Key result
AMIE conversational AI achieves zero safety stops and up to ~100% favorable clinician quality ratings.
Why the study?
Does a patient-facing conversational AI system (AMIE) demonstrate conversation safety, quality, and user acceptance in adults scheduled for a single-complaint urgent primary care appointment?
Does a patient-facing conversational AI system (AMIE) demonstrate conversation safety, quality, and user acceptance in adults scheduled for a single-complaint urgent primary care appointment?
This prospective feasibility study demonstrates that a patient-facing conversational AI system can safely and effectively gather clinical information prior to urgent primary care visits with high user and evaluator acceptance.
Supports safety and acceptability of conversational AI for pre-visit history-taking in urgent primary care; leaves open effects on outcomes and workflow integration.
BACKGROUND: Artificial intelligence (AI)-based systems show promise for assisting primary care providers (PCPs) with patient care. We aimed to evaluate the safety and quality of clinical conversations of a patient-facing conversational AI system, which engaged in real-world urgent primary care appointments. METHODS: In this prospective, single-centre, single-arm feasibility study, English-speaking patients aged at least 18 years interacted with the Articulate Medical Intelligence Explorer (AMIE) up to 5 days before a single-complaint urgent primary care appointment. Physician safety supervisors monitored all interactions and were trained to intervene on the basis of predefined safety criteria. AMIE transcripts and summaries were shared with PCPs before the visit. Primary outcomes were the number of supervised conversation safety stops, AMIE's conversation quality assessed by clinical evaluators, and patient and PCP experiences per surveys. This study is registered with ClinicalTrials.gov (NCT06911398). FINDINGS: From April to November, 2025, 114 patients were enrolled with 98 completing both the AMIE interaction and the PCP appointment. Zero conversation safety stops were required on the basis of prespecified criteria. Safety supervisors noted one hallucination and added clinical information in five interactions. AMIE's conversations were rated favourably in 87-100% of cases (17 criteria) by clinical evaluators, and 48-96% (16 criteria) by patients. Patient attitudes towards AI improved after interacting with AMIE and remained elevated after the patient's visit with their physician. PCPs completed post-surveys in 60 of 98 cases, including 44 cases in which they reviewed the AMIE transcript before the visit. PCPs found AMIE helpful for visit preparation in 33 of 44 cases and reported that it might have changed their behaviour in 25 of 44 cases. INTERPRETATION: Although further research is needed, this study shows the initial feasibility of conversational AI in a real-world setting-assessed via conversation safety and quality, as well as user acceptance-and represents a crucial step towards clinical translation. FUNDING: Alphabet.
No takes yet. Share an insight, caveat, or question.
Brodeur et al. (2026) studied Single-complaint urgent primary care (n=114). Articulate Medical Intelligence Explorer (AMIE) conversational AI system was evaluated on Number of supervised conversation safety stops, AMIE's conversation quality assessed by clinical evaluators, and patient and PCP experiences per surveys. The AMIE conversational AI system required 0 safety stops across 98 primary care consultations and achieved 87-100% favorable quality ratings from clinical evaluators.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: