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
AI-Based Slab Reconstruction Streamlines Digital Breast Tomosynthesis
AI-driven slab reconstruction in DBT improves workflow efficiency without compromising diagnostic accuracy in breast cancer screening.
•AuntMinnie
AI Model Predicts Dosimetry for Lu-177 PSMA Therapy Using PET/CT
A machine learning PET/CT model shows promise for predicting radiation dose prior to Lu-177 PSMA therapy in prostate cancer patients.
•AuntMinnie
AI Model Uses Ultrasound to Assess Fetal Lung Maturity
Researchers demonstrated an AI model's strong accuracy in measuring fetal lung maturity from ultrasound images.