Using machine learning to improve screening for serious heart defects in newborns
Official title: Machine Learning for CCHD Screening using Dynamic Data
Funded at University of California at Davis · NIH-11042185 · Data updated 2026-11-12
This study is working on a smart computer program that helps doctors find serious heart problems in newborns by using information from a simple test that measures oxygen levels, aiming to catch more cases that might be missed with current methods.
Quick facts
| Grant type | NIH-funded research |
|---|---|
| Study type | NIH-funded research |
| Funding institution | University of California at Davis NIH-funded |
| Lab location | 1 site (Davis, United States) |
| Project start | March 10, 2023 |
| Project end | February 28, 2027 |
| Funding year | 2025 |
| Award (this year) | $163,432 |
| NIH project number | 5K23HD108353-03 |
| Project ID | NIH-11042185 on NIH RePORTER |
Who could benefit from this research
✓Could help
Ideal candidates for this research are newborns aged 0-4 weeks who are undergoing screening for congenital heart defects.
✕Less likely to help
Patients who are older than 4 weeks or those without any congenital heart disease may not benefit from this research.
What this research studies
This research aims to develop a machine learning algorithm that enhances the screening process for critical congenital heart disease (CCHD) in newborns by utilizing dynamic data from pulse oximetry. Current screening methods often miss many cases of CCHD, particularly those without obvious symptoms. By analyzing various pulse oximetry features, such as oxygen saturation and perfusion index, the study seeks to improve detection rates significantly. The approach involves creating a model that can adapt its predictions based on real-time data, potentially leading to better outcomes for affected infants.
Why it matters
Potential benefit: If successful, this research could lead to earlier and more accurate detection of critical congenital heart disease in newborns, improving treatment outcomes.
How similar studies have gone: Previous research has shown promising results using machine learning for similar screening approaches, indicating potential for success in this novel application.
Where this research is happening
-
University of California at Davis
Davis, United States Active
Researchers
- Principal investigator: Siefkes, Heather M — University of California at Davis
- Study coordinator: Siefkes, Heather M
Related research
Other NIH-funded projects on the same topics.
-
UC Davis IGA Innovation Center
A research center at UC Davis will study gene-edited livestock to improve animal health, safety, and policy through sharing genetic data and findings about genome edits in cattle, pigs, sheep, and goats.
-
Administrative Core of an equitable breast cancer screening program
A national program headed from UC Davis is coordinating several research efforts to improve how breast cancer screening is done in community settings.
-
The role of novelty and surprise in learning for people with Alzheimer’s disease
A study explores how surprising events affect memory and learning in people related to Alzheimer’s disease, using everyday tasks to see how the brain remembers new information.
-
Understanding how distraction affects students and how to measure it better
This grant studies why distracted students, including those with ADHD, struggle in real-life learning and tests a clearer way to measure distraction in everyday settings.
-
California Partnership for Personalized Nutrition
A California clinical center is testing personalized dietary approaches to improve blood sugar and health for adults with diabetes by using big data and AI to tailor meals.
-
Advancing gastric cancer care for Latinos through patient-derived tumor models
Aimed at Latinos with gastric cancer, this project uses patient-derived tumor models to study how cancer biology and treatments work in real tumors.
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.