Mayo taps Watson for clinical matching
[See also: Watson + Siri: new mHealth power couple?]
With an eye toward turning its current proof-of-concept phase into clinical reality by early next year, Mayo hopes Watson's artifical intelligence will speed appropriate treatments and lead to new research discoveries.
This iteration of Watson, specifically developed for use at the Mayo Clinic, is able to "learn" about the clinical trials process as it works through repeated matching tasks, becoming more efficient and, probably, more generalizable, IBM officials say. Eventually, Watson could even help find appropriate patients for specialized trials, such as those involving rare diseases.
[See also: Watson joins the fight against cancer]
"In an area like cancer – where time is of the essence – the speed and accuracy that Watson offers will allow us to develop an individualized treatment plan more efficiently so we can deliver exactly the care that the patient needs," says Steven Alberts, MD, chair of medical oncology at Mayo Clinic, in a press statement.
Clinical trials offer access to new and emerging treatments, but enrolling participants can be a big challenge, especially with current processes: done manually, with clinical coordinators sorting through patient records and conditions, aiming to match them with the requirements of a given study protocol. Mayo conducts more than 8,000 human studies at any given time, officials say, in addition to the 170,000 ongoing worldwide.
Watson can help more patients get matched, accurately and consistently, with promising clinical trial options. Indeed, many clinical trials at Mayo Clinic – and elsewhere – go unfinished thanks to lack of sufficient enrollment. This project could help drive those numbers up. Currently, just 5 percent of patients at Mayo take part in studies. The clinic hopes to raise clinical trial involvement to include up to 10 percent of its patients, officials say, improving the quality of research outcomes.
Citing numbers from the Center for Information and Study on Clinical Research Participation, Sean Hogan, IBM's general manager and vice president of healthcare, points out that $95 billion is spent in the U.S. on medical research each year, yet only 6 percent of clinical trials finish on time.
"Clinical trial recruitment is a data-intensive task that typically requires clinicians and researchers to manually cross reference patient data with criteria for thousands of available clinical trials," he writes. "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. The new Watson solution will help ensure that all eligible patients are considered for clinical trials and could help accelerate medical research."
"With shorter times from initiation to completion of trials, our research teams will have the capacity for deeper, more complete investigations," says Nicholas LaRusso, MD, a Mayo Clinic gastroenterologist and the project lead for the Mayo-IBM collaboration, 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."
Mayo Clinic is working with IBM to expand Watson's corpus of knowledge to include all clinical trials performed there, as well as those in public databases such as ClinicalTrials.gov. The new Watson system is being trained to analyze patient records and clinical trial criteria in order to determine appropriate matches for patients.
"Ultimately, this effort will also help advance scientific discoveries into promising new forms of care that clinicians can use to treat all patients," said Mike Rhodin, senior vice president, IBM Watson Group, in a statement.