FDA to probe public risks of AI’s ever-growing role in radiology

The federal agency responsible for clearing new artificial intelligence (AI) algorithms wants to better understand the risks and rewards of this technology’s burgeoning use in imaging.

As such, the Food and Drug Administration (FDA) is planning a two-day public workshop in February to explore AI’s explosion across the specialty. Federal officials want to get ahead of any possible dangers as machine-learning technologies evolve ever-closer to complete autonomy.

“The potential for independent action by these devices to bypass human clinical review is an important factor in their benefit-risk profile, and it heightens expectations for the safety and effectiveness of these devices,” the FDA wrote in its meeting announcement. “Through this workshop, FDA is seeking to engage with stakeholders to explore benefits and risks of these evolving applications of AI in radiology,” the agency added later.

The FDA’s gathering will kick off the morning of Tuesday, Feb. 25, and run through Wednesday, Feb. 26, at the Natcher Conference Center in Bethesda, Maryland. Admission is free, but attendees must register beforehand to reserve a seat. Those who cannot make it to the National Institutes of Health’s main campus can watch the event via webcast. The agenda also includes a public comment period, and the FDA is accepting written testimony through March 26.

Topics on the agenda include radiological AI device regulation, emerging trends in software, and machine-guided image acquisition. With AI technologies’ role continuing to evolve in radiology, FDA officials want to know whether their own vetting processes need a makeover, too.

“As the benefit-risk profile changes, it is critical to adapt the methods used to evaluate and characterize their performance,” the FDA wrote.