Watson is capable of assessing health data, including medical laboratory test results
When IBM’s Watson “supercomputer” squared off against human contestants on the Jeopardy game show last February, there certainly were some pathologists and clinical laboratory managers watching this “man versus machine” battle of knowledge. But those pathologists and medical lab managers did not realize that IBM intends for Watson to play a major role in helping physicians diagnose and treat disease.
IBM is designing Watson to use analytical algorithms to support how physicians assess information as they evaluate patients. In this role, it is likely that Watson will be fed laboratory test data and evidence-based medicine algorithms as part of the data it draws upon to help physicians more accurately diagnose disease and come up with appropriate treatment plans.
Pathologists May Also Interact with IBM’s Watson
In fact, that is the end game for IBM as it expands its Analytics Solutions Center in Dallas, Texas. IBM’s goal is to find ways to use the analytical algorithms developed while creating Watson to enable physicians to retrieve medical data on their smartphones using verbal commands. If this sounds like science fiction, it is and it isn’t.
Just as officers aboard the Starship Enterprise queried their ship’s computer through voice commands, physicians could vocally address their cybernetic “assistant” and verbally request data on a patient’s condition during the office visit. Using natural-language processing, IBM’s “deep Q & A ” technology, and drawing on virtually all available medical knowledge, the “assistant” would then send medical data related to the patient’s condition to a smartphone, or other handheld device, enabling the physician to diagnose and treat the patient with a higher degree of confidence for a successful outcome. Welcome to state-of-the-art evidence-based medicine in the 21st century.
Winning Jeopardy Means Never Having to Say “I Don’t Know”
IBM’s Watson supercomputer took first place in that 3-day Jeopardy tournament. It defeated the number one and number two “human” Jeopardy contestants of all time. Watson won $1 million for charity, and equally important, it validated IBM’s drive to build a computer that could “listen” to verbal questions, analyze them, decipher their meaning, mine existing data for answers, and then answer those questions vocally or by sending the data to handheld devices.
That’s a long way from the defeat of chess Grandmaster Garry Kasparov by IBM’s Deep Blue supercomputer in 1997. Deep Blue was IBM’s first major success at pitting machine “minds” against humans. IBM created Deep Blue with only one purpose—to win at chess. It did this exceedingly well. But it was limited in its applications, and it had no verbal interface.
Watson was the next logical step: The ability for computers to understand natural human language, and to act on that understanding. Watson’s algorithms also can be re-tasked for a broad set of “common” computation needs, such as mining healthcare databases in support of evidence-based medicine.
Transforming Evidence-based Healthcare that Uses Medical Lab Test Data
In a split second, Watson can digest all of the healthcare industry’s knowledge, organize it into categories and sub-categories, and then draw on that database to answer queries from physicians with accurate analytical results.
Significantly, Watson is designed to learn as it goes, improving its analytical performance over time. It learns from doing, just like humans. Such a capability in computers has only existed in science fiction—until now.
“We can transform the way that healthcare professionals accomplish everyday tasks by enabling them to work smarter and more efficiently,” said John E. Kelly III, Senior Vice President, Research and Intellectual Property at IBM.
A recent IBM survey revealed that four out of five CIOs believe business intelligence and analytics are crucial to their business. In addition, 87% of hospital CIOs currently use analytics, versus 69 percent in other industries.
Primary care physicians aren’t the only doctors who can benefit from “collaborating” with a Watson-like information system. Virtually all specialists, from radiologists to cardiologists to pathologists have mountains of data that must be analyzed, processed and stored, not only on individual patients, but on the state of their medical practices as well. A Watson-type clinical information system that’s accessible at the point of care and mobile—going where the doctor goes—puts the world’s medical knowledge at the physician’s disposal whenever and wherever it’s needed.
“It would take almost two decades to embed all this medical data into clinical practice,” said Michael Sherman, M.D., Chief Medical Officer at Harvard Pilgrim Healthcare in a Fox Business News article.
Watson can be used to measure physicians’ performance, as well, and speed outcomes reporting for enhanced transparency. It also can be used to monitor patients remotely, extending the doctor’s care into the patient’s home. The possibilities are endless.
Finally, those pathologists and clinical laboratory managers who attended the 2005 Executive War College on Lab and Pathology Management were among the first to hear IBM’s vision for how “supercomputing” could be used to support physicians in real time. A keynote address was delivered by Kareem Saad, the Worldwide Genomics Leader at the IBM Healthcare Division in Armonk, New York.
Saad’s session was titled; “Genetic Medicine’s Information Overload and How Information Technology Must Support Physicians’ Diagnoses.” He talked about how IBM saw an opportunity to build a smart software capability that could draw in all the relevant patient health data—including medical laboratory test results—and tap a knowledge base containing evidence-based medicine algorithms. This software, now apparently dubbed “Watson,” would then provide the physician with a focused list of his or her best options for a specific patient.