|Courtesy of IBM
It's difficult to match oncology patients to the most appropriate clinical trial. But IBM Watson is using cognitive computing to better match patients with clinical studies. One of the early adopters is Froedtert & MCW Cancer Network, part of a regional health network based in Milwaukee, WI, which is slated to start using Watson for Clinical Trial Matching this fall.
A clinician submits a particular patient's health information, and then Watson analyzes the patient's data against clinical trial databases. It then offers feedback to the physician on the patient's eligibility for specific clinical studies. IBM ($IBM) is working with Froedtert & MCW specifically for its cancer network, which includes four locations in southeastern Wisconsin.
The need for such an approach will continue to grow as trials increasingly factor in genetic components as personalized medicine continues to come to the fore--requiring the targeting of specific, and perhaps small, groups of patients who may have no natural affiliation, like patient groups in orphan disease.
"Clinical trials are at the heart of all medical advances to find new ways to prevent, detect and treat cancer. However, no two people and no two cancers are alike," said Dr. James Thomas, oncologist and medical director at Froedtert & MCW Cancer Clinical Trials Office and Translational Research Unit, in a statement.
"Watson will support a higher level of personalized care for our patients by enabling us to securely connect individual health information with a vast array of clinical trials. By matching clinical trials to more patients with a high degree of precision, we believe Watson will help us fulfill our mission to advance the health of our community through scientific discovery," he added.
An estimated 53,000 cancer clinical trials are ongoing in the U.S. at any given time, according to clinicaltrials.gov. At Froedtert & MCW alone, there were 220 cancer trials last year.
The current process for trial matching is conducted via clinical coordinators who sort through patient records to match them to a given study protocol. But a given protocol has, on average, 46 requirements. These criteria can include a certain genetic marker, age range, tumor stage or treatment history. That huge range of data to be matched makes this a complex and difficult task to conduct without advanced analytics capabilities.
IBM Watson's cognitive computing capability is designed to analyze large volumes of structured and unstructured data. It can answer questions posed in natural language--and, perhaps most importantly, learns over time as it gains experience from prior interactions.
"Watson for Clinical Trial Matching can help Froedtert & MCW doctors bring more patients and researchers together in an effort to speed the development of new cancer therapies and extend hope to patients," said IBM Watson Health VP of Oncology Rob Merkel.
- here is the announcement