AI-powered ultrasound significantly improves the detection of congenital heart defects

AI-powered ultrasound significantly improves the detection of congenital heart defects

Doctors at Mount Sinai's Raquel and Jaime Gilinski Department of Obstetrics, Gynecology and Reproductive Sciences have become the first in New York City to implement an artificial intelligence (AI) tool that improves ultrasound scans at scale - leading to earlier detection and better care for babies and families.

Congenital heart defects, or conditions present at birth that affect the structure of the heart, are among the most common birth anomalies. According to the National Institutes of Health, about 1 in 500 newborns will be diagnosed with a serious congenital heart defect that requires urgent medical or surgical intervention to survive.

Carnegie Imaging for Women, an advanced obstetrics and gynecology imaging facility, is the first center in New York City to use a Food and Drug Administration-approved AI software tool from medical company BrightHeart to make ultrasounds more accurate and efficient. The center, affiliated with Mount Sinai, has three locations in Manhattan.

In a current oneObstetrics and gynecologyIn a study led by doctors at Mount Sinai West, researchers used AI technology to improve their detection rates of ultrasound findings suspicious for serious congenital heart defects to over 97 percent, reducing reading time by 18 percent and improving confidence scores by 19 percent.

AI support in prenatal diagnostics not only offers improved detection, but also has the potential to significantly improve workflow and increase efficiency. We as clinicians should utilize the innovations and technologies available to maximize the quality of patient care. This technology enables “leveling” the field of prenatal diagnostics to enable near-expert level review of fetal ultrasound examinations, particularly in centers or geographic locations without fetal heart experts.”

Jennifer Lam-Rachlin, MD,Corresponding author,Assistant Professor of Obstetrics, Gynecology and Reproductive Sciences at the Icahn School of Medicine at Mount Sinai

Researchers examined a dataset of 200 unidentified fetal ultrasound scans between weeks 18 and 24 of pregnancy from 11 medical centers in two countries, including 100 with at least one suspicious finding. The aim of the study was to evaluate the association between the use of AI-based software and reading performance in identifying second trimester ultrasounds suspected of major congenital heart defects. Seven obstetrician-gynecologists and seven maternal-fetal medicine specialists (experts in high-risk pregnancies) reviewed each examination in random order, both with and without AI assistance, and assessed the presence or absence of each finding suspicious for congenital heart defects using confidence scores.

AI-assisted interpretation was associated with improved detection of lesions suspected of having major congenital heart defects. The study demonstrated the ability of AI-based software to improve the detection of these suspicious findings using prenatal ultrasound, as well as the overall safety and time efficiency in interpreting these scans.

“Our study should initiate and encourage future research into the ability of AI-powered software to improve detection rates once integrated into clinical workflows to reduce variability and disparity in the detection of congenital heart defects worldwide,” said co-author Andrei Rebarber, MD, director of the Division of Maternal-Fetal Medicine at Mount Sinai West and clinical professor of obstetrics, gynecology and reproductive sciences at the Icahn School of Medicine at Mount Sinai. “The future of prenatal diagnostic imaging is bright when AI software is used to complement medical interpretation.”

Sources: