TV’s Dr. Gregory House may be brilliant, but, frankly, he could use some help from IBM’s Watson–which is looking for a new challenge now that it has beaten the top human champions at Jeopardy! “House eventually gets to the right diagnosis, but he typically saves the patient only at the last minute,” says Dr. Eliot Siegel, a radiologist and director of the Maryland Imaging Research Technologies Lab at the University of Maryland School of Medicine. “Watson would give House a much higher level of expertise. He’d lose some viewers, but he’d practice better medicine.”
All kidding aside, Siegel believes that a version of Watson designed for the healthcare industry “could revolutionize the way we practice medicine.”
And Siegel has the opportunity to help make that happen. IBM and Nuance Communications today announced a joint effort aimed combining Watson’s advanced analytics with Nuance’s speech recognition to create services for the healthcare industry. They’ll be assisted by physicians and researchers at Maryland and Columbia University Medical Center. The two companies hope to bring a solution to market in the next 18 to 24 months.
Siegel and his colleagues at the University of Maryland are working to identify the best way that a technology like Watson could interact with doctors and nurses to to provide the maximum assistance.
Here’s Siegel’s vision of how Watson could help: 1) Read electronic medical records, create summaries and call out what’s important, 2) Read all of the literature in a doctor’s specialty–something no one could do on their own, 3) Check for drug interactions, 4) Comb through clinical data and suggest possible diagnoses and potential treatments, 5) Advise a doctor in real time when they’re meeting with a patient.
But what about the “Toronto” glitch? During his three-day stint on Jeopardy!, Watson made some embarrassing errors–such as the one where it identified Toronto as a U.S. city.
Siegel’s not worried about that. A Dr. Watson would not replace a real doctor; it would just assist the physician. He sees Watson providing some of the help that he now gets from medical students and residents. They give him ideas and backstop him. “Neither we humans nor the system are infallible, but I look forward to being able to work with Watson and to have it learn a lot and get better over time,” says Siegel. “My medical students and residents leave, but Watson would stay with me. All the knowledge will be preserved, and Watson will get smarter and smarter.”