BRIGHT EVIDENCE PACK / Emerging
Google’s AMIE medical AI interviewed real patients before their appointments
A real-patient study of Google’s AMIE found useful pre-visit conversations under physician supervision. Here’s what the results mean for primary care.
Canonical Bright record · JSON evidence pack · Key-facts embed
Dates and assessment
- Source published
- 2026-10-08
- Bright published
- 2026-10-10
- Substantive update
- 2026-10-10
- Evidence state
- Emerging
- Independent verification
- Not established by this source review
- Last source review
- 2026-10-10
The claim in context
The human problem
Clinicians need a clear account of symptoms and history before deciding how to investigate and care for a patient.
The prior constraint
Patients and clinicians have limited appointment time to establish and clarify the patient’s story.
AI’s actual role
AMIE conducted a pre-visit text conversation under live physician supervision and produced a transcript and summary for the treating clinician.
The documented result
In 44 cases where clinicians reviewed the chatbot’s output before seeing a patient, 33 said it helped them prepare for the appointment.
Why it may matter
A supervised pre-visit conversation could help the patient’s account reach their clinician in a useful form. Comparative evidence is still needed to establish clinical benefit.
Limitations
- This was a single-center, single-arm feasibility study, without a usual-care control group.
- The present findings capture clinicians’ impressions; they do not establish a measured reduction in workload or improvement in health outcomes.
- Eligibility required English, an existing relationship with the clinic and suitable computer access; pregnancy and mental-health chief complaints were excluded.
- No completed conversation met the study’s predefined criteria for a safety stop. However, supervisors noted one hallucination and added clinical information in five interactions.
- These findings concern rated outputs under different information conditions; they cannot establish clinical interchangeability.
Original evidence
- A prospective clinical feasibility study of a conversational diagnostic AI in an ambulatory primary care clinic · Google publication record and final Lancet abstract · paper
- BIDMC research shows safety, quality of AI in primary care · October 9, 2026 · institution
- Exploring conversational diagnostic AI in a real-world clinical study · Google Research, updated October 8, 2026 · institution
- AMIE’s clinical feasibility study published in The Lancet · Google, October 8, 2026 · institution
- Prospective clinical feasibility study · March 2026 preprint, version 3 · paper
Attribution
Credit Bright AI Future and link the canonical Bright record.
- Link to the canonical Bright record.
- Keep material limitations with the claim they qualify.
- Link to the original evidence when repeating a substantive claim.
- Do not describe a source check or organization-reported result as independent verification.
Linked source material, quotations, trademarks and media remain subject to their owners’ terms. No reuse right is granted for third-party media.