AI model LeDXA extracts disease risk and biological age from X-ray scans

Researchers have developed LeDXA, a self-supervised learning model that extracts health insights from dual-energy X-ray absorptiometry (DXA) scans. Trained on unlabeled DXA images, LeDXA predicts disease risk, biological aging, and heritability, outperforming conventional DXA measurements and a general-purpose model like DINOv3. The model demonstrated improved prediction of prevalent and incident diseases, including hip and knee arthrosis and type 2 diabetes, and accurately estimated biological age, which correlated with disease burden and mortality risk. AI

IMPACT This research demonstrates the potential for AI to extract deeper health insights from medical imaging, potentially improving disease prediction and personalized health assessments.

RANK_REASON Publication of a new research paper detailing a novel AI model and its findings. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.CV →

• DINOv3
• dual-energy X-ray absorptiometry
• Human Phenotype Project
• LeDXA
• UK Biobank

• paper
• model release
• other

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →