IBM’s Watson makes drug development inroads
The strides in IBM Watson’s march into biopharma R&D are swift as Icon and Teva Pharmaceuticals are the latest companies to sign strategic partnership agreements to access the cognitive computing system, enabling them to develop new ways to find and match patients to clinical trials and develop disease models.
For IBM, the formal introduction of IBM Watson Health Cloud for Life Sciences Compliance is designed to help biomedical companies bring medical innovation to market more efficiently.
Icon is the first global CRO to apply Watson to clinical trial matching, tapping into an estimated dataset of 50 million patient records to automate the cumbersome process of identifying patients who meet the study criteria for a clinical trial, analyze protocols to assess trial feasibility and identify optimal trial sites. Initially, Icon is applying Watson to a six-month pilot study involving 25 breast, lung, colon and rectal cancer trials that will enable the CRO to advise sponsors how many patients match their trial criteria. It also will show where these patients are geographically located and how they will recruit them.
“By applying IBM Watson to our clinical trials, we have the potential to revolutionize clinical trial feasibility, patient recruitment and study startup timelines, which will help our customers take significant time and cost from their development programs,” Icon COO Steve Cutler said in a prepared statement, citing how patient recruitment costs can represent more than 30% of total study costs. “Together with IBM, we are providing a better and faster way to connect patients with clinical trials that are most relevant to them.”
While life science companies have been able to work with non-regulated workloads in the cloud, notably data research and discovery, they have been unable to use regulated workloads such as preclinical studies, clinical trial research data and market application information. Those workloads are where IBM Watson Health Cloud enables Icon—and soon others—to share and collaborate on their regulated workloads. In essence, the Watson Health Cloud process amounts to infrastructure-as-a-service solution for companies to create a compliant infrastructure to achieve regulatory compliance around required laboratory, clinical data and manufacturing practices. Watson also will analyze study protocols to determine trial feasibility and find the best trial sites.
“If machine learning can bring pattern recognition to protocol design, that would be a major achievement,” said Scott Ballenger, founder and CEO of Trial Acceleration, which provides its clinical trial clients with ways to improve study cycle times. “However, in pursing patient recruitment, matching patients and sites, there is still the potential for some kind of breakdown, especially in that vexing last mile. So it will be interesting to see how it all turns out.”
For Teva, the goal is broader: to create disease models and “advanced therapeutic solutions” using Watson, which the pharmaceutical company hopes will lead to therapeutic advances. Teva will rely on the cognitive computer system to gather and analyze real-world data to come up with solutions for reducing drug misuse and improving medicine adherence, along with other topics.
“By building on the Watson Health Cloud, we believe Teva will be in a unique position to put the best information and insights in the hands of physicians, care teams and patients to empower treatment optimization for individuals and populations across the spectrum of acute and chronic conditions,” Guy Hadari, Teva’s chief information officer, said in a prepared statement.
With Watson, Teva should be able to analyze high volumes of data and understand complex questions posed in natural language followed by evidence-based answers. The initial focus is to help the large global population of people with complex and chronic conditions such as asthma, pain and neurodegenerative diseases. The Israeli-based company expects to introduce its first e-health solution next year.
“IBM’s approach with Watson is using different approaches for what is good for patients; it’s also good for the marketplace as Watson is centered around natural language processing of unstructured data or documents and then making sense out of it all,” said Thomas Krohn, chief development officer at TrialReach and the former director of clinical development and clinical open innovation at Eli Lilly, which, he recalled, did some early exploration with Watson. “The interest in Watson will attract other groups that do A.I. (artificial intelligence) machine learning for given problems as healthcare costs rise and where you can show value and improvement by using advanced technologies.”
In addition to Icon and Teva, IBM Watson, which is based in Cambridge, Mass., also announced new partnerships with Boston Children’s Hospital as its foundational pediatrics partner where IBM plans to integrate Watson’s question-and-answer capability with a goal to bring lifesaving medical knowledge to pediatric caregivers.
Another new partnership is with Columbia University Medical Center’s Departments of Pathology & Cell Biology and Systems Biology, which will use Watson to help oncologists translate DNA insights into personalized treatment opinions for patients.
IBM’s Watson Health Cloud also is working with Sage Bionetworks’ Open Biomedical Research Platform, under a partnership with Apple, to aggregate, store, curate and analyze data collected via apps using ResearchKit. Sage currently is using ResearchKit on projects in breast cancer and Parkinson’s disease with IBM providing the underlying technology with Watson.
Email comments to Ronald at firstname.lastname@example.org. Follow @RonRCW
This article was reprinted from Volume 19, Issue 37, of CWWeekly, a leading clinical research industry newsletter providing expanded analysis on breaking news, study leads, trial results and more. Subscribe »