Researchers have created an AI model using ultrasound to accurately forecast expectant mothers’ delivery timelines.
Key Details
- 1AI software developed by Ultrasound AI predicts time to delivery using ultrasound images.
- 2Model trained on over 2 million de-identified images from pregnant women.
- 3Validated on data from women delivering at the University of Kentucky (2017-2021).
- 4System estimates days until delivery and predicts likelihood of preterm birth.
- 5Described as a milestone with potential to improve prenatal care, especially in low-resource settings.
Why It Matters
Accurate prediction of delivery timing can enhance patient counseling, risk stratification, and resource allocation in maternal-fetal medicine. This represents a significant advance for imaging AI in obstetrics, contributing to better outcomes in women's health.
Source
Health Imaging
Related News
•Health Imaging
AI as Second Reader Surpasses Radiologists in Breast Cancer Screening
AI used as a second reader on mammograms improves cancer detection rates compared to radiologists alone.
•AuntMinnie
ChatGPT-4 Turbo Powers Postdeployment Monitoring of ICH Detection AI
Researchers found ChatGPT-4 Turbo could efficiently monitor the performance of Aidoc's ICH detection AI across real-world radiology practices.
•Health Imaging
Can ChatGPT Help Monitor AI Drift in Radiology?
Researchers explore using ChatGPT to monitor AI model drift for radiology applications.