Sunday, February 10, 2013

IBMs Watson completes Fellowship in Oncology


You may remember the game of Jeopardy played by IBMs Watson  two years ago, defeating two championship players. For those of you living in a Bin-Laden bombed out cave, Watson is the look-alike “HAL” from  the movie, 2001 Space Odyssey.

Many physicians were intrigued about the possibilities of having some form of Artificial Intelligence to assist with diagnoses and treatments. Watson’s tremendous computing power gives it a sort of AI-like ability by storing and having the analytic ability to sort and analyze it’s databases.

"Dr". Watson's taking patients now, through a cloud-based medical application.

Thanks to a business partnership among IBM, Memorial Sloan-Kettering and WellPoint, health care providers will now be able to tap Watson’s expertise in deciding how to treat patients. Pricing was not disclosed, but hospitals and health care networks who sign up will be able to buy or rent Watson’s advice from the cloud or their own server.

Over the past two years, IBM’s researchers have shrunk Watson from the size of a master bedroom to a pizza-box-sized server that can fit in any data center. (I will purchase one when it gets to be size of an iPad mini, or Nexus 7. And they improved its processing speed by 240%. Now what was once was a fun computer-science experiment in natural language processing is becoming a real business for IBM and Wellpoint, which is the exclusive reseller of the technology for now. Initial customers include West Med Partners and the Maine Center for Cancer Medicine & Blood Disorders.

Watson was tasked with a pre-medical, medical school, and an oncology fellowship. Watson’s professors and mentors think he has graduated cum laude and is ready for practice. (no word on whether he has been approved by the FDA or any medical boards as yet, and we don’t know if a procedural code has been entered into CMS’ data fields.

Today Watson has analyzed 605,000 pieces of medical evidence, 2 million pages of text, 25,000 training cases and had the assist of 14,700 clinician hours fine-tuning its decision accuracy. Six “instances” of Watson have already been installed in the last 12 months.

There are few areas more in need of supercharged decision-support than health care. Doctors and nurses are drowning in information with new research, genetic data, treatments and procedures popping up daily. They often don’t know what to do, and are guessing as well as they can.

Samuel R. Nussbaum, M.D.

WellPoint’s chief medical officer Samuel Nussbaum said at the press event  that health care pros make accurate treatment decisions in lung cancer cases only 50% of the time (a shocker to me). Watson, since being trained in this  medical specialty, can make accurate decisions 90% of the time.

Watson doesn’t tell a doctor what to do, it provides several options with degrees of confidence for each, along with the supporting evidence it used to arrive at the optimal treatment. Doctors can enter on an iPad a new bit of information in plain text, such as “my patient has blood in her phlegm,” and Watson within half a minute will come back with an entirely different drug regimen that suits the individual.

WellPoint will be using the system internally for its nurses and clinicians who handle utilization management, the process by which health insurers determine which treatments are fair, appropriate and efficient and, in turn, what it will cover. The company will also make the intelligence available as a Web portal to other providers as its Interactive Care Reviewer. It is targeting 1,600 providers by the end of 2013 and will split the revenue with IBM.

The triumvirate of computer science, clinician and payers will be a major contribiutor to reduction in cost of healthcare.

The price was not disclosed for R&D nor it’s end user price. However I am certain it will more than pay for itself with better outcomes and perhaps fewer admissions.

Have you ever tried arguing with an ATM machine?

No comments:

Post a Comment