Topol and Rajpurkar propose three models for dividing diagnostic tasks between AI and radiologists to improve workflow outcomes.
Key Details
- 1Eric J. Topol, MD, and Pranav Rajpurkar, PhD, outlined their ideas in a commentary in RSNA's Radiology.
- 2They challenge the traditional 'assistive approach,' citing evidence that integrated workflows don't always enhance results.
- 3Three division-of-labor models are described: AI-first, physician-first, and case allocation based on complexity.
- 4Role separation is promoted to leverage the unique strengths of both AI and radiologists and reduce automation errors.
- 5The authors note that hybrid and adaptive approaches will likely emerge in clinical practice, based on context.
Why It Matters
These recommendations highlight the evolving strategies for effectively integrating AI into radiology practice. Clarifying roles can help maximize clinical benefits and reduce risks such as automation bias or neglect.
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.