AI-derived measurement of heart fat from CT scans significantly improves long-term cardiovascular disease risk prediction.
Key Details
- 1Mayo Clinic researchers augmented routine coronary artery calcium CT scans with AI to measure pericardial (heart) fat.
- 2Study included nearly 12,000 adults, followed for around 16 years.
- 3Approximately 10% of participants developed cardiovascular disease during the study period.
- 4Higher heart fat volume predicted elevated risk of cardiovascular events independently of traditional risk factors and coronary calcium scores.
- 5Adding this AI-derived metric to existing models improved predictive accuracy, especially for patients at borderline or intermediate risk.
- 6Method leverages information from scans already widely performed, without extra testing or cost.
Why It Matters
This approach demonstrates how AI can extract valuable additional prognostic data from existing cardiac imaging, potentially enabling earlier and more tailored intervention for cardiovascular disease using data already available to radiologists.
Source
EurekAlert
Related News
•EurekAlert
NIH-Backed AI Model Predicts Cancer Survival Using Single-Cell Data
Researchers have developed scSurvival, a machine learning tool that uses single-cell tumor data to accurately predict cancer patient survival and identify high-risk cell populations.
•EurekAlert
AI Pathology Model Outperforms PD-L1 in Predicting NSCLC Immunotherapy Response
MD Anderson's Path-IO machine learning platform accurately predicts immunotherapy responses in metastatic non-small cell lung cancer, surpassing current biomarker standards.
•EurekAlert
Deep Learning Pathomics Platform Improves Immunotherapy Prediction in Lung Cancer
A deep learning pathomics platform accurately predicts immunotherapy response in metastatic NSCLC using routine pathology slides.