Clinical Evidence and FDA Recalls of Artificial Intelligence–Enabled Medical Devices

Which artificial intelligence (AI)–enabled medical device characteristics, such as availability of clinical performance studies and the nature of postmarket issues, are associated with risk of recall?This cohort study of 903 medical devices found that devices with information missing from supporting clinical studies had an increased likelihood of recall compared with devices supported by such evidence. Use-related deviations most often triggered recalls, highlighting unique safety challenges of AI systems.These findings suggest that device features and postmarket evidence jointly determine safety profiles of such devices and that establishing a unified surveillance framework could enhance safety signal detection.

Corresponding Author: Enrico G. Caiani, MSc, PhD, Department of Electronics, Information and Bioengineering, Politecnico di Milano, Piazza Leonardo Da Vinci 32, 20133 Milano, Italy (enrico.caiani@polimi.it).

Link to the article in your story

We encourage you to link out to this article in your story using the link below. It includes an access token that will give free access to the article for your readers up to one year after publication. (The link will be live after the article publishes and embargo is lifted.)

Please see the article for additional information, including full author list, author contributions and affiliations, conflict of interest and financial disclosures, and funding and support.

Need more information? Contact us.