A new artificial intelligence (AI) model accurately detected the presence of placenta accreta spectrum (PAS), a dangerous pregnancy condition that often goes undetected by current screening methods, according to new research presented today at the Society for Maternal-Fetal Medicine (SMFM) 2026 Pregnancy Conference™. Researchers say PAS is a leading cause of maternal mortality and morbidity, but only half of all cases are diagnosed during pregnancy.
PAS is a life-threatening pregnancy complication in which the placenta becomes abnormally attached to the uterine wall and is often associated with previous uterine surgery, such as a caesarean section. The incidence of PAS is increasing in the United States. Placenta accreta, a condition that is poorly diagnosed before birth, can lead to massive maternal bleeding, multisystem organ failure, and death. Pregnancies at high risk for PAS are usually screened based on risk factors and ultrasound examinations to identify and prepare for the problem before birth, but many factors can lead to inconclusive findings and misdiagnosis.
“Our team is very excited about the potential clinical implications of this model for the accurate and timely diagnosis of PAS,” said researcher Alexandra L. Hammerquist, MD, a maternal-fetal medicine fellow at Baylor College of Medicine in Houston, Texas. “We hope that using this as a screening tool will reduce PAS-related maternal morbidity and mortality.”
Baylor College of Medicine researchers used an innovative AI program to retrospectively review 2D obstetric ultrasound images of 113 patients at risk for PAS who delivered at Texas Children’s Hospital between 2018 and 2025. The mean gestational age at the time of maternal ultrasound examination was 30.89 +3.67 weeks.
Based on a retrospective review of 2D ultrasound images from 113 patients, the researchers found that the AI model accurately detected the presence of all PAS cases. There were two false-positive reports of placenta accreta, but no false-negative reports.
sauce:
http://Maternal-Fetal Medicine Society
