Imagine this dream scenario: you are a doctor and have a series of subtle, detailed questions about a patient’s condition to which the answers will help you correctly diagnose their illness, and/or decide the best treatment. You turn to your “assistant” Watson, in this case not Sherlock’s friend but a computer, pose the questions and within seconds, you have the answers, plucked from millions of pages of medical information.
Well that dream appears to be a step closer, because health insurer WellPoint Inc and IBM have agreed to create the first commercial applications of the computer giant Watson’s “Deep Question Answering (QA) technology”.
Under the agreement, IBM will develop the base Watson healthcare platform, and WellPoint will develop and launch solutions that run on it to “help improve patient care through the delivery of up-to-date, evidence-based health care for millions of Americans”, according to a statement released earlier today.
Watson is not named after Sherlock Holmes’ friend but after IBM founder Thomas J Watson. Designed and built by IBM scientists, the goal is for Watson to rival the human ability to answer questions posed in natural language with speed, accuracy and confidence.
Watson passed an important milestone when in February this year, it competed on the US popular daily quiz show Jeopardy! and beat the show’s two most successful and celebrated contestants: Ken Jennings and Brad Rutter. The match, which took place over three days, is currently being rebroadcast.
The quiz show provided Watson’s creators with the ultimate challenge, because the clues have subtle meanings, riddles, irony, and other complexities and nuances of languages that humans deal with easily but computers find hard to understand.
The scientist leading the team that created Watson, Dr. David Ferrucci, an IBM Fellow, told the press that:
“With the Jeopardy! challenge, we accomplished what was thought to be impossible – building a computer system that operates in the near limitless, ambiguous and highly contextual realm of human language and knowledge.”
He said watching the match again will remind us of “the great power and potential behind Watson to be able to make sense of the massive amounts of data around us and to solve problems in new ways.”
WellPoint and IBM see that Watson’s ability to analyze the meaning and context of human language and quickly sift through vast amounts of data to suggest options tailored to the patient’s condition will help nurses and doctors identify the most likely diagnosis and treatment options.
Today, medical professionals face a huge challenge in keeping pace with the hundreds of thousands of articles on the latest studies and research, and then applying that knowledge to the care of their patients.
Watson can sift through 1 million books or about 200 million pages of data, analyze it, and return precise answers in under three seconds.
The skill of course is in how to put the information into the system in the first place, and this is what the two companies will be working on. The plan is to allow physicians easily to coordinate medical data programmed into Watson with specific patient factors.
Conditions such as diabetes, cancer, chronic heart or kidney disease, are complex and arriving at their diagnosis and options for treatement involves piecing together intricate details. WellPoint and IBM intend to develop Watson to be able to look not only at massive amounts of medical literature and population health data, but also at the patient’s record, while complying with the relevant privacy and security laws, to address profound and complex questions.
For example, they see doctors being able to use Watson to consult patient histories, see recent test results, recommend treatments and highlight the latest relevant research findings so they can discuss the best and most effective treatments with their patients.
WellPoint’s Chief Medical Officer, Dr Sam Nussbaum said:
“There are breathtaking advances in medical science and clinical knowledge, however; this clinical information is not always used in the care of patients. Imagine having the ability to take in all the information around a patient’s medical care — symptoms, findings, patient interviews and diagnostic studies.”
“Then, imagine using Watson analytic capabilities to consider all of the prior cases, the state-of-the-art clinical knowledge in the medical literature and clinical best practices to help a physician advance a diagnosis and guide a course of treatment,” he added.
It is possible that the joint development will take Watson to the point where it can help doctors also take into account drug interactions and so narrow down from a large range to a select few treatment options for their patients.
The developers also anticipate that Watson will streamline communication between the doctor and the patient’s health plan, leading to more efficient clinical review of complex cases.
Manoj Saxena, general manager, Watson Solutions, IBM Software Group, said:
“With medical information doubling every five years and health care costs increasing, Watson has tremendous potential for applications that improve the efficiency of care and reduce wait times for diagnosis and treatment by enabling clinicians with access to the best clinical data the moment they need it.”
WellPoint said they hope to start pilot trials of the jointly developed Watson in early 2012.
Written by Catharine Paddock PhD