Trustworthy Embodied Conversational Agents for Healthcare. A Design Exploration of Embodied Conversational Agents for Periconception at Erasmus MC
Authors
This paper explores the potential implications of embodied conversational agents (ECAs) in healthcare, focusing on the impact of appearance and conversation style on trustworthiness. We conducted a Research through Design investigation of ECAs for supporting women during the periconception period and in pregnancy. The paper presents the results of a Wizard of Oz study in which two alternative prototypes, a chatbot, and an ECA, were tested in a tertiary hospital by 25 participants. Reflecting on the results we suggest that limited patients' trust in ECAs maybe be beneficial for achieving trustworthy use of these agents in the healthcare context.
Research Questions / Practical Problems
Question signals indexed for this paper.
Research Questions
3- How can embodied conversational agents (ECAs) be designed to foster patient trust during the periconception period (before and after pregnancy)?Category: Medical AI Explanation, Trust, and RelianceSimilar questionsarrow_forward
- How do ECA appearance (e.g., cartoon-like design) and medical-context referential conversational style affect patient trust?Category: Medical AI Explanation, Trust, and RelianceSimilar questionsarrow_forward
- How can appropriate rather than excessive or insufficient patient trust in ECAs be achieved in healthcare settings?Category: Medical AI Explanation, Trust, and RelianceSimilar questionsarrow_forward
Practical Problems
1- Patients have limited trust in healthcare conversational agents, hindering their clinical adoption.Category: Medical AI Explanation, Trust, and RelianceSimilar questionsarrow_forward
- 60%
Scaffolded Turns and Logical Conversations: Designing Humanized LLM-Powered Conversational Agents for Hospital Admission Interviews
CHI '25· Conversational Chatbots +1
- 60%
Mining Evidence about Your Symptoms: Mitigating Availability Bias in Online Self-Diagnosis
CHI '25· Conversational Chatbots +1
Based on Jaccard similarity of research subtopics & professions (≥60%)