Voice Assistants for Health Self-Management: Designing for and with Older Adults

2024-09-23

arXiv.org

AI Summary

Older adults often exhibit weak health literacy and poor medication adherence, hindering effective self-management of chronic conditions. Method: This study proposes a voice assistant (VA) design framework centered on dual objectives—enhancing health awareness and improving medication adherence—developed through a five-stage participatory design process (e.g., in-home interviews, co-design workshops, and in-situ home trials). Integrating large language models (LLMs), context-aware modeling, and adaptive spoken dialogue technologies, we built a high-fidelity, deployable, older-adult-friendly VA prototype supporting post-consultation summary interpretation and personalized medication reminders. Contribution/Results: Empirical evaluation demonstrated significant improvements in older users’ health information comprehension and medication adherence. The study further distilled seven age-inclusive design principles and a comprehensive checklist of VA-specific gerontechnology features, establishing both a theoretical foundation and an actionable implementation paradigm for intelligent, age-appropriate health interaction systems.

Technology Category

• Humans and AI: Intelligent User Interfaces
• Cognitive Modeling & Cognitive Systems: Adaptive Behavior
• Data Mining & Knowledge Management: Conversational Systems for Recommendation & Retrieval

Application Category

• User Modeling, Personalization and Recommendation: User modeling and simulation for interactive and conversational systems
• Search and Retrieval-Augmented AI: Assisted, interactive, and conversational search
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions

Abstract

Supporting older adults in health self-management is crucial for promoting independent aging, particularly given the growing strain on healthcare systems. While voice assistants (VAs) hold the potential to support aging in place, they often lack tailored assistance and present usability challenges. We addressed these issues through a five-stage design process with older adults to develop a personal health assistant. Starting with in-home interviews (N = 17), we identified two primary challenges in older adult's health self-management: health awareness and medical adherence. To address these challenges, we developed a high-fidelity LLM-powered VA prototype to debrief doctor's after-visit summary and generate tailored medication reminders. We refined our prototype with feedback from co-design workshops (N = 10) and validated its usability through in-home studies (N = 5). Our work highlights key design features for personal health assistants and provides broader insights into desirable VA characteristics, including personalization, adapting to user context, and respect for user autonomy.

Problem

• Designing voice assistants for older adults' health self-management.
• Addressing health awareness and medical adherence challenges.
• Developing personalized, context-aware, and user-respectful VA features.

Innovation

• High-fidelity LLM-powered voice assistant prototype
• Tailored medication reminders and health summaries
• Co-design workshops for usability refinement