HealthDial: A No-Code LLM-Assisted Dialogue Authoring Tool for Healthcare Virtual Agents

TL;DR

HealthDial addresses the barrier to creating healthcare virtual agents by combining no-code authoring with LLM-assisted drafting and a deterministic finite-state machine delivery format. The approach enables topic-based session planning and multi-turn conversations derived from health education materials, while preserving safety through human-in-the-loop editing and FSM export. A feasibility study with counselors and students demonstrates convincing usability, trust in AI scaffolding, and high-quality health communication, suggesting HealthDial can scale patient education and training for clinicians. The work lays groundwork for democratized, safe, and scalable deployment of healthcare virtual agents across topics and settings.

Abstract

We introduce HealthDial, a dialogue authoring tool that helps healthcare providers and educators create virtual agents that deliver health education and counseling to patients over multiple conversations. HealthDial leverages large language models (LLMs) to automatically create an initial session-based plan and conversations for each session using text-based patient health education materials as input. Authored dialogue is output in the form of finite state machines for virtual agent delivery so that all content can be validated and no unsafe advice is provided resulting from LLM hallucinations. LLM-drafted dialogue structure and language can be edited by the author in a no-code user interface to ensure validity and optimize clarity and impact. We conducted a feasibility and usability study with counselors and students to test our approach with an authoring task for cancer screening education. Participants used HealthDial and then tested their resulting dialogue by interacting with a 3D-animated virtual agent delivering the dialogue. Through participants' evaluations of the task experience and final dialogues, we show that HealthDial provides a promising first step for counselors to ensure full coverage of their health education materials, while creating understandable and actionable virtual agent dialogue with patients.

Figures (2)

• Figure 1: The visual representation of a dialogue state, as part of the dialogue finite state machine in HealthDial
• Figure 2: HealthDial System Architecture and LLM orchestration