Using ultrasound images and AI to better describe and predict heart attacks
Official title: Cardiac Ultrasound Radiomics-Guided Deep Neural Networks for Acute Myocardial Infarction Precision Phenotyping
Funded at Rutgers Biomedical and Health Sciences · NIH-11247576 · Data updated 2026-11-12
This project uses routine heart ultrasound images plus AI to create detailed profiles that help predict outcomes for people hospitalized with acute heart attacks.
Quick facts
| Grant type | R01 grant |
|---|---|
| Study type | NIH-funded research |
| Funding institution | Rutgers Biomedical and Health Sciences NIH-funded |
| Lab location | 1 site (Newark, UNITED STATES) |
| Project start | December 12, 2024 |
| Project end | November 30, 2028 |
| Funding year | 2026 |
| Award (this year) | $578,414 |
| NIH project number | 5R01HL173998-02 |
| Project ID | NIH-11247576 on NIH RePORTER |
Who could benefit from this research
✓Could help
Adults hospitalized with acute myocardial infarction who have routine cardiac ultrasound (echocardiogram) images and clinical records available are the ideal candidates.
✕Less likely to help
People without usable echocardiogram images, those with non-cardiac chest pain, or patients with conditions unrelated to acute myocardial infarction are unlikely to benefit from this work.
What this research studies
If you have a heart attack and received a routine echocardiogram, researchers will use those images and your medical records to extract detailed imaging features (radiomics) and train AI models to identify who is at higher risk of complications. The team will standardize how ultrasound scans are converted into quantitative markers and combine those markers with standard echo measurements and clinical data from several hospitals. They will train and validate deep neural networks using existing hospital imaging and patient databases to improve prediction of outcomes after acute myocardial infarction. The effort aims to make noninvasive, objective markers that could guide personalized follow-up and treatment.
Why it matters
Potential benefit: If successful, this could help doctors identify which heart attack patients are at higher risk and tailor treatments or follow-up care accordingly.
How similar studies have gone: Early clinical data and preliminary studies suggest ultrasound radiomics can flag high-risk patients, but large-scale standardization and deep-learning validation remain relatively novel.
Where this research is happening
-
Rutgers Biomedical and Health Sciences
Newark, United States Active
Researchers
- Principal investigator: Sengupta, Partho P — Rutgers Biomedical and Health Sciences
- Study coordinator: Sengupta, Partho P
Related research
Other NIH-funded projects on the same topics.
-
Using advanced imaging and AI to improve heart attack risk assessment
This study is looking at how advanced heart imaging and smart computer technology can help doctors better understand which heart attack patients are at the highest risk, so they can create more personalized treatment plans to improve their health.
-
Targeted nanotherapy to calm inflammation, grow new blood vessels, and prevent scarring after a heart attack
A new treatment approach uses engineered secretions from immune cells delivered early after a heart attack to reduce inflammation, promote blood vessel growth, and limit scarring to protect heart function.
-
Real-time multi-lead ECG from wearables to help detect heart attacks early
A new AI-based approach uses everyday wearable sensors to turn simple PPG signals into multi-lead ECG data to monitor for heart attacks in real time, even outside the clinic.
-
Extreme heat and heart attack risk: who is most at risk and why
High heat and air pollution may raise the risk of heart attacks, and this project looks at who is most affected.
-
MMP-responsive biomaterials to treat a heart attack
A heart-attack treatment using smart materials that release healing therapies right where the heart was damaged, aimed at people who’ve had a heart attack.
-
Targeted ultrasound delivery of anti-inflammatory nitro-fatty acids to heal the heart after a heart attack
Using ultrasound-triggered microbubbles to deliver anti-inflammatory nitro-fatty acids directly to the heart for people recovering from a heart attack.
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.