A deep-learning model predicts coronary artery calcium (CAC) scores from chest x-rays, improving risk assessment for coronary artery disease.
Key Details
- 1Researchers developed and validated an AI model to predict CAC scores from chest x-rays.
- 2The study analyzed data from 10,230 patients with paired chest x-rays and CAC scores.
- 3Models were trained to classify risk based on CAC thresholds of 0, 100, and 400.
- 4Best performance AUCs were 0.74–0.79 (x-ray only), improving to 0.77–0.82 with clinical variables.
- 5External validation resulted in consistent AUCs of 0.78–0.81, supporting robustness.
Why It Matters
This research demonstrates AI's potential to estimate coronary risk from routine chest x-rays, reducing reliance on CT, lowering costs, and minimizing radiation exposure for cardiovascular risk assessment.
Source
AuntMinnie
Related News
•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.
•Cardiovascular Business
Radiology Maintains Lead in FDA-Cleared AI Algorithms, Cardiology Follows
Radiology remains the top specialty for FDA-cleared AI, with cardiology as a strong second, particularly in cardiovascular imaging.
•AuntMinnie
Deep Learning Models Rival Radiologists for Pancreatic Cancer Detection on CT
Deep-learning models achieved comparable or superior accuracy to experienced radiologists in detecting pancreatic cancer on CT scans, especially for small tumors.