The trials of AI
Machine learning and other tools seeing increased interest for clinical studies
The U.S. Food and Drug Administration (FDA) can do a lot to spur action and interest (or concern) in certain areas. And artificial intelligence (AI) may be one of those areas, given an online posting late last year by FDA Commissioner Dr. Scott Gottlieb in which he noted, “Our longstanding goal for medical care is to ensure that the right drug or device is delivered to the right patient at the right time. This vision is increasingly possible with the innovative products that are becoming available. These new technologies offer transformative opportunities, but they also challenge [FDA] to modernize its approach to evaluating new innovations.”
And now, it seems, the FDA seeks to promote enhanced innovation in multiple areas that currently lack regulatory standards—one of those being AI. Given that this is happening concurrently with FDA efforts to improve clinical trial efficiency, one could logically assume there will be overlap between the two areas, and the FDA commissioner’s further comments hint at that.
“AI holds enormous promise for the future of medicine. We’re actively developing a new regulatory framework to promote innovation in this space and support the use of AI-based technologies,” Gottlieb noted. “We know that to support the widespread adoption of AI tools, we need patients and providers to understand the connection between decision-making in traditional healthcare settings and the use of these advanced technologies.”
Of course, it’s not just the government interested in the intersection of clinical trials and AI. For example, the company Trials.ai is leveraging artificial intelligence and machine learning technology to optimize clinical trials for speed and success.
And last year, IBM’s Watson cognitive computing system—which first gained fame by defeating all-star contestants on the game show “Jeopardy!” several years ago, and has since found its way into a variety of healthcare and life-science applications—got teamed up with the Mayo Clinic.
In this pilot collaboration, which is also a proof-of-concept study, IBM and the Mayo Clinic are applying a customized version of Watson to the task of matching patients more quickly with appropriate clinical trials, beginning with 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,” said Dr. Steven R. Alberts, chair of Medical Oncology at the Mayo Clinic Cancer Center.
One of the hopes is that use of AI for trial matching will clear up bottlenecks in recruitment and get more people involved in trials who might otherwise fall through the cracks.