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
Study: Computer Vision Models Best LLMs in Chest CT Breast Abnormality Detection
Computer vision models (CVMs) surpass large language models (LLMs) in accurately labeling incidental breast abnormalities on chest CT scans.
•AuntMinnie
Deep Learning Models Rival Radiologists for Pancreatic Cancer Detection on CT
Deep-learning models achieved comparable or superior accuracy to experienced radiologists in detecting pancreatic cancer on CT scans, especially for small tumors.
•Radiology Business
Radiology AI Devices at Elevated Risk for FDA Recalls, Study Finds
Radiology AI devices are more likely to face FDA recalls, largely due to deviations from intended use and incomplete clinical data.