AI could cut medical device recalls by nearly a third, study finds
Most medical devices do not enter the market through rigorous safety testing but by being deemed similar enough to something already approved—the "predicate" device—through a mechanism known as the FDA's 510(k) pathway. But similar is not a synonym for safe. While the assumption may be that substantial equivalence is a reasonable stand-in for a safety review, some devices cleared with this method…
An Indiana University-led study reveals that AI-powered triage could significantly improve the Food and Drug Administration's (FDA) medical device clearance process. Currently, the FDA spends substantial resources reviewing devices deemed substantially equivalent to existing approved devices, despite the fact that a portion of these devices may still be recalled.
The proposed human-plus-algorithm approach could help the FDA focus its limited review resources on devices with higher safety risks, potentially reducing the recall rate by 32.9% and saving up to $1.7 billion annually in healthcare costs. By leveraging machine learning to flag devices with lower safety risks for algorithmic clearance, and reserving ambiguous or high-risk cases for human experts, the FDA could streamline its review process and allocate its resources more efficiently.
The study also aligns with the FDA's recent draft guidance emphasizing safety track records over mere availability when evaluating predicate devices.
Written by urgent.news from Medical Xpress's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.
