IBM’s Watson, first made famous for defeating two human champions on Jeopardy, has a new role at Cedars-Sinai’s Samuel Oschin Comprehensive Cancer Institute in Los Angeles, California.
Watson will be advising oncologists, using an enormous database of both Cedar-Sinai’s own historical data and current records as well as current medical literature to formulate recommendations.
Also involved is Nuance Communications, who’s speech and imaging recognition software will be integrated into the applications to be developed.
The imedicalapps team has previously discussed the healthcare implications of Watson and its ability to affect patient outcomes. While we have also discussed some of its limitations, Watson’s new role at Cedars-Sinai is the first tangible example of what it can potentially do.
The aim is nothing short of extraordinary – to take not only the full wealth of medical knowledge in reference texts, clinical trials, case reports, and other research but also use all local, national, and even international data sources to come up with an individualized evidence-based recommendation.
“Working with speech and imaging recognition software provider Nuance Communications, IBM said the supercomputer can assist healthcare professionals in culling through gigabytes or terabytes of patient healthcare information to determine how to best treat specific illnesses. For example, Watson’s analytics technology, used with Nuance’s voice and clinical language understanding software, could help a physician consider all related texts, reference materials, prior cases, and latest knowledge in journals and medical literature when treating an illness.”
A critical feature, then, is the quality of the data – but even the most rigorous randomized controlled trials have their detractors who point out the extensive exclusion criteria, debatable statistical designs, and other features that make room for the “art” of medicine. It will be interesting to see how the physicians and developers tackle this issue because the quality of the recommendations will ultimately hinge on the quality available to the algorithms they develop.
Steve Gold, director of worldwide marketing for IBM Watson Solutions, believes that Watson will be apt at giving recommendations to physicians to prescribe treatments that have the best outcomes.
“For example, between the first and second prescribed treatments of a cancer patient, 50% of the time the prescribed medication changes for the second treatment based on the patient’s reaction to the initial treatment. Watson may be able to better prescribe initial treatments based on past patient data and information specific to the patient being treated.”
“May” is certainly the operative word, but we are optimistic that Watson will soon provide extraordinarily valuable input and insights that are likely to improve patient care.