PDC30 Chatbot: A Qualitative Study of the Acceptability of a Psychoeducational Resource for Dementia Caregivers (Preprint)

Author:

Cheng Sheung-TakORCID,Ng Peter H. F.ORCID

Abstract

BACKGROUND

Providing ongoing support to the increasing number of caregivers as their needs change in the long-term course of dementia is a serious challenge to any healthcare system. Conversational artificial intelligence (AI) operating 24/7 may help to tackle this problem.

OBJECTIVE

This article describes the development of a generative AI chatbot, called PDC30 Chatbot, and an evaluation of its acceptability in a qualitative study.

METHODS

Divided into two phases, Study One focused on the development of the PDC30 Chatbot using the GPT-4o large language model, with a personality agent to constrain its behavior to providing advice on dementia caregiving based on the Positive Dementia Caregiving in 30 Days Guidebook. PDC30 Chatbot’s responses to 21 common questions were compared with those of another chatbot (called Chatbot-B) using a collection of authoritative sources (World Health Organization iSupport, By Us For Us Guides, and 185 webpages by Alzheimer’s Association, National Institute on Aging, and UK Alzheimer’s Society) as its knowledge base. In Study Two, 10 caregivers used PDC30 Chatbot for two weeks and provided ratings and comments on its acceptability.

RESULTS

Study One showed that the PDC30 Chatbot produced highly context-sensitive advice, which was comparable to, if not better than, those of Chatbot-B. In Study Two, 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.

CONCLUSIONS

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 to caregivers.

CLINICALTRIAL

ClinicalTrials.gov identifier NCT06409455

Publisher

JMIR Publications Inc.

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3