BrightHeart and Mount Sinai Deploy AI Ultrasound Tool to Improve Congenital Heart Defect Detection

Mount Sinai Health System has become the first in New York City to adopt an FDA-approved artificial intelligence tool to enhance prenatal ultrasounds at scale, aiming to improve the early detection of congenital heart defects. Carnegie Imaging for Women, a Mount Sinai-affiliated imaging center with three locations in Manhattan, is the first facility in the city to use the BrightHeart AI software to support clinicians in reading ultrasound scans. Congenital heart defects remain one of the most common birth abnormalities, with approximately 1 in 500 newborns classified as having a severe defect requiring immediate medical or surgical intervention, according to the National Institutes of Health.

A recent study in Obstetrics & Gynecology, led by clinicians at Mount Sinai West, evaluated the use of the AI technology on 200 deidentified fetal ultrasound examinations between 18 and 24 weeks’ gestation from 11 medical centers across two countries. Half of the scans contained at least one suspicious finding. Fourteen physicians, including seven obstetrician-gynecologists and seven maternal-fetal medicine specialists, reviewed each ultrasound in randomized order with and without AI support. The study found that AI assistance improved detection rates of suspicious findings for major congenital heart defects to more than 97 percent, while reducing reading time by 18 percent and increasing confidence scores by 19 percent.

Jennifer Lam-Rachlin, MD, corresponding author and Assistant Clinical Professor of Obstetrics, Gynecology and Reproductive Science at the Icahn School of Medicine at Mount Sinai, stated that “AI assistance in prenatal diagnosis offers not only improved detection, but has the potential to offer significant improvement in workflow and efficiency benefits. We, as clinicians, should embrace innovation and technology that is available, in order to maximize quality patient care. This technology allows for 'leveling' of the field of prenatal diagnosis to offer close to expert-level review of fetal ultrasounds, particularly in centers or geographical locations without fetal heart experts.”

Co-author Andrei Rebarber, MD, Director of the Division of Maternal-Fetal Medicine at Mount Sinai West, added that “Our study should prompt and encourage future research into AI-assisted software's ability to improve detection rates, once integrated into clinical workflows, to reduce the variability and inequity of detection of congenital heart defects globally. The future for prenatal diagnostic imaging is bright when AI software is employed as an adjunct to physician interpretation.”

Click here for the original news story.