Towards Automated Pain Assessment using Embodied Conversational Agents

Abstract

Narrative accounts are the ultimate authoritative source for pain assessment, and face-to-face encounters provide a rich context in which nonverbal conversational behavior can be used to enrich the detail in these descriptions. Embodied Conversational Agents - animated characters that simulate face-to-face conversation - can provide a medium for automated pain assessment in which multimodal pain narratives are elicited, clarified, and grounded. These agents can also use facial displays and nonverbal behavior to provide simulated empathic responses to help patients feel understood. We describe work towards a conversational agent that elicits various aspects of a pain experience, followed by an empathic summary. Our preliminary findings indicate that individuals are comfortable reporting their pain experiences to the agent, and are largely satisfied with this assessment methodology. We also find evidence that patients prefer the conversational empathic summary to standard self-report measures.