Using ultrasound images and AI to better describe and predict heart attacks
Cardiac Ultrasound Radiomics-Guided Deep Neural Networks for Acute Myocardial Infarction Precision Phenotyping
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 ID | NIH-11247576 on NIH RePORTER |
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.
Who could benefit from this research
Good fit: Adults hospitalized with acute myocardial infarction who have routine cardiac ultrasound (echocardiogram) images and clinical records available are the ideal candidates.
Not a fit: 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.
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 performed: 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
Newark, UNITED STATES
- 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
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.