ACR launches one-stop shop to find FDA-cleared AI algorithms
The American College of Radiology just made it much easier for radiologists to find AI algorithms cleared by the Food and Drug Administration all in one place.
ACR’s Data Science Institute on Thursday, Nov. 21, released a new list of ongoing endorsements, compiled by querying the FDA’s database. The resource currently includes more than two dozen applications, with uses varying from triaging head CT imaging patients to analyzing wrist radiographs.
The list is fleshed out to include each model’s manufacturer, FDA product codes, body area, modality, predicate device, product testing and evaluation of the product’s performance. ACR has also linked some of the models to related case studies, according to an announcement. It plans to update the list regularly as more products gain clearance.
The development of algorithms to help simplify radiologists’ work has exploded in recent years, with numerous new machine learning tools hitting the market. Just this fall, the FDA cleared GE Healthcare's collection of AI algorithms that scan chest radiographs for signs of a suspected pneumothorax.
Marty Stempniak has covered healthcare since 2012, with his byline appearing in the American Hospital Association's member magazine, Modern Healthcare and McKnight's. Prior to that, he wrote about village government and local business for his hometown newspaper in Oak Park, Illinois. He won a Peter Lisagor and Gold EXCEL awards in 2017 for his coverage of the opioid epidemic.