A survey of over 900 women reveals substantial variation in acceptance and expectations of AI in mammography depending on healthcare setting and demographics.
Key Details
- 1UT Southwestern surveyed 924 women across safety-net and academic medical centers between 2023–2024.
- 2Participants at academic centers were generally older, more educated, wealthier, and had higher self-reported AI knowledge.
- 3Higher education and AI knowledge correlated with greater acceptance of AI; non-Hispanic Black participants showed lower acceptance.
- 4Only 7% of women were comfortable with AI acting as the sole interpreter; 84% wanted a radiologist to review AI-detected abnormalities.
- 5Approximately 72% supported AI deployment in mammogram interpretation, but most preferred to wait for human oversight.
- 6Safety-net patients were less accepting of AI compared to academic center patients.
Why It Matters
These findings highlight the importance of tailoring AI implementation strategies and communication efforts to different patient populations in radiology. Patient education, consent, and human oversight remain critical for building trust and ensuring equitable use of AI in breast imaging.
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.