AI-powered echocardiography to spot common heart defects in newborns
Official title: AI-facilitated Echocardiography for Early Detection of Acyanotic Congenital Heart Disease in Infants
Funded at Health Research Foundation · NIH-11446295 · Data updated 2026-11-12
A new AI tool analyzes infant heart ultrasound images to help non-specialist health workers identify five common, treatable heart defects early.
Quick facts
| Grant type | R21 grant |
|---|---|
| Study type | NIH-funded research |
| Funding institution | Health Research Foundation NIH-funded |
| Lab location | 1 site (Buea, CAMEROON) |
| Project start | September 18, 2026 |
| Project end | August 31, 2028 |
| Funding year | 2026 |
| Award (this year) | $74,995 |
| NIH project number | 1R21HL188666-01 |
| Project ID | NIH-11446295 on NIH RePORTER |
Who could benefit from this research
✓Could help
Infants aged 0–12 months evaluated in settings with limited access to pediatric cardiology.
✕Less likely to help
If there is no access to echocardiography or trained personnel, the AI tool may not be deployable.
What this research studies
This project aims to create AI models that can automatically detect five common acyanotic congenital heart defects (ASD, VSD, AVSD, COA, PDA) in infants using postnatal echocardiography. Building on prior work that automated basic cardiac view identification, the team will adapt models to recognize specific defects and landmarks, leveraging datasets from South Africa and Cameroon. The goal is to enable nurses, midwives, general practitioners, and sonographers in low-resource settings to screen for these conditions where specialists are scarce. The project will use convolutional neural networks to identify anatomical features and patterns associated with each CHD directly from echocardiogram videos. Overall, the work seeks to deliver a practical, point-of-care AI tool that supports earlier detection and timely referral for treatment.
Why it matters
Potential benefit: If successful, babies with acyanotic CHDs could be diagnosed earlier, enabling faster treatment and better outcomes.
How similar studies have gone: Previous work automated general echocardiography view identification; this project extends to specific CHD detection in real-world, low-resource settings.
Where this research is happening
-
Health Research Foundation
Buea, Cameroon Active
Researchers
- Principal investigator: Leke, Aminkeng Zawuo — Health Research Foundation
- Study coordinator: Leke, Aminkeng Zawuo
Related research
Other NIH-funded projects on the same topics.
-
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.
-
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.
-
Heart development study using patient stem cells to understand NOTCH1 and congenital heart disease
A study using patient-derived stem cells and genome editing to learn how NOTCH1 affects early heart development and congenital heart defects in humans.
-
Genetic clues to congenital heart defects and outcomes
This grant studies how genetic differences contribute to congenital heart defects (CHD) and how these variations affect health over time, with patient data from a large biobank and health records.
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.