How Memorial Sloan-Kettering is Training Watson to Personalize Cancer Care

What happens when you let the world's foremost oncologists train the world's smartest computer?
Dr. Mark G. Kris, Chief, Thoracic Oncology Service at MSKCC
watson_article1_image.jpg

As a longtime fan of the TV quiz show, Jeopardy!, I was fascinated when I watched an IBM computer named Watson beat all-time Jeopardy! champions, two years ago.

I was particularly interested because my friend and colleague Larry Norton had previously alerted me to the fact that systems like IBM Watson could be harnessed to improve cancer care and research. Combining the abilities to process massive amounts of data and using natural language processing could not only accomplish amazing things ... like winning Jeopardy!, but also revolutionize care and research, accelerating progress for people with cancers. After a year on this project, I remain as excited today as I was on day one.

Over the past year, we at Memorial Sloan-Kettering have worked with an IBM team to train Watson to help assist medical professionals in choosing treatments for lung and breast cancers. We are sharing our knowledge and expertise in oncology to help Watson learn everything it can about cancer care and how Memorial Sloan-Kettering's experts use medical information and their experience in personalized cancer treatments.

Cancers are illnesses that continually humble doctors. A major leap forward in understanding these diseases over the last 40 years is realizing the complexity of these illnesses. You may notice that I have been using the word cancers instead of cancer. I do it deliberately, as a reflection of what we have learned. Doctors treating these illnesses know how different they are from person to person. We need better ways to help us understand the complexity and variation of these diseases to improve care and research. Textbook and guideline-based treatments are a good place to start, but they can't address the many biological and other factors affecting the course and aggressiveness of cancers.

Current guidelines aren't granular enough to determine treatments best matched to the person with the illness. The guideline recommended treatment may be chemotherapy, but how do you pick among 10 or more possible chemo options? How do you choose the dosage? What treatment frequency would work best? Oncologists learn ways to make these choices from their experience treating individual patients. That kind of wisdom is what the Memorial Sloan-Kettering team is adding to IBM Watson. Our hope is to share our experience and knowledge, and, enabled by Watson technology, help physicians around the world to understand and mine the subtleties of each person's illness. We believe this strategy can take us one step closer to the goal of personalized care for every person facing cancer treatment.

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. 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.

In collaboration with IBM and WellPoint, we have unveiled the first commercially developed Watson-based cognitive computing system that is being taught by Memorial Sloan-Kettering experts. We believe these innovations will help transform the quality and speed of care for patients and enhance research to lead to more cures.

IBM_injector_MSK cancer center.jpg
One of the big goals for Memorial Sloan Kettering and IBM Watson is to improve the quality of care delivered to persons with cancers: every person, every time, and that it will learn with every encounter, continually getting smarter.

Watson can also help to reduce the time and documentation required to get an approval to start treatment. It is an interesting aspect of the project that using a machine can actually allow doctors and nurses more time to focus on patients, rather than paperwork.

I'm sure that applying the Watson technology to oncology has the power to transform cancer care so that our healthcare providers can dedicate more time toward delivering the best possible care.

A version of this opinion piece originally appeared on IBM's Building a Smarter Planet: A Smarter Planet Blog on Feb. 8, 2013

About the author of this Post

Dr. Mark G. Kris, Chief, Thoracic Oncology Service at MSKCC
Dr. Mark G. Kris is Chief of the Thoracic Oncology Service, Division of Solid Tumor Oncology, Department of Medicine, at Memorial Sloan-Kettering Cancer Center and Attending Physician at Memorial Hospital for Cancer and Allied Diseases, New York, N.Y. Dr. Kris is a specialist in lung cancer and other tumors arising in the chest. He is particularly interested in developing strategies to choose treatments for patients based on molecular characteristics of their tumor specimens. His research also includes the use of cognitive computing (IBM’s WATSON) to assist physicians in choosing the best treatment for their patients.
Sponsor Content Presented By

Join the Discussion

The Atlantic does not moderate these reader comments, except to the same extent comments are moderated pursuant to the Terms & Conditions generally applicable to all content on The Atlantic's sites. blog comments powered by Disqus

Learn More About Watson