Feature | February 22, 2013

IBM's Watson Artificial Intelligence System Goes to Medical School

Article in The Atlantic discusses the next major step in clinical decision support software

robot clinical decision support, RP 7 robot

The InTouch RP7 robot allows physicians to conduct rounds and check in on patients remotely. New development is now taking place to allow a real robot with artificial intelligence to help diagnose patients.

February 22, 2013 — Artificial intelligence may be an ingredient in the future practice of medicine, where computers will offer their medical advice to human physicians on patient cases. While it sounds like science fiction, the roots of this technology are already in use today with computer aided detection (CAD) systems to help detect lung, breast and colon cancers on images. Another form is clinical decision support (CDS) software, which determines if a patient qualifies for a particular test or procedures based on appropriate use criteria. Going a step beyond these types of second opinion software is an effort to train a computer to think like a physician and make much more complex clinical decisions.

The March 2013 issue of The Atlantic, out this week, includes the article “The Robot Will See You Now,” which looks at how IBM's Watson — the same machine that beat Ken Jennings on Jeopardy — is now churning through case histories at the Memorial Sloan-Kettering Cancer Center, learning to make diagnoses and treatment recommendations. This is one in a series of developments suggesting that technology may be about to disrupt health care in the same way it has disrupted so many other industries. The story asks the questions if doctors are necessary and just how far might the automation of medicine go?

Computers offer the ability to analyze far more data in an empirical fashion than the human mind, which might be able to overcome some of the bias and details that might be overlooked by human doctors.

Drawing on his own clinical experience and on academic studies, Marty Kohn, an emergency-room physician and a clinical leader of the IBM team training Watson for healthcare who was interviewed for the article, explained about one-third of errors made by doctors appear to be products of misdiagnosis. He said one cause of this is “anchoring bias.” Which is the human beings’ tendency to rely too heavily on a single piece of information. This happens all the time in doctors’ offices, clinics, and emergency rooms. A physician hears about two or three symptoms, seizes on a diagnosis consistent with those, and subconsciously discounts evidence that points to something else. Or a physician hits upon the right diagnosis, but fails to realize that it’s incomplete, and ends up treating just one condition when the patient is, in fact, suffering from several. Tools like Watson are less prone to those failings. As such, Kohn believes, they may eventually become as ubiquitous in doctors’ offices as the stethoscope.

“Watson fills in for some human limitations,” Kohn told The Atlantic. “Studies show that humans are good at taking a relatively limited list of possibilities and using that list, but are far less adept at using huge volumes of information. That’s where Watson shines: taking a huge list of information and winnowing it down.”

Cleveland Clinic is also helping to develop Watson, first as a tool for training young physicians and then, possibly, as a tool at the bedside itself. The insurance company WellPoint has also begun testing Watson as a support tool for nurses who make treatment-approval decisions.

To read the full Atlantic article, visit www.theatlantic.com/magazine/archive/2013/03/the-robot-will-see-you-now/309216/

Related Content

3 Recommendations to Better Understand HIPAA Compliance
Feature | Information Technology | May 17, 2019 | Carol Amick
According to the U.S.
What is Next in Healthcare IT?
News | Information Technology | February 28, 2019
The Healthcare Information and Management Systems Society (HIMSS) shared insights on what’s next in health on the heels...
Office of the National Coordinator Releases Proposed Rule on Healthcare Data Interoperability
News | Information Technology | February 14, 2019
The U.S. Department of Health and Human Services (HHS) has proposed a new rule to support seamless and secure access,...
Seamless Interoperability – Fact or Fiction? This webinar will show how Nemours Children’s Health System adoption of ScImage’s PICOM365 Enterprise PACS  improved workflow.
Sponsored Content | Webinar | Information Technology | January 17, 2019
This ScImage-sponsored ITN/DAIC webinar will be held at 2 p.m. Eastern time, Wednesday, Feb. 6, 2019.  
Digital mHealth advances like wearable heart monitors, use of smartphone apps and artificial intelligence will reshape the standard of care in the coming years according to three recent JACC articles.

Digital mHealth advances like wearable heart monitors, smartphone apps and artificial intelligence will reshape the standard of care in the coming years according to three recent JACC articles.

Feature | Information Technology | June 05, 2018
June 5, 2018 — The future of cardiovascular care will be transformed by advances in artificial intelligence, digital
Lumedx Demonstrates Advanced Analytics at HIMSS18
News | Information Technology | February 20, 2018
February 20, 2018 – LUMEDX Corporation, a top cardiovascular data intelligence company, will show off the latest in a
ACC Unveils Innovation Roadmap for Future of Healthcare Delivery, the future of cardiology.
News | Information Technology | January 09, 2018
In a new health policy statement, the American College of Cardiology (ACC) identifies how to best support healthcare...
Nuance Restores Service to Majority of eScription Clients Following Malware Incident
News | Information Technology | July 28, 2017
Nuance Communications Inc. provided an update on its restoration process following the previously reported June 27,...
News | Information Technology | May 11, 2017
McKesson Imaging & Workflow Solutions, an industry leader in providing healthcare IT and imaging solutions, is...
Overlay Init