Exploring the Feasibility and Acceptability of AI-Mediated Serious Illness Conversations in the Emergency Department
For emergency department clinicians, this work explores a novel approach to elicit patient values in a time-constrained setting, though it is an early-stage feasibility study with identified risks.
A voice-based conversational agent for serious illness conversations in the emergency department was tested with 55 patients, showing feasibility and acceptability with ratings comparable to clinicians, but also revealed critical failure modes like hallucinated diagnostic statements.
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.