Mammogram AI to predict breast cancer risk for women in screening programs
Evaluation of Commercial Mammography-Based Artificial Intelligence Algorithms for Breast Cancer Risk Prediction in U.S. Screening Populations
['FUNDING_R37'] · UNIVERSITY OF WASHINGTON · NIH-11189811
This project looks at whether artificial intelligence that reads mammograms can give more accurate breast cancer risk predictions for women who get routine screening.
Quick facts
| Phase | ['FUNDING_R37'] |
|---|---|
| Study type | Nih_funding |
| Sex | All |
| Sponsor | UNIVERSITY OF WASHINGTON (nih funded) |
| Locations | 1 site (SEATTLE, UNITED STATES) |
| Trial ID | NIH-11189811 on ClinicalTrials.gov |
What this research studies
If you get routine mammograms, researchers will use a large, diverse set of screening images and linked cancer outcomes to see how four commercial AI tools estimate future breast cancer risk. They will compare AI-based risk scores to standard clinical risk models and check how well each method works for women of different racial and ethnic groups. The work uses existing mammograms and outcome data from U.S. screening populations rather than testing new treatments, aiming to understand real-world performance before these tools are widely used. This independent comparison is meant to identify which AI tools are accurate and whether they reduce gaps in prediction for Black and Hispanic women.
Who could benefit from this research
Good fit: Ideal candidates are U.S. women who have had routine screening mammograms, including those from Black and Hispanic communities to test equity.
Not a fit: People without recent mammograms, men, or those already diagnosed with breast cancer are unlikely to directly benefit from this evaluation.
Why it matters
Potential benefit: If successful, this work could help identify more women who would benefit from extra screening or preventive measures and reduce racial disparities in risk prediction.
How similar studies have performed: Early studies suggest image-based AI can outperform traditional risk models, but few large, diverse U.S. screening datasets have been independently tested so broader success remains unproven.
Where this research is happening
SEATTLE, UNITED STATES
- UNIVERSITY OF WASHINGTON — SEATTLE, UNITED STATES (ACTIVE)
Researchers
- Principal investigator: LOWRY, KATHRYN PAIGE — UNIVERSITY OF WASHINGTON
- Study coordinator: LOWRY, KATHRYN PAIGE
About this research
- This is an active NIH-funded research project — typically early-stage science, not a clinical trial accepting patient enrollment.
- Some NIH-funded labs run parallel clinical studies or seek volunteers for related work. To check, contact the principal investigator or institution listed above.
- For full project details, budget, and progress reports, visit the official NIH RePORTER page below.
Conditions: Advanced Cancer