AI to find early mitral valve problems and predict future heart risks
Official title: Deep Learning Based Phenotyping and Outcomes Prediction for Valvular Heart Disease
Funded at Cedars-Sinai Medical Center · NIH-11325063 · Data updated 2026-11-12
This project uses artificial intelligence on heart ultrasound images to find early mitral valve changes and predict which adults might later develop serious heart complications.
Quick facts
| Grant type | R01 grant |
|---|---|
| Study type | NIH-funded research |
| Funding institution | Cedars-Sinai Medical Center NIH-funded |
| Lab location | 1 site (Los Angeles, United States) |
| Project start | May 1, 2024 |
| Project end | April 30, 2029 |
| Funding year | 2026 |
| Award (this year) | $817,105 |
| NIH project number | 5R01HL173526-03 |
| Project ID | NIH-11325063 on NIH RePORTER |
Who could benefit from this research
✓Could help
Adults aged 21 and older with known or suspected mitral valve disease or who have had echocardiograms are the most likely candidates for participation.
✕Less likely to help
People under 21, those without available echocardiogram images or clinical follow-up data, or those with valve problems unrelated to the mitral valve may not see direct benefit from this work.
What this research studies
The team will train deep learning models on thousands of echocardiograms linked to clinical outcomes to learn subtle imaging patterns of mitral valve disease and myocardial remodeling. If your images are included, the AI will look for changes that are hard for humans to see and compare them with later events like worsening mitral regurgitation, heart failure, or cardiac arrest. The work combines image analysis with patient health records to build risk prediction tools. The aim is to create automated signals that could one day help clinicians decide who needs closer follow-up or earlier treatment.
Why it matters
Potential benefit: If successful, the approach could help detect dangerous valve changes earlier and guide timely treatment to reduce heart failure and sudden complications.
How similar studies have gone: Previous AI work on echocardiography has shown promising ability to measure heart structure and flag risk features, but using AI to predict long-term mitral valve outcomes is a newer and still-emerging application.
Where this research is happening
-
Cedars-Sinai Medical Center
Los Angeles, United States Active
Researchers
- Principal investigator: Ouyang, David — Cedars-Sinai Medical Center
- Study coordinator: Ouyang, David
Related research
Other NIH-funded projects on the same topics.
-
Using AI to improve diagnosis and outcomes for mitral valve disease
This study is looking at how we can use advanced computer technology to better understand mitral valve disease, helping doctors spot early signs of problems in heart images so they can provide better care and treatment for patients like you.
-
Understanding how blood vessel cells change to help or worsen heart valves
Researchers are studying how endothelial cells change and contribute to mitral valve prolapse to find better ways to treat this common heart valve condition.
-
Improving heart valve disease diagnosis with stress cardiac MRI
This project aims to create a better way to understand mitral valve problems using a special heart MRI scan, helping doctors decide the best treatment for patients.
-
Understanding the role of PKD3 in heart valve disease
This study is looking into how certain heart cells change and affect heart valve health in people with valvular heart disease, with the hope of finding new ways to treat this condition and help patients feel better.
-
Understanding Cilia's Role in Heart Valve Disease
This project explores how tiny structures called cilia and certain gene changes might cause common heart valve problems like mitral valve prolapse.
-
Improving heart valve disease assessment using advanced MRI techniques
This study is testing a new type of heart scan to help doctors better understand and treat mitral valve regurgitation, so if you have this condition, it could lead to more accurate diagnoses and better treatment options for you.
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.