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

2026-04-28

AI Summary

This study addresses the challenge of integrating older patients’ values into serious illness decision-making in the emergency department (ED), where time pressure and emotional burden often impede meaningful communication. The authors developed and evaluated ED GOAL-AI, the first voice-based conversational agent tailored for older ED patients, which combines a structured interview framework with natural language processing to facilitate brief, focused value discussions. Through participatory design and explicit ethical boundaries, the system achieved high completion rates and strong acceptability among 55 participants, with patients reporting a sense of being heard comparable to interactions with human clinicians. The study also identified critical risks, including AI hallucinations. This work provides the first empirical evidence of the feasibility and potential of AI to support value-concordant serious illness conversations in acute care settings.

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.

Problem

• serious illness conversations
• emergency department
• AI-mediated communication
• patient values
• clinical decision-making

Innovation

• AI-mediated conversation
• serious illness communication
• emergency department
• conversational agent
• values-based care