Blog
Notes on safety, governance, and reliability for clinical AI.
Human–AI collaboration in radiology
AI models should complement clinicians rather than replace them. What recent research on human–AI teams in radiology — and our conversations with radiologists — tell us about building an intelligent layer for collaboration.
Nambi AI: An intelligent reliability layer
Hospitals can't scale AI unless they can verify it’s safe, reliable, and useful in real workflows. The next wave of healthcare AI will be won by systems that can assist doctors alongside their workflow rather than in silo.
AI in Mammography: Background and Demo
Background on why radiology is both a promising and failure-prone setting for AI, plus a demo on 945 mammogram cases that surfaced systematic BI‑RADS severity downgrading and clinically meaningful subgroup gaps.