, in 2013, had been for assisting health care providers in patient treatment decisions.
In 2011, Watson outperformed the best two players in the world in a Jeopardy! contest. Jeopardy! was chosen to demonstrate the capabilities of Watson because it isn't a narrow and well-defined task suitable for dumb automation, but on the contrary involves most of the subtleties and intricacies of natural language processing. To achieve the Jeopardy! victory Watson used a comprehensive knowledge base assembled by automatically reading Wikipedia and a wide range of natural language documents, and combining a huge number of individual inferences into factual knowledge.
A similar approach can permit analyzing large amounts of medical data to uncover useful insights for Precision Medicine and assist in the design of personalized therapies for a given patient. Now IBM and the New York Genome Center will build a comprehensive cancer data repository and train Watson to analyze the data and extract clinically relevant insights.
"Data is quickly becoming one of the most valuable resources in the fight against cancer," said John Kelly III, PhD, Senior Vice President, Cognitive Solutions and IBM Research. "By amassing this contributed data and applying cognitive insights to the challenge of analyzing cancer data, we believe we can soon scale access to precision medicine worldwide."
The joint project will create a national cancer data repository, including the genetic characteristics of a wide sample of patients and their response to cancer treatments. IBM and the New York Genome Center will train Watson to analyze the data and identify promising personalized drugs and treatments for new patients, and Watson's insights will be returned to each individual patient’s physician to support the physician’s treatment decisions.
"Our vision is to create a comprehensive cancer data repository that combines whole genome, exome, targeted panel and phenotypic data in an open platform that will empower researchers and clinicians," said Robert B. Darnell, Founding Director and CEO of the New York Genome Center. "We believe that iterative analysis of the data and integration with our growing knowledge of cancer will allow doctors to provide better, personalized treatment."
"Our goal is to take that massive data and turn it into information that can be used for a patient who is waiting at the bedside," added Darnell in an interview, The Washington Post reports. Darnell and Steve Harvey, vice president for IBM Watson Health, said that they eventually hope to scale up the project so that it can handle upward of 100,000 patients a year and that the repository will be accessible to researchers whose patients are participating in the project.
In related news, IBM recently announced its plans to acquire Truven Health Analytics for $2.6 billion. The acquisition of Truven, which provides health-care data services to employers, hospitals, and pharmaceutical companies, would be the last of a series of acquisitions intended to give Watson access to a deep, broad repository of health data.
Applications to Precision Medicine - a high profile endeavor supported by the White House and funding agencies in the US - will continue to establish IBM's leadership in AI and cognitive computing, but IBM is also eyeing derived commercial applications that will boost IBM stock in the mid term. The company's CEO Ginni Rometty predicted a future in which "every decision that mankind makes is going to be informed by a cognitive system like Watson."