AI-enabled medical devices with limited pre-market validation are more likely to be recalled after FDA clearance.
Key Details
- 1AI-enabled device recalls are more common among those lacking prospective human validation prior to FDA 510(k) clearance.
- 2Most AI medical devices are cleared without requiring prospective clinical testing.
- 3Study reviewed all U.S. recalls of AI-enabled devices between Nov. 15–30, 2024.
- 4Validation method (none, retrospective, or prospective) was a notable factor influencing recall likelihood.
- 5Recalls were categorized into errors such as diagnostic, measurement, and functional issues.
Why It Matters
These findings highlight the inadequacy of current FDA pathways to ensure AI device reliability and safety in clinical environments. For radiology professionals and developers, the results underscore the critical importance of robust validation before market approval.
Source
Health Imaging
Related News
•AuntMinnie
Google AI Studio's Performance in Lung Cancer Detection on CT Evaluated
Google AI Studio demonstrates moderate accuracy in identifying lung malignancy on CT, but requires further refinement before clinical use.
•Radiology Business
Google Mammography AI Matches Radiologists, Boosts Efficiency in NHS Study
Google's mammography AI proved as effective or better than radiologists in detecting breast cancer while reducing interpretation time.
•AuntMinnie
AI Model on Mammograms Predicts Women's Cardiovascular Risk
AI-driven quantification of breast arterial calcification (BAC) on mammograms predicts risk of major cardiovascular events in women, independent of traditional risk scores.