A new study finds that under 30% of radiology-focused AI/ML devices authorized by the FDA had clinical testing prior to authorization.
Key Details
- 1FDA has cleared over 1,000 AI/ML devices, most for radiology.
- 2Research published in JAMA Network Open reviewed almost 1,000 algorithms approved from 1995 to June 2024.
- 3Of 723 radiology devices, fewer than 30% underwent any form of clinical testing.
- 4Very few devices were subject to prospective trials before clearance.
- 5Authors highlight a lack of standards for safety and efficacy in FDA authorization of AI/ML devices.
Why It Matters
The rapid proliferation of AI/ML devices in radiology without adequate clinical validation raises concerns about patient safety and efficacy. The findings emphasize an urgent need for more rigorous regulatory oversight and defined testing standards for imaging AI tools.
Source
Radiology Business
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.