Open benchmarks for maternal health AI enable more robust, transparent, and equitable evaluation of tools that can impact care quality for women and children.
Medical question-answering benchmarks rarely cover the maternal, neonatal, child, and reproductive-health questions a nurse-midwife asks, and, to our knowledge, no public chunk-level relevance benchmark exists for…
55 arXiv · 2026-06-28
Deploying robust, offline AI tools for midwives in low-resource settings can directly improve maternal and newborn outcomes, bridging gaps in care.
Maternal and newborn mortality remain among the highest in sub-Saharan Africa, where midwifery care is often delivered by nurses who lack midwifery training to international standards, and consulting authoritative…
39 arXiv · 2026-06-28
Advances in annotation-efficient ultrasound AI can make fetal monitoring more accessible and accurate, especially in resource-limited settings.
Maternal-fetal US is the primary imaging modality for monitoring fetal development, yet accurate automated segmentation remains challenging due to the scarcity of pixel-level annotations. To address this issue, we…
35 arXiv · 2026-06-24