An AI-enabled, handheld ultrasound device could help novice healthcare professionals estimate gestational age as well as experienced sonographers, which could improve pregnancy care in low-resource areas.
Accurate estimates of gestational age are key to informed clinical care for pregnant patients, but making these estimates requires the use of ultrasonography. However, in low-resource settings, access to high-end ultrasound equipment and expert sonographers is often limited.
"In many low- and middle-income countries, women often don't receive an ultrasound during pregnancy," explained senior author of the study Margaret Kasaro, MBChB, MScPH, MMed OBGYN, assistant professor of Global Women's Health at the University of North Carolina (UNC), in a press release.
Kasaro, alongside colleagues from UNC's Institute for Global Health and Infectious Diseases and the University of Zambia, sought to address this by testing whether AI integration with point-of-care medical imaging could help novice clinicians estimate gestational age.
"This technology could [help] to identify high-risk pregnancies and improve outcomes for mothers and babies," she noted.
The study enrolled 400 pregnant patients across clinical sites in North Carolina and Zambia, where healthcare workers were provided with a Butterfly iQ+ handheld ultrasound device. Each patient's due date was confirmed via ultrasonography during their first trimester, and follow-up visits were randomly assigned throughout gestation.
By combining AI with portable ultrasound technology, we're bringing expert-level diagnostics to regions that have long lacked access to such resources.
Jeffrey S. A. Stringer, MD, FACOGLead author and professor of obstetrics and gynecology, UNC School of Medicine
During these visits, expert and non-expert clinicians were tasked with estimating gestational age using fetal biometry and the AI-enabled ultrasound tool, respectively.
The analysis revealed that novice users of the tool could effectively operate it with only one day of training. Between 14 and 27 weeks' gestation, these users could estimate gestational age as accurately as the expert sonographers.
The ultrasound tool performed well across the cohort, enabling generalizable insights in real time without the need for internet connectivity. The device achieved high performance up to 37 weeks' gestation, but isn't recommended for use after that.
Moving forward, additional research will investigate the tool's effectiveness in other geographical locations and in high-risk pregnancies. For now, the researchers emphasized that the study findings have significant implications for pregnancy care in low-resource settings.
"This study represents a major step forward in our ability to provide quality prenatal care globally," said Jeffrey S. A. Stringer, MD, FACOG, lead author and professor of obstetrics and gynecology at the UNC School of Medicine. "By combining AI with portable ultrasound technology, we're bringing expert-level diagnostics to regions that have long lacked access to such resources."
Shania Kennedy has been covering news related to health IT and analytics since 2022.
