Cheng Sheung-Tak, Ng Peter H F
Department of Health and Physical Education, The Education University of Hong Kong, Tai Po, China (Hong Kong).
Department of Computing, Faculty of Computer and Mathematical Sciences, Hong Kong Polytechnic University, Hung Hom, China (Hong Kong).
JMIR Aging. 2025 Jan 6;8:e63715. doi: 10.2196/63715.
Providing ongoing support to the increasing number of caregivers as their needs change in the long-term course of dementia is a severe challenge to any health care system. Conversational artificial intelligence (AI) operating 24/7 may help to tackle this problem.
This study describes the development of a generative AI chatbot-the PDC30 Chatbot-and evaluates its acceptability in a mixed methods study.
The PDC30 Chatbot was developed using the GPT-4o large language model, with a personality agent to constrain its behavior to provide advice on dementia caregiving based on the Positive Dementia Caregiving in 30 Days Guidebook-a laypeople's resource based on a validated training manual for dementia caregivers. The PDC30 Chatbot's responses to 21 common questions were compared with those of ChatGPT and another chatbot (called Chatbot-B) as standards of reference. Chatbot-B was constructed using PDC30 Chatbot's architecture but replaced the latter's knowledge base with a collection of authoritative sources, including the World Health Organization's iSupport, By Us For Us Guides, and 185 web pages or manuals by Alzheimer's Association, National Institute on Aging, and UK Alzheimer's Society. In the next phase, to assess the acceptability of the PDC30 Chatbot, 21 family caregivers used the PDC30 Chatbot for two weeks and provided ratings and comments on its acceptability.
Among the three chatbots, ChatGPT's responses tended to be repetitive and not specific enough. PDC30 Chatbot and Chatbot-B, by virtue of their design, produced highly context-sensitive advice, with the former performing slightly better when the questions conveyed significant psychological distress on the part of the caregiver. In the acceptability study, caregivers found the PDC30 Chatbot highly user-friendly, and its responses quite helpful and easy to understand. They were rather satisfied with it and would strongly recommend it to other caregivers. During the 2-week trial period, the majority used the chatbot more than once per day. Thematic analysis of their written feedback revealed three major themes: helpfulness, accessibility, and improved attitude toward AI.
The PDC30 Chatbot provides quality responses to caregiver questions, which are well-received by caregivers. Conversational AI is a viable approach to improve the support of caregivers.
随着痴呆症病程的发展,照顾者的需求不断变化,为数量日益增加的照顾者提供持续支持对任何医疗保健系统来说都是一项严峻挑战。全天候运行的对话式人工智能(AI)可能有助于解决这一问题。
本研究描述了生成式AI聊天机器人——PDC30聊天机器人的开发过程,并在一项混合方法研究中评估其可接受性。
PDC30聊天机器人是使用GPT-4o大语言模型开发的,带有一个个性代理,以将其行为限制为根据《30天痴呆症护理指南》提供痴呆症护理建议,该指南是基于一份经验证的痴呆症照顾者培训手册编写的面向普通大众的资源。将PDC30聊天机器人对21个常见问题的回答与ChatGPT和另一个聊天机器人(称为Chatbot-B)的回答进行比较,作为参考标准。Chatbot-B采用PDC30聊天机器人的架构构建,但用包括世界卫生组织的iSupport、“我们为自己编写的指南”以及阿尔茨海默病协会、美国国立衰老研究所和英国阿尔茨海默病协会的185个网页或手册在内的权威资料集取代了后者的知识库。在下一阶段,为了评估PDC30聊天机器人的可接受性,21名家庭照顾者使用PDC30聊天机器人两周,并对其可接受性给出评分和评论。
在这三个聊天机器人中,ChatGPT的回答往往重复且不够具体。PDC30聊天机器人和Chatbot-B由于其设计,给出了高度上下文敏感的建议,当问题传达出照顾者有明显心理困扰时,前者表现稍好。在可接受性研究中,照顾者发现PDC30聊天机器人非常用户友好,其回答很有帮助且易于理解。他们对它相当满意,并会强烈推荐给其他照顾者。在为期两周的试验期内,大多数人每天使用聊天机器人不止一次。对他们书面反馈的主题分析揭示了三个主要主题:有用性、可及性和对AI态度的改善。
PDC30聊天机器人对照顾者的问题给出了高质量的回答,受到照顾者的好评。对话式AI是改善对照顾者支持的一种可行方法。