AMIE's Clinical Conversational Abilities in an Urgent Care Setting

Overview

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.

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.