IBM's Watson to help Mayo Clinic tackle clinical trials

By Jonah Comstock
10:10 am
watson Watson at Memorial Sloan-Kettering

IBM's Watson, a cognitive computing system that has already been deployed in a number of healthcare use cases, is teaming up with Mayo Clinic to bring its computing power to bear on the  age-old problem of matching active clinical trials with eligible participants.

"Using natural language processing and powerful data analytics capabilities, Watson will help Mayo clinicians quickly sift through millions of pages of clinical trial and patient data and complete this cumbersome process in seconds," Sean Hogan, general manager and vice president of healthcare at IBM, wrote in a blog post. "The new Watson solution will help ensure that all eligible patients are considered for clinical trials and could help accelerate medical research."

According to IBM, there are 8,000 clinical being carried out at any given time by the Mayo Clinic, and 170,000 worldwide. Currently, matching eligible patients with trials is a matter of luck and guesswork -- the patient's doctor or someone the patient knows has to hear about the trial and get in touch with investigators, and investigators have to cast as wide a publicity net as they can manage to get the word out about their trials. As a result, some trials are never completed or are insufficiently rigorous because of a lack of enrollment. And many patients who would benefit from an experimental treatment don't have access to it. It's been repeatedly identified as one of the highest impact opportunities for mobile health.

IBM and Mayo Clinic will develop a proof-of-concept system, with the hope of implementing it in clinical use in 2015. Watson will use data from patients' records and will scour the Mayo Clinic clinical trial database as well as public databases like It will return matches that clinicians can present to their patients. Mayo Clinic and IBM hope that this will increase the percentage of patients engaged in a trial at Mayo from its current rate of 5 percent to 10 percent (the national average is 3 percent).

"With shorter times from initiation to completion of trials, our research teams will have the capacity for deeper, more complete investigations," Dr. Nicholas LaRusso, a Mayo Clinic gastroenterologist and the project lead for the Mayo-IBM Watson collaboration, said in a statement. "Coupled with increased accuracy, we will be able to develop, refine and improve new and better techniques in medicine at a higher level."

Watson is a computer program that can parse and combine large data sets in an efficient, intelligent way. That capacity brought Watson to victory against human opponents on Jeopardy! three years ago, and since then it has seen numerous applications in the medical field. At Memorial Sloan-Kettering Hospital, Watson combed through the latest medical journals and help doctors sift through the large, ever-changing set of treatment options for cancer patients, including clinical trials. And in its partnership with Welltok, IBM demonstrated that Watson could bring its data-based insights to the individual level, making personalized recommendations to a user based on their particular health needs.

This is IBM's first Watson-related project with the Mayo Clinic, but they are looking at additional applications for the technology in the future. Mayo Clinic is also notably working with Apple on a clinical application for Apple's HealthKit technology.


The latest news in digital health delivered daily to your inbox.

Thank you for subscribing!
Error! Something went wrong!