CAREER: Chest Vibrations as Markers of Critical Congenital Heart Defects: Characterization, Genesis, and Clinical Significance

About This Grant

Every year, about 8000 babies in the United States are born with serious heart defects, known as critical congenital heart diseases (CCHDs). These defects can change the normal flow of blood through the heart and can be life-threatening. It is important to find these defects soon after birth. In the U.S., all newborns are checked for CCHDs before they leave the hospital. This is done using a method called pulse oximetry which measures how much oxygen is in the blood. However, this method doesn’t always find some types of CCHDs. This project will work on a new way to find these heart defects. It is based on the idea that the small movements of a baby’s chest caused by heart activity are different in babies with CCHDs. The project will focus on finding the specific patterns of these chest movements that could indicate a CCHD. This could offer a new way to check for these heart defects. The knowledge and tools created by this project could help improve care for newborns with these heart diseases and reduce healthcare costs. The project will also include activities to teach people about CCHDs and how they are diagnosed, especially among groups who are more likely to be affected by these conditions. These activities include outreach to K-12 students, mentoring K-12 and undergraduate students in CCHD-related research, creating and publicly sharing short educational videos, and developing a mobile app to enhance parental awareness of congenital heart defects. The overall goal of this CAREER project is to enhance our understanding of the impact of major types of CCHDs, including coarctation of the aorta, tetralogy of Fallot, and patent ductus arteriosus, on the patterns and characteristics of chest surface vibrations recorded by seismocardiography (SCG) and gyrocardiography (GCG), and therefore, evaluate the clinical value of these signals in detecting CCHDs. The project’s central hypothesis is that these vibrations vary between newborns with CCHDs and those without cardiovascular diseases, and thus, they hold significant diagnostic potential for identifying CCHDs of interest. The goal of this project will be attained by (i) identifying indicators of CCHDs by evaluating the signatures of SCG and GCG signals in the presence of CCHDs, using machine learning and statistical models, (ii) understanding the spatiotemporal distribution of chest vibrations in the presence of CCHDs by creating and validating a novel vision-based pipeline, and (iii) investigating the genesis of CCHD indicators through developing and validating multiscale computational models. This project is jointly funded by the Engineering of Biomedical Systems Program (EBMS) and the Established Program to Stimulate Competitive Research (EPSCoR). This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.