For the past six months, Watson has been working on a virtual residency of sorts, learning how to practice medicine through simulations carried out using an app IBM created. But sometime this fall, the robot will start seeing actual patients. Watson will essentially take data from a person's chart, crunch it through some algorithms, and come up with a couple of plans of action. For example, it might suggest two courses of chemotherapy, but it will also say that it has a 90 percent level of confidence in one and just 75 percent in the other. That's when an actual doctor would come in and make the final decision.
FastCo explains why the jump from digital prototype to human tests is such a big deal:
Watson could provide any doctor anywhere with the world's best second opinion. A physician in a community hospital in the Midwest, or at a remote medical center in China, could have instant access to everything that the medical field's best oncologists—people like Kris and his colleagues at Sloan-Kettering—have taught Watson. What is more, Watson will be able to excavate facts beyond the ken of Sloan-Kettering's current lineup of specialists. As Kris says, "We could ask Watson: What is the best treatment for this rare condition based on all of Sloan-Kettering's records?" It could then go through several years of cancer cases looking for the most successful outcomes. In time, it could even look at hospital records from around the world.
Watson was built to learn, so it will only become more intelligent the more it works around the hospital. And Wellpoint, a healthcare provider in Virginia, already uses the genius machine to manage very complex cases. However, Watson's job at Sloan-Kettering is even more impressive. It goes to show that the computer is more than just a novelty game show guest. [FastCo]