Empowering frontline maternal care with AI-assisted ultrasound
Web page · https://research.google/blog/empowering-frontline-maternal-care-with-ai-assisted-ultrasound
Health & Bioscience
First seen by Oriel on .
AI summary
Google Research evaluated an AI system that estimates gestational age from blind-sweep ultrasounds performed by minimally trained operators, achieving accuracy comparable to expert sonographers across Chicago and Nairobi.
- The system analyzes standardized abdominal scans captured with low-cost, portable ultrasound probes by frontline workers without specialized sonography training.
- Among 385 participants between 16 and 36 weeks, the AI achieved a mean absolute error of 4.18 days versus 4.48 days for expert sonographers.
- The adapted Chicago model achieved 4.10 days’ error, while Nairobi testing achieved 4.27 days without local fine-tuning.
- The study used Clarius C3 hardware and found generalization across clinical settings, patient populations, workflows, and ultrasound equipment.
- Researchers identified operational needs including swappable batteries and confidence estimates that reject poor-quality scans and communicate uncertainty to clinicians.
#medical ai #ultrasound #maternal health #computer vision
Generated by gpt-5.6-sol. Check the original for details.
Aliases
| Source | External ID | URL |
|---|---|---|
| Google Research Blog | https://research.google/blog/empowering-frontline-maternal-care-with-ai-assisted-ultrasound/ | https://research.google/blog/empowering-frontline-maternal-care-with-ai-assisted-ultrasound/ Read discussion |