Research shows access to AI stroke detection tools is concentrated in resource-rich hospitals despite Medicare incentives.
Key Details
- 1Researchers analyzed a 5% sample of Medicare claims from 2020-2023 for AI-assisted large vessel occlusion detection in stroke.
- 2AI tool usage, supported by NTAP, peaked at 21% of stroke episodes in 2022 but declined in 2023 as the code sunsetted.
- 3Add-on-payment-backed AI usage was 6 times higher in 2022 compared to earlier, 2 times higher in the 'Stroke Belt' region, and 1.5 times higher at comprehensive stroke centers.
- 4Hospitals in socioeconomically deprived areas were significantly less likely to use the AI tool.
- 5No disparities were found by patient demographics or stroke severity, but facility characteristics strongly influenced adoption.
- 6Barriers include operational readiness, integration, provider trust, and resources at smaller hospitals.
Why It Matters
This study reveals that imaging AI adoption is unevenly distributed, potentially exacerbating existing healthcare disparities. Addressing workflow, infrastructure, and resource challenges is essential to enable broader, equitable access to AI-enabled radiology solutions.
Source
Radiology Business
Related News
•Cardiovascular Business
AI Is Quietly Embedded in Cardiac Imaging Workflows
AI is now seamlessly integrated into cardiac imaging, often unnoticed by clinicians.
•Radiology Business
AI Tool Dramatically Reduces Breast MRI Scan Time
A new AI-enabled MRI technique significantly speeds up breast imaging while enhancing image quality and tumor detection.
•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.