Artificial Intelligence for Detecting Fetal Orofacial Clefts and Advancing Medical Education
This research addresses the challenge of accurate prenatal detection of rare fetal orofacial clefts for medical professionals, offering a scalable solution to improve diagnosis and specialist training, especially where experienced radiologists are scarce.
This paper presents an AI system trained on over 45,000 ultrasound images to detect fetal orofacial clefts, achieving over 93% sensitivity and 95% specificity, comparable to senior radiologists. The system also improved junior radiologists' sensitivity by more than 6% when used as a copilot and accelerated expertise development in a pilot study.
Orofacial clefts are among the most common congenital craniofacial abnormalities, yet accurate prenatal detection remains challenging due to the scarcity of experienced specialists and the relative rarity of the condition. Early and reliable diagnosis is essential to enable timely clinical intervention and reduce associated morbidity. Here we show that an artificial intelligence system, trained on over 45,139 ultrasound images from 9,215 fetuses across 22 hospitals, can diagnose fetal orofacial clefts with sensitivity and specificity exceeding 93% and 95% respectively, matching the performance of senior radiologists and substantially outperforming junior radiologists. When used as a medical copilot, the system raises junior radiologists' sensitivity by more than 6%. Beyond direct diagnostic assistance, the system also accelerates the development of clinical expertise. A pilot study involving 24 radiologists and trainees demonstrated that the model can improve the expertise development for rare conditions. This dual-purpose approach offers a scalable solution for improving both diagnostic accuracy and specialist training in settings where experienced radiologists are scarce.