A new study finds fewer than 30% of FDA-cleared AI medical devices reported key safety or adverse event data before approval.
Key Details
- 1Study reviewed FDA data for AI/ML devices cleared between 1995 and July 2023.
- 2Out of 691 devices analyzed, 531 were radiology-specific.
- 3Fewer than 30% of devices shared safety or adverse event information prior to clearance.
- 4Authors call for more stringent testing and clearer regulatory standards.
- 5Lack of predefined efficacy and risk standards highlighted as a critical issue.
Why It Matters
Radiology relies heavily on AI devices, making their safety and efficacy crucial to patient care. The study urges tighter oversight and transparency, which could directly impact how radiologists incorporate AI into practice.
Source
Health Imaging
Related News
•AuntMinnie
Deep Learning Model Predicts Brain Tumor MRI Enhancement Without Gadolinium
German researchers developed a deep learning approach to predict MRI contrast enhancement in brain tumors without the need for gadolinium-based agents.
•Radiology Business
Study Highlights Limitations of AI in Prostate MRI Screening
New research points to several shortcomings in implementing AI for MRI-based prostate cancer screening.
•AuntMinnie
Multimodal LLMs Achieve High Accuracy Detecting Scoliosis on X-rays
Multimodal LLMs achieved up to 94% accuracy for scoliosis detection on spine x-rays, but struggled with lumbar stenosis on MRI.