The PDC30 Chatbot—Development of a Psychoeducational Resource on Dementia Caregiving Among Family Caregivers: Mixed Methods Acceptability Study
Bibliographic record
Abstract
BACKGROUND: 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. OBJECTIVE: This study describes the development of a generative AI chatbot-the PDC30 Chatbot-and evaluates its acceptability in a mixed methods study. METHODS: 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. RESULTS: 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. 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 of caregivers.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.002 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one teacher head, not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".