Prenatal ultrasounds have long been a vital part of pregnancy care, but they can miss a significant number of fetal abnormalities. A newly approved artificial intelligence tool in the United States aims to change that by helping doctors spot potential problems earlier and more reliably.
Real-Time Support in the Scan Room
The US Food and Drug Administration has cleared an AI-powered software developed by American start-up BioticsAI for use in clinical settings. The technology works alongside standard ultrasound machines, analysing images as they are taken and alerting clinicians to possible concerns during the scan itself.
Ultrasound scans are used throughout pregnancy to monitor how a baby is developing. While they can identify some issues affecting organs or limbs, many abnormalities are still overlooked. The new tool is designed to act as a second set of eyes, supporting clinicians as they assess each image.
How the Technology Works
As soon as an ultrasound image is captured, the software reviews it instantly. It checks image quality, suggests adjustments for clearer views and ensures that all essential parts of the fetus are visible, flagging anything that appears to be missing.
By drawing on patterns learned from large global datasets, the AI can highlight signs of potential abnormalities, including heart or limb defects. Once the scan is complete, it produces a summary report for the doctor, which developers say can reduce documentation time by around eight minutes per patient.
FDA clearance confirms the software meets required safety and performance standards and can be integrated into existing healthcare systems as a regulated medical device.
Why Better Detection Matters
According to the European Commission, major congenital anomalies occur in nearly 24 out of every 10,000 births across Europe. Research by Cochrane, which reviewed data from more than seven million pregnancies, shows the limits of traditional screening.
An early ultrasound between 11 and 14 weeks detects only 38 percent of birth defects, while a mid-pregnancy scan at 18 to 24 weeks identifies about 51 percent. Using both scans together improves detection to 84 percent, but gaps remain.
Europe is also seeing similar innovations. French companies Diagnoly and Sonio Detect have received approval for AI-assisted ultrasound tools that automatically identify fetal structures and heart issues, highlighting a growing global shift toward smarter, more reliable prenatal screening.
