IBM’s Watson, the supercomputer known for handily beating human contestants on Jeopardy! a few months ago, started to show off its more practical skills medical knowledge. It recently gave a demonstration to the Associated Press.
According to the AP,
Watson was gradually given information about a fictional patient with an eye problem. As more clues were unveiled — blurred vision, family history of arthritis, Connecticut residence — Watson’s suggested diagnoses evolved from uveitis to Behcet’s disease to Lyme disease. It gave the final diagnosis a 73 percent confidence rating.
The medical version of Watson was trained with medical textbooks and journals, electronic health records, and sample questions from medical students. However, unlike Jeopardy!, where Watson was required to give a single correct answer, researchers are using Watson’s computing power to receive a set of symptoms and offer several possible diagnoses, ranked in order of the computer’s confidence. Physicians are unlikely to blindly accept a diagnosis from a computer, so Watson’s purpose is to reduce physician’s mistakes by handling information overload, offering multiple options, and helping them not become too attached to a single diagnosis.
While Watson may be the most well-known medical supercomputer, it isn’t the first. 10 years ago, Isabel, from Ann-Arbor based Isabel Healthcare, was created after founder Jason Maude’s daughter, Isabel, was nearly fatally misdiagnosed. It works similar to how Watson operates, receiving a set of symptoms and searching for possible diagnoses. While Isabel is older and more fine-tuned, researchers say that Watson is faster and can better understand non-medical terminology.
Article from Associated Press: ‘Jeopardy!’ Computer Delving Into Medicine
Previously: Columbia Doctors Partner With IBM to Develop Watson’s Potential in Healthcare; IBM Watson Could Revolutionize Healthcare