AI that finds hidden heart disease risk in routine abdominal CT scans
Opportunistic Atherosclerotic Cardiovascular Disease Risk Estimation at Abdominal CTs with Robust and Unbiased Deep Learning
This project uses artificial intelligence on already-done abdominal CT scans and medical records to find people at higher risk for heart attack, stroke, or cardiovascular death.
Quick facts
| Grant type | R01 grant |
|---|---|
| Study type | NIH-funded research |
| Funding institution | Stanford University NIH-funded |
| Lab location | 1 site (Stanford, United States) |
| Project ID | NIH-11094820 on NIH RePORTER |
What this research studies
From my perspective as a patient, researchers will apply deep learning to existing abdominal CT images and link those image findings to electronic health records to look for signs tied to future heart problems. The team will automatically measure body fat, muscle, liver features, bone, and vascular calcifications from the scans with built-in quality checks. They will train models in a large, diverse, multi-site group and test performance against standard risk scores to see if the AI adds useful information. The goal is external validation across health systems so the approach could work in real-world care.
Who could benefit from this research
Good fit: Adults (21+) who have had an abdominal CT scan and linked electronic medical records, especially those without known cardiovascular disease, are the ideal candidates for this research.
Not a fit: People without prior abdominal CT scans, without usable medical records, or who already have advanced known cardiovascular disease are less likely to benefit from this work.
Why it matters
Potential benefit: If successful, this could help doctors spot higher cardiovascular risk earlier using CT scans taken for other reasons, enabling earlier prevention to reduce heart attacks and strokes.
How similar studies have performed: Related AI methods have successfully measured body composition and vascular calcification from images and linked them to risk, but applying these methods broadly to routine abdominal CTs for ASCVD prediction is a newer, actively tested idea.
Where this research is happening
Stanford, United States
- Stanford University — Stanford, United States (Active)
Researchers
- Principal investigator: Chaudhari, Akshay — Stanford University
- Study coordinator: Chaudhari, Akshay
About this research
- This is an active NIH-funded research project — typically early-stage science, not a clinical trial accepting patient enrollment.
- Some NIH-funded labs run parallel clinical studies or seek volunteers for related work. To check, contact the principal investigator or institution listed above.
- For full project details, budget, and progress reports, visit the official NIH RePORTER page below.