FEB 23, 2017 12:00 PM PST

Rapid Learning for Precision Oncology

3 1 245

  • Founder and Chairman at Cancer Commons
      Dr. Jay M. ("Marty") Tenenbaum, a world-renowned Internet commerce pioneer and visionary, founded CommerceNet (1994) to accelerate business use of the Internet. While at CommerceNet, he co-founded Veo Systems (1997), the company that pioneered the use of XML for automating business-to-business transactions. When Commerce One acquired Veo Systems in January 1999, Dr. Tenenbaum became chief scientist and was instrumental in shaping the company's business and technology strategies for the Global Trading Web.

      Post Commerce One, Dr. Tenenbaum was an officer and director of Webify Solutions (sold to IBM in 2006) and Medstory (sold to Microsoft in 2007). Currently, his focus is on transforming healthcare and accelerating therapy development through collaborative e-science. Towards that end, he founded CollabRx, which builds "virtual biotechs" to help slash the time, cost, and risk of developing new therapies."

      Prior to CommerceNet, he was founder and CEO of Enterprise Integration Technologies, the first company to conduct a commercial Internet transaction (1992), secure Web transaction (1993), and Internet auction (1993). Earlier in his career, Dr. Tenenbaum was also a prominent AI researcher, and led AI research groups at SRI International and Schlumberger Ltd.

      Dr. Tenenbaum is a fellow and former board member of the American Association for Artificial Intelligence, and a former consulting professor of Computer Science at Stanford. He currently serves as a director of Efficient Finance, Patients Like Me, and the Public Library of Science, and is a consulting professor of Information Technology at Carnegie Mellon's new West coast campus.

      Dr. Tenenbaum holds B.S. and M.S. degrees in Electrical Engineering from MIT, and a Ph.D. from Stanford.


    In this era of precision molecular medicine, knowledge changes rapidly and is highly dispersed.  Physicians and patients are faced with conflicting expert opinions and a shortage of actionable data, buried within a tsunami of literature.  Patient outcomes and quality of life vary widely across physicians and institutions, often falling off dramatically from elite institutions to rural and disadvantaged communities, as well as in developing countries.

    Not only do individual physicians not know the optimal way to treat any complex case; they don’t even how to find this out.  Advanced cancers are characterized by thousands of molecular aberrations, potentially creating tens of thousands of clinically distinct subtypes. Moreover, there are hundreds of approved therapies, which have never been tested head to head, or in combinations. Current clinical trial designs, including contemporary “adaptive” Bayesian designs, cannot efficiently search this huge combinatorial space, especially given the limited number of cancer patients.

    In the absence of definitive clinical studies, the best way to help current patients achieve better outcomes is by aggregating and validating the insights, intuitions, and experiences of our best clinicians.  Every day, thousands of patients who have exhausted the standard of care are treated with off-label drugs and cocktails. These treatment decisions are based largely on the judgments and experience of individual physicians, but the results are seldom reported, so nothing is learned. Cancer Commons is building a platform that will coordinate these thousands of ad hoc “N of 1” experiments, capture their results, and rapidly share them.  Our goal is to transform the everyday practice of oncology into a global adaptive search for better treatments and cures.  Given the wide variation in treatment and outcomes, we are convinced that getting the right knowledge to the right patient and the right physician at the right time will save many lives.


    Learning Objective 1: How to capture, validate and share the knowledge generated from the thousands of N-of-1 experiments that take place daily in oncology practices, far faster than journals and conferences.

    Learning Objectives 2: How to coordinate these experiments across all patients and treatments to search for optimal combination therapies and regimens far more efficiently than clinical trials.  

    Show Resources
    Loading Comments...