
Researchers validated an AI tool that predicts preterm birth from routine prenatal ultrasound scans with high accuracy.
Key Details
- 1Retrospective study used 2,550 pregnancy ultrasound scans from four public hospitals in Chile.
- 2AI tool analyzed standard prenatal ultrasounds to predict preterm delivery risk.
- 3In cases of preterm birth, AI estimated delivery within two weeks in 71% of cases.
- 4At 23-week scan, AI predicted early delivery with 86% accuracy using only image data.
- 5The system functioned without modification and did not affect clinical decisions in the study.
Why It Matters
This research highlights the potential for AI to extract more clinically relevant information from routine ultrasound images than is currently used, potentially enabling earlier and more accurate risk stratification for preterm birth. Such capabilities could inform future prenatal care and intervention strategies.

Source
Radiology Business
Related News

•AuntMinnie
Deep Learning PET Biomarkers Outperform Clinical Tools in Prostate Cancer Survival Prediction
Deep learning-derived PET biomarkers more accurately predict metastatic prostate cancer survival than standard clinical risk models.

•AuntMinnie
Multinational AI Model Flags Osteoporosis on Chest X-rays
AI can opportunistically detect osteoporosis from chest x-rays across diverse international populations.

•AuntMinnie
Two-Stage LLM Pipeline Boosts Patient-Friendly Radiology Reports
A two-stage LLM process significantly improves the readability and accuracy of radiology reports for patients.