Actively Recruiting
Evaluation of an AI Ultrasound Tool for Estimating Fetal Weight in Pregnant Individuals Near Delivery
Led by University of North Carolina, Chapel Hill · Updated on 2026-10-06
1000
Participants Needed
6
Research Sites
N/A
Total Duration
AI-Summary
What This Trial Is About
Researchers are evaluating the accuracy of an AI-enabled ultrasound tool designed to estimate fetal weight in pregnant individuals. This prospective diagnostic study aims to compare AI-generated fetal weight estimates with specialist-performed fetal biometry and actual birth weights to assess the tools performance. The study involves 1,000 pregnant participants expected to deliver within one week of the study procedure, focusing on pregnancies between 24 and 42 weeks of gestation. Participants will undergo two ultrasound assessments during a single visit within one week of delivery. The first consists of standardized sweeps of the gravid abdomen captured as cineloop videos, performed by both specialist and nonspecialist users, which are then analyzed by a deep-learning AI diagnostic tool to estimate fetal weight. The second assessment involves specialist-performed fetal biometry measurements. These two methods will be compared to actual birth weights to evaluate diagnostic accuracy. During the study visit, participants receive the ultrasound procedures as part of the research. Researchers will measure the difference in Mean Absolute Percent Error MAPE between AI estimates and actual birth weights, along with the proportion of estimates within 10% of actual birth weight. The study is conducted by the University of North Carolina, Chapel Hill, and involves no masking or blinding. The total participation involves a single visit shortly before delivery, with data collection focused on comparing diagnostic methods.
CONDITIONS
Brief Title
Prospective Evaluation of an AI Diagnostic Ultrasound Tool for Fetal Weight Estimation
Research Team
K
Katelyn J Rittenhouse, MD
Not the Right Trial for You?
Explore thousands of other clinical trials that might be a better match.
Sign up to get personalized trial recommendations delivered to your inbox.
Already have an account? Log in here