Researchers at the University of Massachusetts Amherst are contributing their computer science prowess to a large-scale federally funded project that will “fundamentally rethink hospital monitoring for expectant mothers and their babies,” according to Assistant Professor VP Nguyen of the Manning College of Information and Computer Sciences.

Image

Peripartum and infant mortality rates in the U.S. are higher than in any other high-income nation. The Advanced Research Projects Agency for Health (ARPA-H), an agency within the U.S. Department of Health and Human Services, Making Obstetrics Care Smart (MOCS) program aims to reduce maternal and infant mortality by creating technologies to make delivery safer.

The UMass Amherst team, led by Nguyen, director of the Wireless and Sensor Systems Laboratory, will build a system integration platform and computer architecture for a MOCS subproject developing a smart belt and ear sensor to monitor vital signs in both fetus and mother. The platform will enable comprehensive, continuous and reliable monitoring of physiological signals and translate those signals into usable data. 

Currently, pregnant patients and their fetuses are monitored during delivery using bedside heart rate detection technologies that inhibit movement to maintain signal quality and consistency. Having fetal heart rate data helps OB-GYNs make decisions about delivery: If the baby’s heart rate indicates cardiovascular distress, the doctor might need to resort to a cesarean section. But a C-section is a major surgical procedure and can lead to complications of its own, so it should be performed only when truly necessary.

Standard electronic fetal monitoring technology has not been updated in half a century, which means babies today are still born with low oxygen levels, and C-sections are performed more often than necessary.

MOCS will change that by pairing new sensors with AI technology to produce reliable information on the fetus’s oxygen levels using a wearable smart belt and ear sensor, even if the mother moves around. That means OB-GYNs will have vital information to perform cesarean sections only when needed.

To help make this happen, Nguyen’s team is contributing to the MOCS project titled “TA2: Novel Intrapartum Fetal Monitor with AI-Driven Decision Support,” which comprises five subprojects. 

This subproject, titled “HARMONI (Hypoxia Assessment via Real-time Maternal-fetal Oxygenation and Neurophysiological Integration),” is led by Tam Vu of Dartmouth College as lead principal investigator, with Xia Zhou of Columbia University as co-lead principal investigator. The research for this subproject will be conducted by scientists from Vu’s lab at Dartmouth College, Zhou’s lab at Columbia University, and Nguyen’s lab at UMass, including senior research scientist Trung Tran and doctoral student Sidharth Anupkrishnan, as well as four companies: Earable Neuroscience, 2333 Design, Sotatek, and Lumius Imaging. Each company offers sensing and data capabilities for use in UMass’s developing integration platform.

Phase 1 of the subproject was funded up to $5 million for the first year through the ARPA-H award and will conclude in June 2027. ARPA-H is a federal funding agency that supports research to drive “the development of high-impact solutions to society's most challenging health problems, delivering health breakthroughs in years, not decades.”

“This project represents a rare opportunity to bring together academic research and industry expertise around a shared platform to be developed by our team,” Nguyen said. “This is a real and exciting computer science research problem.

“And the social impact is significant, with the goal of advancing maternal-fetal health monitoring in ways that could meaningfully improve outcomes for mothers and babies.”

This research was funded, in part, by the Advanced Research Projects Agency for Health (ARPA-H). The views and conclusions contained in this document are those of the authors and should not be interpreted as representing the official policies, either expressed or implied, of the U.S. Government.