AMIE's Clinical Conversational Abilities in an Urgent Care Setting

• Conditions: Artificial Intelligence (AI); Clinical Reasoning

• Registration Number: NCT06911398
• Lead Sponsor: Beth Israel Deaconess Medical Center

Brief Summary

The purpose of this study is to determine the feasibility of a conversational artificial intelligence (AI) system to have a meaningful clinical conversation with a patient prior to an urgent care visit with their primary care physician. In this study, patients who are seeking an urgent care visit (that is, any type of medical visit with their primary care provider for a new complaint) will first have a conversation with an AI system. This interaction with the AI system will happen less than a week before their visit with their physician, and will be supervised by an independent physician who will interrupt in case there are any concerns about patient safety. After the interaction, a summary of the conversation will be sent to the patient's PCP, who will review prior to the in-person visit.

The researchers will investigate:

* Patient views on the AI system

* PCP views on the AI system

* Overall safety, as measured by the physician safety supervisor

* Quality of clinical conversations, measured by standardized rubrics

* Quality of diagnostic and management plans generated by the AI; these will not be shared with the patient or physician, but will be generated after the fact and compared with the actual diagnosis and management plan.

Detailed Description

This study is a pilot study on the ability of the Articulate Medical Intelligence Explorer's ability to have a clinical conversation with urgent care patients. After recruitment into the study, but prior to seeing their primary care physician (PCP), patients will log in to the AMIE chat interface via a secure web application and share their screen via a secure, HIPAA-compliant video conferencing program. They will then interact with AMIE, having a clinical conversation. A physician safety supervisor will be on the call the entire time and will view the chat as it happens. This doctor will interrupt the chat if there are any potentially harmful interactions. At the end of the call, the safety supervisor will discuss with the patient and correct any errors, hallucinations, or problems with the AI. The patient's PCP will receive both a summary and a transcript of the chat prior to their appointment. The patient will then proceed to their urgent care appointment as previously scheduled. Four weeks after the visit, the researchers will perform a chart review to extract a "ground truth" diagnosis from the urgent care visit, if possible. As this is a pilot study, the primary endpoint will be recruitment; the target is between 100 to 200 patients and the study will continue until saturation of different diagnoses has been reached.

Study Timeline

• Study First Submitted: 2025-03-09
• Study First Submitted QC: 2025-03-28
• Study Start: 2025-04-02
• Study First Posted: 2025-04-04
• Status Verified: 2025-05
• Last Update Submitted: 2025-05-20
• Last Update Posted: 2025-05-21
• Primary Completion: 2025-06-30
• Study Completion: 2025-12-31

Recruitment & Eligibility

• Status: ENROLLING_BY_INVITATION
• Sex: All
• Target Recruitment: 200

Inclusion Criteria

• Age > 18
• English included as a primary language in the electronic health record
• Patient is seeking episodic (urgent) care at HCA

Exclusion Criteria

• Age < 18
• English not listed as a primary language in the electronic health record
• Visit reason is related to pregnancy
• Visit reason is a psychiatric concern
• Visit is to establish care, or for follow-up care

Study & Design

• Study Type: OBSERVATIONAL
• Study Design: Not specified

Primary Outcome Measures

Name	Time	Method
Chat terminations	Day 1	The researchers will collect the number of interruptions by the safety supervisor in response to safety concerns. There are four pre-specified interruption criteria; the researchers will connect the total number in each category, as well as a qualitative description of the type of error.
Patient-centered evaluation of clinical dialogue	Day 3	The researchers will use the General Medical Council Patient Questionnaire (GMCPQ) standardized rubric to rate the quality of clinical dialogue.
Clinical skills-based assessment of clinical dialogue	Day 3	The researchers will use the Practical Assessment of Clinical Examination Skills (PACES) standardized rubric to rate the quality of clinical dialogue.
Communication skills evaluation of clinical dialogue	Day 3	The researchers will use the Patient-Centered Communication Best Practice (PCCBP) standardized rubric to rate the quality of clinical dialogue.
Patient satisfaction pre-AMIE encounter	Day 1	Patients will receive a pre-AMIE encounter questionnaire.
Patient satisfaction post-AMIE encounter	Day 1	Patients will receive a post-AMIE encounter questionnaire.
PCP satisfaction	Day 3	The researchers will collect a post-encounter questionnaire from the patient's PCP, asking about views on AI in healthcare and how AMIE interaction may have changed the in-person visit.
Patient satisfaction post-PCP encounter	Day 3	Patients will receive a post-PCP encounter questionnaire.

Secondary Outcome Measures

Name	Time	Method
Semi-structured interviews of patients	Up to 8 weeks	The researchers will perform semi-structured interviews of select patients participating in the study.
Diagnostic accuracy	Up to 4 weeks	The researchers will compare AMIE's differential diagnosis to the final diagnosis.
Management plan quality	Up to 4 weeks	The researchers will compare AMIE's management plan to the final management plan using the Management Reasoning Essential Key Features (MXEKF) rubric.
Semi-structured interviews of PCPs	Up to 8 weeks	The researchers will complete semi-structured interviews with all of the PCPs participating in the study.

Trial Locations

Locations (1)

Beth Israel Deaconess Medical Center; 🇺🇸 Boston, Massachusetts, United States