Ultrasound AI's Study Enhances Delivery Timing Predictions with AI

Ultrasound AI has published a landmark study demonstrating a breakthrough in predicting delivery timing using AI and ultrasound images, announced in a press release. The study, conducted in collaboration with researchers at the University of Kentucky, validates Ultrasound AI's proprietary technology that accurately predicts time to delivery using standard ultrasound images.

The AI model, developed and trained using de-identified ultrasound images from a cohort of women who delivered at the University of Kentucky, shows high accuracy in predicting delivery timing. The AI achieved an R² of 0.95 for term births and 0.92 for all births, accurately predicting the number of days until delivery based solely on ultrasound imagery.

Key findings from the study include improved prediction for preterm birth, with the AI's performance increasing from an R² of 0.48 in its first iteration to 0.72 in its fourth. The AI model is robust and generalizable, having analyzed over 2 million ultrasound images across thousands of patients, and performs consistently across all trimesters and patient demographics.

This technology offers a non-invasive, efficient, and scalable tool for improving pregnancy outcomes, particularly in the fight against preterm birth, and can be deployed in both high-resource and resource-limited settings.