AI that finds hidden heart disease risk in routine abdominal CT scans
Official title: Opportunistic Atherosclerotic Cardiovascular Disease Risk Estimation at Abdominal CTs with Robust and Unbiased Deep Learning
Funded at Stanford University · NIH-11094820 · Data updated 2026-11-12
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 start | September 1, 2023 |
| Project end | May 31, 2028 |
| Funding year | 2025 |
| Award (this year) | $584,766 |
| NIH project number | 5R01HL167974-03 |
| Project ID | NIH-11094820 on NIH RePORTER |
Who could benefit from this research
✓Could help
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.
✕Less likely to help
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.
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.
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 gone: 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 University
Stanford, United States Active
Researchers
- Principal investigator: Chaudhari, Akshay — Stanford University
- Study coordinator: Chaudhari, Akshay
Related research
Other NIH-funded projects on the same topics.
-
Opportunistic heart risk detection from abdominal CTs using robust AI
A doctor-scientist team at Stanford will use existing abdominal CT scans and medical records to build a trustworthy AI tool that helps predict future heart problems in adults.
-
Integrative model of metabolites, equol, and heart disease
This grant looks at how a person’s body processes soy isoflavones into equol and how that relates to atherosclerotic heart disease, using complex data to build predictive models.
-
Lp(a) and HIV: Understanding Heart Disease Risk in HIV Patients
This program looks at how Lipoprotein(a) contributes to higher heart disease risk in people with HIV and what Lp(a) levels mean for future treatments.
-
PVAT and arteries: why some vessels resist plaque
Aims to understand how fat tissue around arteries influences atherosclerosis, especially why the left internal mammary artery stays healthy while others don’t.
-
How T cell genes and signals affect atherosclerosis
This grant studies how a specific immune cell and its signals influence atherosclerosis in people, aiming to uncover new ways to reduce inflammation and heart disease risk.
-
Understanding why some artery plaques become dangerous using genetics, tissue maps, and advanced imaging
Researchers will combine human genetic data with single-cell and spatial tissue maps to find why certain atherosclerotic plaques are more likely to cause heart events, aiming to improve prediction and prevention.
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.