Google’s AMIE research system shows real-time clinical video consultation capabilities in simulated study
AMIE, built on Gemini and Project Astra, interpreted visual and auditory cues and outperformed text chat in user preference during a randomized simulated consultation study.
1 source · cross-referenced
- AMIE is a research medical AI system developed by Google Research and Google DeepMind.
AMIE, a research medical AI system from Google Research and Google DeepMind, demonstrated real-time clinical video consultation capabilities in a first-of-its-kind study. The system interprets visual and auditory cues, guides virtual physical exams, and reasons diagnostically in real time.
Built on Gemini and Project Astra using a multi-agent architecture, AMIE participated in a randomized study with simulated consultations involving patient actors and primary care physicians. Clinical evaluators assessed AMIE favorably across core clinical competencies, including history-taking thoroughness, diagnostic accuracy, management appropriateness, and communication quality.
Patient actors also expressed a preference for the video consultation experience over text chat when interacting with AMIE.
The researchers emphasize that AMIE remains a research system and additional research is required before any responsible real-world clinical deployment.
- Aug 11, 2026 · Simon Willison — everything
Meta releases Muse Glimmer, a 30B open-weight vision model optimized for agentic tasks
Trust78 - Aug 10, 2026 · MIT Technology Review — AI
Startups pursue alternatives to transformer-based LLMs amid efficiency and capability limits
Trust72 - Aug 9, 2026 · Simon Willison — everything
Auto mode becomes default in Claude Code for Pro, Max, and Team plans
Trust78