New Cascadia Data Discovery Initiative accelerates health innovation

Original article posted on Microsoft Blog.

New Cascadia Data Discovery Initiative Accelerates Health Innovation

By John Kahan, Chief Data Analytics Officer, Microsoft

The Cascadia Innovation Corridor is home to some of the world’s leading technology, research, and medical organizations. In December of last year Microsoft and Fred Hutchinson Cancer Research Center together started a new chapter for our region when Microsoft President Brad Smith announced a $4M challenge gift focused on accelerating cancer research. Today, in collaboration with Fred Hutch, we’re proud to welcome four key players as part of the Cascadia Data Discovery Initiative (CDDI): BC Cancer, University of British Columbia, University of Washington eScience Institute and the Knight Cancer Institute at Oregon Health & Science University.

CDDI aims to establish the Cascadia region as the global leader in biomedical data science and health technology innovation, with a robust health data ecosystem that focuses on enabling collaboration, data sharing, and data-driven research.

The partnership will tackle the barriers that make breakthroughs in research difficult, starting with barriers to data discovery and data access. Descriptions of what specific types of cancer data are at BC Cancer, for instance, could be visible to researchers at Fred Hutch. If there is mutual scientific interest in sharing, the consortium could help expedite a data-sharing agreement through use of a common platform that would minimize technical and governance impediments to collaboration.

But before we can achieve this vision, we must overcome significant regulatory, social, technical and licensing barriers limiting cross-organizational access to data, resources, research, and technology. Often, these impediments make it difficult for research organizations and technology companies to partner in creating innovative solutions for patients and consumers and hinder the aggregation of data sets large enough to support machine learning, especially across an international border.

World class data scientists and medical researchers are interested in working with cutting-edge tools being developed every day by the technology sector, including Azure, Fast Healthcare Interoperability Resources, Differential Privacy, and Azure Confidential Computing.  By bringing together those producing the data and those building novel tools and governance processes to help manage, integrate and analyze diverse datasets, we have the potential to make impactful, life-changing — and potentially lifesaving — discoveries using the massive amount of scientific, educational, and clinical trial data being generated every day.

CDDI hopes to bridge this gap by building a framework for cross-institutional data governance and creating an ecosystem of shared workspaces, analytical tools, and methods among the five key organizations. We’ve identified several pilot projects which can demonstrate the value of data/metadata sharing and collaboration, and we look forward to providing more detail on early milestones at the Cascadia Innovation Corridor conference this October in Seattle.

This effort is first and foremost a collaboration, and here I wanted to share comments from my colleagues at the Fred Hutch, BC Cancer, UBC, UW and OHSU on why CDDI is important:

Matthew Trunnell, Chief Data Officer at the Fred Hutch, had this to say about the importance of CDDI:

“Fred Hutch has been at the forefront of shaping a future of data sharing and enhanced collaboration to break barriers by connecting the best minds in biomedical research and technology. With BC Cancer, UBC, UW eScience and the OHSU Knight Cancer Institute now on-board, the vision we have for the CDDI is coming together as a platform for leaders in the research, academic, business and tech fields to accelerate data-driven innovation to ultimately discover breakthrough cures and therapies.”

Dr. François Bénard, vice president of research at BC Cancer, said: “Our team at BC Cancer is looking forward to working in partnership with Microsoft, Fred Hutch, the University of British Columbia, the University of Washington eScience Institute and the Knight Cancer Institute at Oregon Health & Science University, to support health care innovation and be part of making life-saving discoveries. The creation of the Cascadia Data Discovery Initiative will transform health care and provide an avenue for us to share data and apply new technologies to support patient care.”

Raymond Ng, Director of the UBC Data Science Institute and Computer Science professor says the Institute will help CDDI build tools to automate meta data generation along with recommendation tools for data discovery. “Sharing meta data is a powerful way to jump-start collaboration, as it minimizes the risk of patient privacy breaches. Once specific data sets are identified, appropriate data sharing agreements can then be signed by partners,” says Ng. “A platform to promote data sharing is valuable not only for researchers in different organizations, but also for colleagues within the same institution. It promotes innovation within the entire ecosystem.”

Sarah Stone, executive director of the UW’s eScience Institute, said: “As a hub for data-intensive discovery on the UW campus, the eScience Institute encompasses a broad community of researchers focused on developing and utilizing modern data science tools and techniques to drive discovery and tackle pressing societal challenges We are excited to join our CDDI partners in this innovative effort to advance cancer research along the Cascadia Corridor.” 

Shannon McWeeney, associate director of computational biomedicine in the OHSU Knight Cancer Institute, said: “At the OHSU Knight Cancer Institute, we view patients as our partners in our mission to end cancer as we know it and they may permit us to responsibly use their data to achieve optimal benefit through broad data sharing. We envision a global research community in which sharing deidentified data becomes the norm. Efforts like CDDI that are working towards this vision will help maximize the knowledge gained from the efforts and sacrifices of our patients.”

At the inaugural Cascadia Corridor conference in 2016, Washington Governor Jay Inslee noted the potential of collaborative data sharing, telling the Vancouver, BC audience that “the cures for cancer reside on both sides of this border.” Today, we’re working to turn this core belief into transformative breakthroughs, realizing the power of collaborative data sharing across our region and our world.

All of us at Microsoft are thrilled to bring our tools and resources to this project, and we will continue to update you on our progress.