What would it be like to have a doctor who’s always up on the latest research and has learned about treatments from over 1.5 million previous cases? It would look alot like Watson, IBM’s Jeopardy! playing supercomputer that’s getting ready to roll out with an all new look and a Memorial Sloan Kettering Cancer Center education in oncology.
“It will be like having a Memorial Sloan Kettering trained colleague for any doctor on earth,” claims Dr. Mark Kris, an MSKCC oncologist. “The goal here is to be part of the relationship between doctor and patient.”
Unlike IBM’s previous entrant in the battle between man and machine, the chess playing computer Deep Blue, Watson is set to go commercial and earn IBM a healthy profit. Taking the data query and natural language processing tools developed while learning Jeopardy!, Wilson is getting a top ranked medical education and aiming to be the all knowing decision support system that will transform the medical field.
“The power of the technology is that it has the ability to take the information about a specific patient and match it to a huge knowledge base and history of treatment of similar patients.” stated Dr. Kris, “This process can help medical professionals gain important insights so that they can make more informed decisions, evidence based decisions, about what treatment to follow. Watson’s ability to mine massive quantities of data means that it can also keeps up – at record speeds – with the latest medical breakthroughs reported in scientific journals and meetings.”
This is a great application for Watson. Medical knowledge is growing faster than anyone can keep up with, and no adequate technology exists to help doctors maintain awareness about new discoveries in the field. The medical field currently produces so much new research, that a doctor would have to spend 160 hours a week reading in order to stay informed. The research can mean the difference between life and death, but without proper tools doctors simply cannot keep up. Enter Watson medical assistant, IBM has retooled him to use the data query tools and natural language interpretation skills he perfected on Jeopardy! to be a new type of tool to help doctors solve this problem. Watson will in essence be an artificial brain interpreting all the data available, and giving doctors recommendations based on current research.
What does this mean for healthcare?
Watson powered healthcare could be a truly transformative technology and the biggest thing to ever come from IBM; the potential is truly staggering. This will play out in two ways, both are already being tested: patient care and financing.
At least six instances of Watson are currently deployed at partnering healthcare facilities, and doctors are using Watson to help patients suffering from lung, breast, and prostate cancer. Using its superior knowledge of research and patient records, Watson is already helping doctors determine the best course of action for each individual patient.
Watson helps in every phase of healthcare, from diagnosing to treating, and functions much like a conventional doctor. By examining the patients electronic medical record (EMR), Watson builds a profile of the patient that it cross references with research, and suggests questions that will help build a deeper understanding of the patients condition. Based on answers to questions and the EMR, Watson suggests possible tests that could help diagnose the patient. Throughout the whole process, Watson suggests treatment options and medical trials for the patient, and these suggestions have varying levels of confidence depending on available information. Low confidence likely means that more tests or questions should be used before treatment is administered.
IBM's demo shows how Watson will help doctors determine proper treatment and diognosis for their patients:
So far, Watson is performing wonderfully and drastically improving healthcare. Studies have shown that doctors are right in their cancer diagnosis about 50% of the time, Watson is right 90% of the time.
IBM is also partnering with Wellpoint to tackle the financial side of healthcare. Using the same diagnostic method used for patient care, Watson is helping the insurance company determine whether or not a particular treatment is the best option for the patient financially. The implications of this role may be even more disruptive to healthcare than the improvement to patient care.
The skyrocketing cost of healthcare in the United States is severely damaging citizens, both economically and physically. Health insurance is expensive and only going up, while quality is dipping below that of other countries. It is absolutely possible that Watson could make a difference in this growing problem.
IBM estimates that $2.3 trillion of healthcare expenses are wasted and believes Watson will drastically reduce that number. By finding the best possible treatment plan for people, both economically and physically, Watson could reduce the per patient cost for insurance companies as well as individuals. This could effectually lower healthcare costs for everyone and make it possible for hospitals to better use their resources.
If you’re interested in learning more about how this type of data mining is done, we just finished a book on this very topic that we're offering you for free! Data Science Secrets explores in greater detail the process's that enable companies to do this and other amazing things with their data. Free for for a limited time, get your copy today by signing up below: