AMIE with real patients before urgent primary care visits: a prospective feasibility study
In a single-arm study at Beth Israel Deaconess Medical Center, 98 patients completed a text conversation with Google's AMIE in the five days before an urgent primary care visit, under live physician supervision; no conversation needed a safety stop under prespecified criteria, supervisors noted one hallucination, and physicians found the transcript helpful for preparation in 33 of the 44 cases where they reviewed it.
- Model
- AMIE (Articulate Medical Intelligence Explorer)
- Field
- Medicine
- Date
- 2026-10-08
- Human collaborators
- Peter G. Brodeur, Alan Karthikesalingam, Adam Rodman
What was found
Adults with a single-complaint urgent appointment talked with AMIE beforehand, and the transcript and a summary went to their physician before the visit. 114 patients were enrolled between April and November 2025. Physician safety supervisors watched every conversation and were trained to intervene on predefined criteria; they intervened to add clinical information in five conversations. Clinical evaluators rated AMIE's conversations favourably in 87% to 100% of cases across 17 criteria, and patients in 48% to 96% across 16. Patients' attitudes towards AI improved after the conversation and stayed higher after their visit. Physicians returned surveys in 60 of 98 cases, read the transcript in 44, and said it might have changed their behaviour in 25. Funded by Alphabet.
Novelty check
Europe PMC, (conversational OR chatbot OR large language model) with prospective and (primary care OR patients OR diagnosis) in titles, 2023 to 7 October 2026: prospective clinic studies of LLM diagnosis exist, for example in vestibular disorders (Journal of Medical Internet Research, August 2026), and so do shadow evaluations, but this search found no earlier prospective study of a patient-facing diagnostic conversational agent in primary care.
Caveats and known objections
Single site, single arm, no comparison group and 98 patients, so it measures feasibility and acceptance, not diagnostic accuracy or outcomes. A physician who could stop it watched every conversation live, so safety was shown under supervision, not unsupervised. Funded by Alphabet with Google co-authors. Autonomy is ai-assisted: AMIE talked to patients on its own, but the physicians made every care decision. Published eight days before this entry was added, with no independent check yet.
Trial registration
That a study was registered, with the outcomes it declared and the date it declared them, so a published endpoint can be checked against the one planned. It does not certify the results, their analysis, or any clinical benefit; registry records are submitted by the sponsor and are not peer reviewed.
Nobody outside the lab has checked this yet.
Reading the primary source closely enough to say whether it supports the claim counts as a check, and you are credited on the entry.
Or on GitHub: submit a check challenge the grade send a correction or send a pull request
Flag this for triage
Signals order the review queue and nothing else. They are never published, and they never move a grade: that takes a citation.
Entry history (1 event)
- AddedEntered the registry graded Peer reviewed and AI-assisted.
Entries are never deleted. A grade that does not hold up is downgraded on the record, with the reason beside it.
Graded peer reviewed for verification and ai-assisted for autonomy. What these mean.
Cite this entry
whataifound.org. (2026). AMIE with real patients before urgent primary care visits: a prospective feasibility study. whataifound.org: A Registry of AI Scientific and Mathematical Discoveries. https://whataifound.org/finding/2026-10-08-amie-primary-care-feasibilityBibTeX
@misc{whataifound-google-2026-feasibility,
title = {AMIE with real patients before urgent primary care visits: a prospective feasibility study},
author = {{whataifound.org}},
year = {2026},
howpublished = {whataifound.org: A Registry of AI Scientific and Mathematical Discoveries},
note = {Result by Google / Beth Israel Deaconess Medical Center. Verification: Peer reviewed. Autonomy: AI-assisted.},
url = {https://whataifound.org/finding/2026-10-08-amie-primary-care-feasibility}
}