A deep learning model can predict cardiovascular risk in women using routine mammograms, performing comparably to traditional risk calculators.
Key Details
- 1Developed by The George Institute for Global Health in collaboration with UNSW and University of Sydney.
- 2Uses only mammographic features and age—no need for additional clinical data.
- 3Validated using data from over 49,000 routine mammograms linked to hospital and death records.
- 4Performs comparably to traditional cardiovascular risk models requiring more extensive data.
- 5Potential for integration into existing high-participation breast screening programs globally.
Why It Matters
This approach could allow opportunistic cardiovascular risk screening for women already undergoing mammograms, potentially improving early identification and prevention of heart disease. It demonstrates innovative use of imaging AI beyond traditional cancer detection, with public health implications for women's care.
Source
EurekAlert
Related News
•EurekAlert
AI-Powered OCT Enables Rapid 'Optical Biopsy' for Early Endometrial Cancer Detection
A team at Washington University has developed a catheter-based 3D OCT system with AI to quickly and noninvasively detect early endometrial cancers.
•EurekAlert
AI Clinical Reasoning in Diagnostics and Digital Fatigue in Healthcare
Recent JMIR features explore large language models in clinical diagnostics and digital fatigue among healthcare professionals.
•EurekAlert
KAIST, MIT, Microsoft Develop Efficient AI Image Upsampling for Robotics
KAIST, MIT, and Microsoft have created 'Upsample Anything,' a training-free AI method to restore high-resolution visual data from compressed images with up to 16x improved GPU memory efficiency.