Risk prediction
iCAD, now part of DeepHealth
Uses screening mammograms to estimate a woman’s near-term risk of developing breast cancer.
Designed for
Radiologist and breast care team
Care setting
Breast imaging center
Specialty
Breast imaging, Radiology
Our assessment
ProFound AI Risk has useful external validation showing that mammography-derived risk can be evaluated beyond its original development population. The unresolved question is clinical utility: whether its estimates are sufficiently calibrated to improve screening or prevention without inequitable overuse.
Based on public sources. RIR did not independently test this product. This is not an endorsement or recommendation.
What the evidence supports
Reviewed sources establish a real image-based breast cancer risk product with published model evidence.
What remains uncertain
Prospective outcome benefit, calibration across populations, and effects of risk-guided screening pathways remain unresolved here.
How it was studied
ProFound AI Risk has been assessed in retrospective cohorts for its ability to estimate future breast cancer risk from mammography. A published external validation tested version 1.0 in a U.S. screening cohort that included White and Black women.
Product facts
Sources reviewed
3 public sources represented in this evidence profile.
Evidence source base
Published external validation and developer science materials. Calibration and clinical action policies remain site and version dependent.
Important limitation
Discrimination alone does not establish calibration, useful thresholds, benefit from changing screening, or equitable outcomes in the adopting population.
Questions to ask