Experts Propose New AI–Radiologist Division of Labor Models
July 30, 2025
Topol and Rajpurkar propose three models for dividing diagnostic tasks between AI and radiologists to improve workflow outcomes.
Key Details
- Eric J. Topol, MD, and Pranav Rajpurkar, PhD, outlined their ideas in a commentary in RSNA's Radiology.
- They challenge the traditional 'assistive approach,' citing evidence that integrated workflows don't always enhance results.
- Three division-of-labor models are described: AI-first, physician-first, and case allocation based on complexity.
- Role separation is promoted to leverage the unique strengths of both AI and radiologists and reduce automation errors.
- The 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.