IBM and Cleveland Clinic Put Watson to Work

Author(s):

Two new projects from IBM Research will put artificial intelligence to work in teaching medical students and making sense of electronic medical records.

This article published with permission from The Burrill Report.

IBM Research used the Cleveland Clinic’s Medical Innovation Summit to debut two new projects using its Watson computer system to help doctors and medical students make more informed and accurate health care decisions.

“WatsonPaths” and “Watson EMR Assistant,” both early-stage projects with a focus on decision-support, may help health care providers deal with growing pressures to practice evidence-based medicine as the amount of available evidence balloons.

WatsonPaths is the result of a year-long research collaboration between faculty, physicians and students at the Cleveland Clinic Lerner College of Medicine of Case Western Reserve University.

The project aims to illuminate the logic Watson’s software applies in suggesting diagnosis and treatment options while also making clear what inferences the system makes in arriving at a recommendation, says Eric Brown, IBM’s research director of Watson technologies.

When ready, it will put Watson’s artificial intelligence system to work mapping medical evidence to prompt clinic faculty and students to consider new factors that may help them to create additional differential diagnoses and treatment options. It will be available as part of their problem-based learning curriculum and in clinical lab simulations.

“The vision is for WatsonPaths to act as a useful guide for students to arrive at the most likely and least likely answers to real clinical problems, but in a classroom setting,” says J. Eric Jelovsek, director of the Cleveland Clinic Multidisciplinary Simulation Center.

Watson EMR Assistant aims to help doctors uncover key information from patients’ electronic medical records to improve the quality and efficiency of care they provide. IBM and Cleveland Clinic will use it to explore how to navigate and process electronic medical records to unlock hidden insights within the data, with the goal of helping physicians make more informed and accurate decisions about patient care.

IBM has already trained Watson to help doctors arrive at better individualized cancer diagnostic and treatment recommendations in partnership with Memorial Sloan-Kettering Cancer Center. It has also been trained to help speed up the claims review process with the health insurance company WellPoint. Those partnerships led IBM to launch two new products in February, Interactive Care Insights for Oncology and the WellPoint Interactive Care Guide and Interactive Care Reviewer.

The Cleveland Clinic partnership is intended to “significantly advance technologies that Watson can leverage to handle more and more complex problems in real time and partner with medical experts in a much more intuitive fashion,” says Brown.

As the rocky launch of the federal health insurance marketplace Healthcare.gov made plain, intuitive interfaces matter more than is often anticipated by the technical teams behind complex computing systems. But finding the right fit between doctors and students at leading medical institutions will be crucial for the market success of such clinical decision support systems and the abilities of their makers to find a place for them.