Crypto Briefing • October 8th 2026, 10:37 PM
Google’s AMIE study shows AI can enhance patient-physician relationships
Key Summary
Google's AMIE system, a conversational diagnostic reasoning AI, has shown promising results in a real-world study at Beth Israel Deaconess Medical Center. The system accurately diagnosed patients 90% of the time, with doctors and patients reporting improved preparation for visits and positive attitudes toward AI. The study's findings suggest that AMIE can be a valuable support tool in healthcare, but more research is needed to establish its efficacy and usability in clinical settings.
Please see our real time news feed on our Home Page
Study Overview
Google's AMIE system was tested in a prospective feasibility study at Beth Israel Deaconess Medical Center (BIDMC) from April to November 2025. The study included 100 adult participants who chatted with AMIE via text chat before a primary care visit. Live physician supervisors monitored the sessions and reported zero required safety interventions.Results
Accuracy was measured after an 8-week chart review, which gave doctors time to confirm what patients actually had. The results showed that AMIE accurately diagnosed patients 90% of the time in the top-7 list, 75% of the time in the top-3 list, and 56% of the time in the top-1 list.Physician and Patient Feedback
Primary care physicians received AMIE's transcripts and summaries before seeing their patients. 75% of PCPs reported feeling better prepared for the visit, and nearly 60% indicated that the material could potentially change how they approached the patient's care. Patients responded very positively to AMIE, with many saying their attitudes toward AI improved after the interactions.Background and Future Directions
AMIE was first introduced in 2024 and has been extensively tested in simulated settings. The system has expanded to include multimodal vision capabilities and features for longitudinal disease management. The developers argue that prospective real-world trials are essential to building trust in clinical AI. The next steps include larger prospective trials across more sites and patient populations, studies without real-time physician supervision, and any regulatory pathway toward clinical deployment.#Google#US#Healthcare#AI#MedicalAI