This AJR Expert Panel Narrative Review, published 2 September, addresses the gap between society guidance on breast cancer risk assessment, which varies, and what radiology departments actually do.
It reviews commonly used risk prediction models, compares existing guideline recommendations on their use, and proposes a practical approach: when to assess risk, which tools to use, and how to translate a calculated risk into a screening decision such as supplemental MRI. It also looks at research into deep learning models that predict risk from the mammogram itself.
For breast imaging services, the message is that risk assessment should be a routine, standardised step rather than something left to referrers, because the benefit–harm balance of screening improves when intensity matches risk.
- Build a formal risk assessment step into the breast screening pathway.
- Use a validated risk model and record the result in the report.
- Offer supplemental MRI to women whose calculated lifetime risk meets guideline thresholds.
- Treat image-based AI risk models as investigational for now.
Why it matters
Moves risk-based screening from a referrer's afterthought into the radiology workflow.
Don't overread it
This is an expert narrative review, not new outcome data; model choice still varies between societies.
Read the rest in the app
You have read your two free briefings this month. The app carries all 27 specialties, every morning, free — and this finding is waiting in it.

Scan to keep reading on your phone. No account needed to start.
Tomorrow morning, before your first patient
One edition a day for radiology, written by the desk, every claim tied to its paper. Six minutes.
Get the app — free