Optimizing AI-Driven Messaging for Type 2 Diabetes Management: Insights from Patient Preference Elicitation

2026-10-04

AI Summary

This study addresses the mismatch between the communication styles of generative AI conversational agents and patient preferences in diabetes management. By integrating discrete choice experiments, online surveys, human-computer interaction, and natural language processing techniques, this work systematically investigates the communication preferences of patients with type 2 diabetes regarding the uMatter agent. The findings reveal significant preference heterogeneity among patients concerning emoji usage and personified communication styles, while also identifying specific requirements for dynamic, context-aware dialogue. Accordingly, this research proposes a personalized messaging strategy and design framework, providing empirical evidence to optimize AI-driven health conversational systems and enhance user experience.

Abstract

Generative AI (GenAI) allows for improved user experience within conversational agents for diabetes management by supporting dynamic, context-aware conversations. In this study, we elicited patient preferences for the communication style of a GenAI-based conversational agent (uMatter) developed to support diabetes management. We conducted an online survey with 125 individuals with type 2 diabetes. The survey included a discrete choice experiment to evaluate participant preferences for different types of messaging attributes. The survey also elicited participant perceptions and feedback on the messages from uMatter. We found significant preference heterogeneity for the inclusion of emojis within the messages. Additionally, qualitative findings indicated that participants had different desired personas and communication styles for the conversational agent. We propose strategies from recent human-computer interaction and natural language processing research that can be used to design GenAI-based conversational agents that align with the communication preferences of patients.

Problem

• Type 2 Diabetes Management
• Generative AI
• Conversational Agent
• Patient Preference
• Communication Style

Innovation

• Generative AI
• Conversational Agent
• Discrete Choice Experiment
• Patient Preference Elicitation
• Type 2 Diabetes Management