Supercomputer and former Jeopardy! contestant Watson is the focus of a new Cleveland Clinic-IBM partnership that will teach Watson about medicine and help it become a clinical decision support tool for future doctors.
IBM announced today that a team of researchers will work with physicians, faculty and medical students at the Cleveland Clinic Lerner College of Medicine of Case Western Reserve University to enhance the Watson technology with medical knowledge. At the same time, it will also help medical students learn to think critically and rationally about medical diagnoses and treatments.
The idea is that Watson can be fed with medical information and research — more than even the best doctor could keep in his head — and can use that information to connect the dots within a medical case. For example, it could read symptoms, medical history and lab results from a patient’s EMR and use its knowledge and algorithms to find a likely diagnosis or treatment for that patient.
But the project hopes to move Watson beyond the Jeopardy! version of itself that just provided answers to questions. With this program, called WatsonPaths, the reasoning behind Watson’s answer is presented in the form of inference graphs that visually map out the evidence the computer used to come to its answer.
“Ultimately, we look at Watson as a tool that helps a decision-maker,” said David Ferrucci, the principal investigator of the Watson project, who demoed and discussed the program with CCLCM faculty at the Medical Innovation Summit today.
In return, students and clinicians provide feedback to Watson, who learns and uses that feedback in later analyses. As the first milestone of this project, Watson will take the U.S. Medical Licensing Exam, Ferrucci said.
It’s all being done with the goal of helping physicians — both current and future — move away from memorization and instead use critical, evidence-based thinking to come to decisions.
A Deep-dive Into Specialty Pharma
A specialty drug is a class of prescription medications used to treat complex, chronic or rare medical conditions. Although this classification was originally intended to define the treatment of rare, also termed “orphan” diseases, affecting fewer than 200,000 people in the US, more recently, specialty drugs have emerged as the cornerstone of treatment for chronic and complex diseases such as cancer, autoimmune conditions, diabetes, hepatitis C, and HIV/AIDS.
“You get the computer to do what it does best, and get the human to do what it does best, and see if the collaboration can create the best outcomes,” Ferrucci said.
It’s a cool concept, but no one’s expecting Watson to replace doctors, even years from now. “The human element of medicine will never disappear,” said Jim Young, executive dean of the Education Institute at the Clinic. “(Watson) lets the professional link the knowledge base to what some people call the art of medicine.”
But down the line, Watson could have more applications beyond the classroom and in the clinic.
“I think about Watson almost as a facilitator between the physician and the patient,” Ferrucci said. “When you see these options laid out before you, it makes things more transparent and it helps build more confidence that you’re not being left out of the process.”
Or, in a nutshell, it could help enable what patients and physicians really want — a personalized care plan, said James Stoller, chair of the Education Institute. “That’s beyond the first level, but at its best, this thing would help form fabulous seasoned clinical decisions.”
