Google Research and Google DeepMind have advanced their research medical AI system, AMIE, to enable real-time clinical video consultations. The system, built on Gemini and Project Astra using a multi-agent architecture, now interprets visual and auditory cues, guides virtual physical exams, and reasons diagnostically in real time. This marks a significant step toward integrating AI into clinical settings, offering a glimpse into the future of health AI. According to the source, the system was tested in a randomized study involving simulated consultations with patient actors and primary care physicians, where it received positive feedback on core clinical competencies. The study highlighted AMIE's ability to perform thorough history-taking, provide accurate diagnostics, and ensure appropriate management and communication.
Patient actors also preferred the video experience over text chat, indicating a potential shift in how consultations are conducted. While AMIE remains a research system and more research is needed before responsible real-world clinical deployment, the results suggest a promising direction for AI in healthcare. The findings were shared on the Google Research blog, marking a milestone in the development of medical AI systems.
Source: googleai
