Using AI to identify undiagnosed heart diseases from ECGs
Official title: Capitalizing on Artificial Intelligence to Capture Undiagnosed Structural Heart Disease from Electrocardiograms (CACTUS)
Funded at Columbia University Health Sciences · NIH-11029663 · Data updated 2026-11-12
This study is testing a new tool called EchoNext that uses heart wave data to help doctors find heart problems in patients who come to the emergency room, especially those who might not usually get the tests they need.
Quick facts
| Grant type | R01 grant |
|---|---|
| Study type | NIH-funded research |
| Funding institution | Columbia University Health Sciences NIH-funded |
| Lab location | 1 site (New York, United States) |
| Project start | April 1, 2025 |
| Project end | January 31, 2030 |
| Funding year | 2025 |
| Award (this year) | $704,611 |
| NIH project number | 1R01HL177055-01 |
| Project ID | NIH-11029663 on NIH RePORTER |
Who could benefit from this research
✓Could help
Ideal candidates for this research include patients presenting to emergency departments who may have undiagnosed structural heart disease.
✕Less likely to help
Patients with known structural heart disease or those who do not present to emergency departments may not benefit from this research.
What this research studies
This research focuses on improving the detection of structural heart disease (SHD) using a deep learning model called EchoNext, which analyzes raw electrocardiogram (ECG) waveforms. By leveraging a large database of ECGs and echocardiograms, the model aims to accurately predict SHD and identify patients who may need further evaluation through echocardiography. This approach is particularly beneficial for patients in emergency departments, especially those from disadvantaged backgrounds who may not have access to standard diagnostic methods. The study will assess the effectiveness of EchoNext in detecting undiagnosed SHD among patients presenting to emergency departments.
Why it matters
Potential benefit: If successful, this research could lead to earlier diagnosis and treatment of structural heart disease, potentially reducing cardiovascular morbidity and mortality.
How similar studies have gone: Previous research has shown promise in using AI for medical diagnostics, indicating potential success for this novel approach.
Where this research is happening
-
Columbia University Health Sciences
New York, United States Active
Researchers
- Principal investigator: Elias, Pierre a — Columbia University Health Sciences
- Study coordinator: Elias, Pierre a
Related research
Other NIH-funded projects on the same topics.
-
Accelerating Rheumatic Heart Disease Prevention in Uganda
A program to find people with rheumatic heart disease in Ugandan communities and give them preventive care close to home.
-
Multimodal AI to improve genetic diagnosis of congenital heart disease
A new AI tool uses multiple types of patient data to help doctors find genetic causes of congenital heart disease more accurately.
-
Functional screen of hydrocephalus and heart-disease genes in a frog model
A study uses frog embryos to test how human genetic changes might cause congenital hydrocephalus and related heart defects, with the goal of understanding why these conditions occur.
-
Multimodal AI to improve genetic diagnosis of congenital heart disease
A big AI project will help doctors and families by better identifying genetic causes of congenital heart defects using imaging, medical data, and genome information.
-
Brain injury risk in preterm babies with heart disease and how surgery choices affect their brains
This project follows newborns with congenital heart disease born early to understand how their brains are affected and how different surgical approaches might influence outcomes.
-
Newborn brain injury risk during birth transition in babies with congenital heart defects
This project will look at how circulation changes around birth affect newborn brain health in babies with transposition of the great arteries.
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.