Conversational Agents for Older Adults' Health: A Systematic Literature Review

2025-03-29

AI Summary

Conversational agents (CAs) exhibit limited efficacy in geriatric health applications due to persistent challenges in user acceptance and interaction design. Method: We conducted a systematic literature review (SLR), synthesizing empirical findings from 72 studies to analyze CA deployment in aging populations from a human–computer interaction (HCI) perspective. Contribution/Results: The review identifies three root causes of low elderly acceptance—compromised autonomy, privacy concerns, and unnatural interaction—and distills four core requirements: natural-language interaction, multimodal integration, explainability, and personalized, fully user-controllable interfaces. Based on these insights, we propose a novel HCI-oriented interaction design framework specifically tailored for geriatric health CAs. This framework advances theoretical understanding of age-inclusive AI design and provides actionable guidelines to enhance technological accessibility, trustworthiness, and adoption among older adults.

Technology Category

• Humans and AI: Intelligent User Interfaces
• Cognitive Modeling & Cognitive Systems: Social Cognition And Interaction
• Intelligent Robots: Human-Robot Interaction

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

There has been vast literature that studies Conversational Agents (CAs) in facilitating older adults' health. The vast and diverse studies warrants a comprehensive review that concludes the main findings and proposes research directions for future studies, while few literature review did it from human-computer interaction (HCI) perspective. In this study, we present a survey of existing studies on CAs for older adults' health. Through a systematic review of 72 papers, this work reviewed previously studied older adults' characteristics and analyzed participants' experiences and expectations of CAs for health. We found that (1) Past research has an increasing interest on chatbots and voice assistants and applied CA as multiple roles in older adults' health. (2) Older adults mainly showed low acceptance CAs for health due to various reasons, such as unstable effects, harm to independence, and privacy concerns. (3) Older adults expect CAs to be able to support multiple functions, to communicate using natural language, to be personalized, and to allow users full control. We also discuss the implications based on the findings.

Problem

• Reviewing Conversational Agents' role in older adults' health
• Analyzing older adults' acceptance and concerns about health CAs
• Identifying expected CA features for older adults' health support

Innovation

• Surveyed 72 papers on CAs for elderly health
• Analyzed older adults' CA acceptance and expectations
• Proposed multi-functional, personalized CA solutions