AI Shows Promise in Early Detection of Life-Threatening Placenta Accreta

A new artificial intelligence (AI) model is demonstrating significant accuracy in detecting placenta accreta spectrum (PAS), a dangerous and potentially fatal pregnancy complication, before delivery. This breakthrough offers hope for improved diagnosis and management of a condition that is increasingly prevalent and often goes undetected with current screening methods.

The Rising Incidence of Placenta Accreta

Placenta accreta occurs when the placenta abnormally attaches to the uterine wall. The incidence of PAS is rising in the United States, linked to increasing rates of cesarean deliveries and pregnancies occurring at older maternal ages. A study cited by the MSD Manual found that the rate increased from 1 in 2,510 deliveries in the 1970s to 1 in 272 deliveries between 1998 and 2011. MSD Manual

The condition can lead to massive maternal hemorrhage, organ failure, and even death, making early and accurate diagnosis crucial.

How the AI Model Works

Researchers from Baylor College of Medicine retrospectively analyzed 2D obstetric ultrasound images from 113 patients at risk for PAS who delivered at Texas Children’s Hospital between 2018 and 2025. Society for Maternal-Fetal Medicine The AI model accurately identified all cases of PAS, demonstrating no false negatives. There were, however, two false positives.

“Our team is very excited about the potential clinical implications of this model for accurate and timely diagnosis of PAS,” said Dr. Alexandra L. Hammerquist, a maternal-fetal medicine fellow at Baylor College of Medicine. Society for Maternal-Fetal Medicine “We are hopeful that its use as a screening tool will help decrease PAS-related maternal morbidity and mortality.”

Additional Research and Machine Learning Approaches

Mount Sinai researchers are also exploring machine learning models to predict placenta accreta spectrum, utilizing Electronic Medical Record (EMR) data. EurekAlert! Their work suggests that machine learning can identify patients at elevated risk with high sensitivity and specificity, potentially identifying anemia as a novel predictor and facilitating early risk counseling and personalized care planning.

The Role of Cesarean Delivery

Both increasing cesarean section rates and increasing maternal age are contributing factors to the rise in placenta accreta worldwide. In France, 21.4% of deliveries were by cesarean section in 2021. Society for Maternal-Fetal Medicine

Looking Ahead

The development of this AI model represents a significant step forward in improving the detection and management of placenta accreta. Further research and clinical implementation are needed to fully realize its potential to reduce maternal morbidity and mortality associated with this dangerous pregnancy complication.