Google's ultrasound AI matched expert accuracy in Kenya with zero fine-tuning
ymatias · x · 2026-10-22
A follow-up to Google Research's JAMA study: tested with Northwestern Medicine and Jacaranda Health in Kenya, the blind sweep ultrasound AI matched expert accuracy with zero local fine-tuning. Context: WHO estimates 250k+ preventable pregnancy-related deaths yearly and two-thirds of people globally lack ultrasound access. Also covered in an "Ask a Scientist" YouTube episode.
Related event: Google's On-Device AI Ultrasound Enables Novice Pregnancy Screening(2 posts)→
More from Research
- LightOn open-sources SlideOn: SAE-based sparse retrieval beats its dense teacher at 174M params — tomaarsen · 2026-10-22
- Harvard physicist says AI could solve fundamental physics in 5 years as accuracy jumps 2% to 35% — AryHHAry · 2026-10-22
- Stanford's Librarian Agents: RL-curated workspaces boost long-context QA by 30+ points — khademinori · 2026-10-22
- Tinker ships StableReinforce to keep off-policy RL runs from suddenly collapsing — simonguozirui · 2026-10-22
- Forward-only pretraining matches backprop: val 3.704 in 2.5 min on 8×H100, no autograd — tensorqt · 2026-10-22
- Wikipedia editors gut mech interp article, citing preprints and blog posts as unusable — Sauers_ · 2026-10-22