Exploring the Feasibility and Acceptability of AI-Mediated Serious Illness Conversations in the Emergency Department

TL;DR

This study evaluates ED GOAL-AI, a voice-based AI tool for serious illness conversations with older adults, finding it feasible and acceptable but highlighting ethical risks and the need for careful design.

Contribution

Introduces a novel AI-mediated approach for structured values discussions in emergency settings, demonstrating initial feasibility and acceptability.

Findings

Most participants completed the conversation and felt heard.

Ratings of feeling understood were comparable to clinicians.

Critical failure modes included hallucinated diagnostic statements.

Abstract

Serious illness conversations (SICs) align care with patients' values, goals, and preferences, yet they rarely occur in emergency departments (EDs), where time constraints and emotional burden often leave clinicians making high-stakes decisions without documented insight into what matters most to patients. We present a case study of ED GOAL-AI, a voice-based conversational agent for brief, structured values discussions with older adults in the ED, evaluated with 55 patients for feasibility and acceptability. Most participants completed the conversation and reported the interaction as acceptable and feasible, with ratings of feeling heard and understood comparable to clinicians. However, we also observed critical failure modes, including boundary violations such as hallucinated diagnostic statements, highlighting ethical and emotional risks. This work points to early promise for AI-mediated SICs while underscoring the need for careful boundary setting and participatory design before broader deployment.