Skip to main content
SMFM 2025 Pregnancy Meeting Main banner
Final Program


Program Book
Icon Legend
Presentation Icons
Additional registration fee required
Additional registration fee required
CME Credit Offered
CME Credit Offered
Abstract Award
Abstract Award
Poster Icons
Additional registration fee required
Additional registration fee required
Faculty have requested this content not be shared on social media
Faculty have requested this content not be shared on social media
CME Credit Offered
CME Credit Offered
Abstract Award
Abstract Award
Back

Oral Concurrent Session 3 - Ultrasound and Genetics

Oral Concurrent Sessions

Oral Concurrent Session 3 - Ultrasound and Genetics

(34) AI Assistance Enhances Physician Performance in Identifying Congenital Malformations

Thursday, January 30, 2025
2:45 PM – 3:00 PM  
Location: Aurora Ballroom CD, Lobby Level
Objective: Accurate sonographic identification of congenital malformations by interpreting Healthcare Practitioners (HCP) is critical for effective prenatal care. An AI software (under development, not FDA cleared) was trained to detect 10 fetal signs on automatically recognized views within its scope. This study aims to evaluate whether physician performance in identifying malformations improves with the assistance of the AI software versus without.

Study Design: A total of 1453 fetal images were labeled by experts and then reviewed by five physicians with varied profiles (Maternal-Fetal Medicine specialists, Obstetricians/Gynecologists, and General Radiologists). The reviews were conducted in two sessions (with and without the AI software), separated by one week to minimize recall bias. Each provider reviewed a mix of pathological and non-pathological images.

Results: There was a clear improvement for each reviewer and in overall performance - from 40% sensitivity (92% specificity) to 70% (96% specificity) with AI support (Figure 1). When assisted by the AI, physicians refined their reviews to more closely match the AI's output, leading to notable enhancements in performance (Figure 2).

Conclusion:

AI-powered review of fetal images improves physician identification of signs of fetal malformations, highlighting the potential clinical impact of AI software to support more precise diagnosis.