Ultrasound AI Publishes Landmark Study Demonstrating Breakthrough in Predicting Delivery Timing Using AI and Ultrasound Images
The AI predicts delivery timing with up to 95% accuracy using over two million ultrasound images, aiming to improve management of preterm births worldwide, researchers said.
- On August 13, 2025, Ultrasound AI revealed that the results of its PAIR Study had been published in The Journal of Maternal-Fetal and Neonatal Medicine during an event held in Denver.
- The research utilized a dataset comprising more than two million de-identified ultrasound images collected from thousands of women who gave birth at the University of Kentucky between 2017 and 2021.
- Ultrasound AI's proprietary technology accurately predicted time to delivery using only ultrasound images, performing consistently across trimesters and demographics without clinical inputs.
- The AI demonstrated a strong accuracy of 0.95 in predicting term births and significantly enhanced preterm birth prediction accuracy from R=0.48 to 0.72 through ongoing retraining. Robert Bunn highlighted that this advancement could greatly impact medical care and public health, particularly by enabling early risk detection in areas with limited access to specialized healthcare.
- This milestone suggests Ultrasound AI's technology could advance global maternal health by enabling scalable, non-invasive delivery timing prediction and improving early risk identification worldwide.
Insights by Ground AI
Does this summary seem wrong?
13 Articles
13 Articles
AI and ultrasound images can now help predict infant delivery timing
Ultrasound AI, which develops artificial intelligence applications for medical imaging, has published findings from its PAIR (Perinatal Artificial Intelligence in Ultrasound) Study in The Journal of Maternal-Fetal & Neonatal Medicine.

+10 Reposted by 10 other sources
Ultrasound AI Publishes Landmark Study Demonstrating Breakthrough in Predicting Delivery Timing Using AI and Ultrasound Images
AI-powered delivery date prediction model shows high accuracy and improved performance over time, with promise for global maternal health impact
Coverage Details
Total News Sources13
Leaning Left1Leaning Right0Center6Last UpdatedBias Distribution86% Center
Bias Distribution
- 86% of the sources are Center
86% Center
14%
C 86%
Factuality
To view factuality data please Upgrade to Premium