An AI model accurately predicted breast cancer risk in a racially and ethnically diverse screening population using mammogram data.
Key Details
- 1Study included 206,929 women (average age 56.1) from a province-wide screening program starting at age 40.
- 2AI model used both current and up to four years of prior mammograms for risk scoring.
- 3Model achieved AUROC of 0.78 overall, 0.77 in East Asian, 0.77 in Indigenous, and 0.75 in South Asian women.
- 44,168 breast cancer cases confirmed over an average 5.3-year follow-up.
- 5Model showed consistent performance across age groups and ethnicities.
Why It Matters
Demonstrating robust, consistent AI performance across diverse populations supports its broader clinical adoption. Such risk models may enable more personalized and equitable breast cancer screening and resource allocation.
Source
AuntMinnie
Related News
•Radiology Business
Stanford and Rad Partners Propose Framework for Evaluating Radiology AI Models
Stanford and Rad Partners developed a structured framework for pre-deployment evaluation of radiology AI models to guide purchasing decisions.
•AuntMinnie
Deep Learning CT Muscle Segmentation Enhances Sarcopenia Detection in COPD
A deep learning model for CT-based 3D pectoralis muscle segmentation outperforms standard 2D techniques in assessing muscle loss among COPD patients.
•AuntMinnie
Stanford Launches Merlin: 3D AI Model for Abdominal CT Interpretation
Stanford researchers introduce Merlin, a 3D vision-language AI model for interpreting abdominal CT scans, demonstrating strong performance across multiple radiology tasks.