Three years ago, Watson, IBM’s supercomputer, challenged Brad Rutter and Ken Jennings to a game of Jeopardy... and won. One reason this marketing stunt so surprised fans and brainiacs across the land was that to succeed, Watson had understood questions posed in natural language, the spoken coin we daily trade complete with puns, synonyms, slang, homonyms, and jargon. Now, the supercomputer is applying its skills to a more worthy aim: Dr. Watson is now seeing patients. To understand better how Watson might transform healthcare research, watch the YouTube video that demonstrates how a physician might use the supercomputer to assist in the diagnosis and treatment of a new patient:
Scientific research has been expanding exponentially over the past decade, with some experts estimating that medical knowledge alone is now doubling every five years. Medical decision-making, then, is a hugely complex process as medical journals publish new discoveries and information every day. Yet, 81 percent of physicians report spending only five hours per month, or less, reading journals. Add to this the fact that hospitals have a staggering amount of clinical knowledge lying buried in the notes of its many nurses and physicians. Although computers should be able to help sort through this data, too much of it is ‘unstructured’ — available only in natural language. What makes Watson so special, then, is that it has the ability to read data sets, while remaining fully fluent in human speech. Along with the ability to develop hypotheses and analysis based on the many scientific journals it reads, Watson also has the ability to get smarter with repeated use. By learning from both its successes and failures, Watson will gradually learn become a better diagnostician.
“IBM Watson represents a new era of computing, in which data no longer needs to be a challenge, but rather, a catalyst to more efficiently deploy new advances into patient care,” Manoj Saxena, general manager of IBM Watson Solutions, stated in a press release. The University of Texas MD Anderson Cancer Center in Houston as well as Memorial Sloan Kettering Cancer Center in New York have collaborated with Watson over the past few years in an effort to harness the supercomputer's cognitive power and assist doctors in diagnosis and treatment of cancer. Most recently, Watson has worked with the Cleveland Clinic in order to learn how to cull new insights from electronic medical records (EMR).