A new mammography-based AI model predicts 10-year breast cancer risk more accurately than established clinical and AI models.
Key Details
- 1Developed by Karolinska Institute, the AI model uses digital mammogram images to assess long-term breast cancer risk.
- 2Tested in 8,696 women (KARMA and Olmsted cohorts) with 1,633 incident breast cancers.
- 3Model achieved AUC of 0.72 for invasive cancers in both KARMA and Olmsted cohorts, and 0.70 in the EMBED cohort.
- 4Outperformed the Mirai model (AUC 0.64 in Olmsted/KARMA; 0.63 in EMBED) and clinical risk models in all cohorts.
- 5In the KARMA cohort, the top 10% risk group identified by the AI model captured 33% of cancers, higher than other models.
- 6The model is being prepared for further validation in broader populations and potential integration into risk-stratified prevention programs.
Why It Matters
Improved long-term breast cancer risk prediction could enable more precise, personalized screening and prevention strategies. This model could shift mammography from a purely diagnostic tool to a critical predictor of future disease, enhancing patient care and outcomes.
Source
AuntMinnie
Related News
•Radiology Business
Study Finds Disparities in Access to Stroke Imaging AI Tools
Research shows access to AI stroke detection tools is concentrated in resource-rich hospitals despite Medicare incentives.
•Radiology Business
AI Tool Dramatically Reduces Breast MRI Scan Time
A new AI-enabled MRI technique significantly speeds up breast imaging while enhancing image quality and tumor detection.
•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.