Uniting a leading maternal-fetal medicine program with some of the world’s most advanced supercomputing resources, researchers and clinicians at The University of Texas at Austin are aiming to reduce rates of stillbirth, which occurs more than 20,000 times per year in the U.S. alone.
The solution may already be in your pocket.
Stillbirth — pregnancy loss after 28 weeks — occurs every 16 seconds globally. Monitoring a fetus’ movements can be the most helpful health indicator in late pregnancy, but traditional, manual methods like having a mother track “kick counts” can be limited to as little as 30% overall accuracy.
Kenneth Moise, M.D., a maternal-fetal specialist and professor in the Department of Women’s Health at Dell Medical School, has launched a study in collaboration with Kelly Gaither, Ph.D., the deputy director at the Texas Advanced Computing Center and an associate professor in the Department of Women’s Health at Dell Med, to create a deep-learning algorithm that relies on smartphone audio recordings to track fetal movements. Pilot studies of the algorithm indicate an accuracy rate of more than 70% in detecting gross fetal movement, already more than doubling the accuracy of traditional methods and creating a pathway for consistent, reliable, at-home monitoring. The algorithm can also detect fetal breathing movements, a marker for fetal well-being.
The data gives providers an additional tool to intervene earlier if concerns arise, and in addition to providing real-time data, future applications like a smartphone app could allow mothers to track movement patterns over time, offering a daily snapshot of fetal well-being.
“By identifying deviations from normal fetal movement patterns, we can intervene before a crisis arises, and more broadly, change the landscape of later-stage prenatal care,” says Moise, who leads the Comprehensive Fetal Care Center at Dell Children’s Medical Center, a partnership between UT Health Austin and Ascension Seton. “Current methods can lead to unnecessary anxiety or missed warning signs, and it’s hard to be in that in-between space. Our goal is to create a system that provides accurate, real-time data that can help identify potential risks early, giving parents and doctors more confidence.”
Building the Solution
The current study is following 25 pregnant women over the course of five visits. At each visit, the team tracks three monitoring methods simultaneously: Ultrasound provides high-accuracy control data, while mothers also hold a smartphone to their abdomen to record sound, and they separately track “kicks” in the traditional method.
“The process was so simple, and it’s such an easy thing to do to help progress some really valuable technology,” says Sara Toynbee, who participated in pilot studies and has now returned to participate during her second pregnancy. “I’ve had that feeling later on in my first pregnancy where you haven’t felt any movement in awhile, and the ability to have some control or useful information to react to would have been invaluable. Technology like this is a no-brainer.”
With the significant amount of data to be reconciled across the three types of data inputs, Texas Advanced Computing Center, which houses the world’s largest academic supercomputer, brings unique expertise and technical capability to bear on producing a usable, reliable algorithm.
“Smartphones are a perfect tool for this kind of project,” Gaither says. “They’re always with the user, they’re noninvasive, and they can provide real-time feedback. During low-risk pregnancies, patients see the doctor 11-15 times, which represents less than 1% of their lived experiences. With the power of machine learning and artificial intelligence, we can build an algorithm to reduce the guesswork and alleviate unnecessary anxiety for the patient while providing critically needed data to inform clinicians with the overall goal of improving stillbirth rates.”
Translation to the Real World
Currently, the project is a finalist in the most recent cycle of participants for Texas Health Catalyst, a Dell Med initiative that identifies and nurtures promising solutions to pressing health challenges. One focus of this cycle is on advancing the “hospital of the future,” which is underpinned by hospital-at-home technologies like accessible monitoring.
“From here, we could produce a basic smartphone app that can be bought and used by parents like any other app,” Moise says. “Another pathway, though, could involve more rigorous, multicenter trials that track outcomes, which would allow us to apply for Food and Drug Administration approval and incorporate it in clinical workflows as a true diagnostic tool that physicians can prescribe.
“Programs like Texas Health Catalyst help our teams think through the best paths to market — the paths that will have the best patient uptake and impact on outcomes, which is really what we’re after.”