by Thor Olavsrud

Mayo Clinic Turns to IBM’s Watson to Fill Clinical Trials

News Analysis
Sep 08, 20144 mins
AnalyticsBig DataBusiness Intelligence

Mayo clinicians will leverage Watson's natural language processing and data analytics capabilities to quickly sift through millions of pages of clinical trial and patient data to match patients with appropriate clinical trials.

clinical trials healthcare
Credit: Thinkstock

IBM’s Watson cognitive computer will soon be helping Mayo Clinic enroll patients in clinical trials in an effort to increase the speed of new discoveries while offering patients more and better treatment possibilities. The collaboration will begin with research studies in cancer.

Mike Rhodin, senior vice president of the IBM Waston Group, announced the plans for the collaboration today at Mayo Clinic’s Transform 2014 Symposium in Rochester, Minn.

“Ultimately, we believe Watson will help advance scientific discoveries into promising new forms of care that clinicians can use to treat all patients,” Rhodin says. “Through this effort, Mayo Clinic can consistently offer more medical options to patients and conclude clinical trials faster.”

“In an area like cancer, where time is of the essence, the speed and accuracy that Watson offers will allow us to develop an individualized treatment plan more efficiently so we can deliver exactly the care that the patient needs,” adds Steven Alberts, M.D., chair of medical oncology at Mayo Clinic.

Filling Clinical Trials Is a Data-Intensive Task

According to the Center for Information and Study on Clinical Research Participation, $95 billion is spent on medical research in the U.S. each year, but only six percent of clinical trials are completed on time. One reason for that is the data-intensive nature of clinical trial recruitment. Clinicians and researchers typically have to manually cross reference patient data with criteria for thousands of available clinical trials — there are nearly 170,000 clinical trials in progress worldwide at any given time and more than 8,000 of them in progress at the Mayo Clinic alone.

Big Blue says Mayo clinicians could instead leverage Watson’s natural language processing and data analytics capabilities to quickly sift through millions of pages of clinical trial and patient data to complete the process in seconds.

IBM and Mayo experts are training a version of Watson, geared specifically for working with the Mayo Clinic, to analyze patient records and clinical trial criteria to determine appropriate matches for patients. As the pilot gets underway, Watson will learn more about the clinical trials matching process, becoming more efficient. IBM and Mayo experts are currently feeding Watson’s corpus of knowledge with all clinical trials at the Mayo Clinic and in public databases like

IBM says Watson may also be able to help locate patients for hard-to-fill trials, like those involving rare diseases. This is a big deal, IBM says, because many clinical trials aren’t completed due to a lack of adequate enrollment — only five percent of Mayo Clinic patients currently take part in trials, despite well-organized efforts. Nationally, the rate is even more dismal at three percent. Mayo hopes Watson’s help will allow it to include up to 10 percent of its patients in clinical trials.

“With shorter times from initiation to completion of trials, our research teams will have the capacity for deeper, more complete investigations,” says Nicholas LaRusso, M.D., a Mayo Clinic gastroenterologist and the project lead for the Mayo-IBM Watson collaboration. “Coupled with increased accuracy, we will be able to develop, refine and improve new and better techniques in medicine at a higher level.”

Mayo clinicians and clinical trial coordinators will begin piloting Watson as a patient enrollment tool in early 2015. IBM notes it is also discussing other potential Watson applications with Mayo Clinic. IBM is also bringing Watson’s cognitive computing capabilities to bear in a number of other life sciences and healthcare research collaborations, including the following:

  • MD Anderson Cancer Center, which is using Watson to help oncologists create individualized treatment plans for leukemia patients
  • New York Genome Center, which is using a version of Watson designed for genomic analysis to advance personalized cancer treatment
  • Baylor College of Medicine, which is leveraging Watson to automate the process of reviewing comprehensive scientific data and formulating hypotheses
  • Johnson & Johnson, which is exploring how Watson can help advance comparative effectiveness studies to determine which drugs are most effective for subsets of the population
  • Memorial Sloan-Kettering Cancer Center which is working with IBM to co-develop a Watson-powered app that will help oncologists anywhere develop personalized treatment options for cancer patients.

Follow Thor on Google+