AI could cut medical device recalls by nearly a third, study finds

AI Summary

A study finds that applying artificial intelligence could reduce medical device recalls by nearly a third. Many devices enter markets via the FDA's 510(k) pathway based on similarity to predicate devices, which does not guarantee safety, highlighting an opportunity for AI to enhance device safety review processes.

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 are still recalled, and the FDA spends valuable time reviewing devices the same way, regardless of how risky they appear on paper.