Related Experiment Video
Updated: Jul 19, 2026
Fetal Mouse Cardiovascular Imaging Using a High-frequency Ultrasound 30/45MHZ System
Published on: May 5, 2018
Artificial intelligence-driven framework for improving prenatal screening for congenital heart disease in rural
Ling Li1,2, Alex J Foy1,2, Jason T Christensen1,2
1Criss Heart Center, Children's Nebraska, Omaha, NE, United States.
Insights
This study introduces an AI framework to improve early detection of congenital heart disease (CHD) in rural Nebraska. The goal is to reduce disparities by integrating AI into routine prenatal care for better neonatal outcomes.
Area of Science:
- Cardiology
- Medical Imaging
- Artificial Intelligence
Background:
- Congenital heart disease (CHD) is a common birth defect impacting neonatal health.
- Rural areas face disparities in CHD detection due to limited access to specialized diagnostics.
- Existing prenatal imaging has limitations in early CHD identification in underserved communities.
Purpose of the Study:
- To propose an AI-enabled framework for early CHD detection in routine prenatal care.
- To address and reduce the rural-urban gap in Nebraska for CHD diagnosis.
- To enhance prenatal care accessibility in underserved regions.
Main Methods:
- Reviewed 1,502 surgical CHD cases (2019-2024) at Children's Nebraska to identify geographic disparities.
- Developed a secure, cloud-based platform for applying AI algorithms to standard obstetric ultrasound images.
- Established a referral system to nearby fetal cardiology outreach centers for flagged cases.
Main Results:
- Identified significant geographic disparities in prenatal CHD detection.
- Proposed an AI framework leveraging existing infrastructure and interdisciplinary collaboration.
- Demonstrated a method to reduce delays in accessing tertiary care.
Conclusions:
- The AI framework decentralizes diagnostics for earlier triaging in community settings.
- This approach offers a scalable and accessible solution for improving prenatal CHD detection.
- The model has strong potential for national replication in underserved regions.
Purpose:
Congenital heart disease (CHD) is the most common birth defect and a leading cause of neonatal morbidity and mortality. Despite advances in prenatal imaging, rural communities face persistent disparities in CHD detection due to limited access to specialized diagnostics. This position paper proposes an AI-enabled framework to embed early CHD detection into routine prenatal care and reduce the rural-urban gap in Nebraska.
Method:
A review of 1,502 surgical CHD cases at Children's Nebraska (2019-2024) revealed significant geographic disparities in prenatal detection. In response, we outline a framework that leverages a secure, cloud-based platform to apply AI algorithms to standard obstetric ultrasound images. Flagged cases are referred to nearby fetal cardiology outreach centers, reducing delays associated with centralized tertiary care access.
Framework:
This approach leverages existing infrastructure, including the Children's Nebraska fetal heart center, UNMC's rural residency network, and maternal-fetal medicine collaborations. Implementation will be led by an interdisciplinary team spanning cardiology, Obstetrics, rural health, imaging, and machine learning.
Conclusion:
By decentralizing diagnostics and enabling earlier triaging in community settings, this scalable, accessible framework offers a practical solution for improving prenatal CHD detection in underserved regions, with strong potential for national replication.
