Empowering Informal Caregivers of Persons With Early-Stage Dementia by Large Language Models: Mixed Methods Evaluation
Bibliographic record
Abstract
Background: Acquiring relevant knowledge and support is essential for informal caregivers of persons with early-stage dementia, including awareness, access, and use of comprehensive resources for both persons with dementia and caregiver support. With appropriate strategies and early-stage support, informal caregivers can play a vital role in enhancing the well-being of persons with dementia and potentially slowing their progression. While large language models (LLMs) can provide easy access to caregiving knowledge, the risks, perceived challenges, and ways to improve LLM-generated responses in practice remain underexplored. Objective: In this study, we aim to (1) examine the risks and perceived challenges of using a baseline ChatGPT-4o, an internet-accessible artificial intelligence model, for dementia caregiving support and (2) understand how an enhanced version of ChatGPT-4o, equipped with up-to-date dementia caregiving knowledge, can mitigate these risks and challenges. Methods: We compiled 32 representative questions from informal caregivers seeking guidance on early-stage dementia. We developed two ChatGPT-4o conditions: C1, the publicly available baseline model, and C2, an experimental version enhanced through prompt engineering and grounded in a conceptual framework-drawn from health science and gerontology literature-to empower caregivers of individuals with early-stage dementia. Using these conditions, we generated 64 responses (32 pairs) to the questions. Twelve experts evaluated them with validated tools assessing accuracy, reasoning, clarity, usefulness, trust, satisfaction, safety, harm, and relevance. A Mann-Whitney U test compared the conditions. After the survey, we conducted interviews to explore experts' perceived differences, remaining challenges, and design opportunities. Interviews were transcribed and analyzed using descriptive thematic analysis. Results: Responses in C2 showed significant improvements in 3 criteria-actionability, relevance, and perceived satisfaction-compared to C1. However, no significant differences were found in the remaining 5 criteria: response accuracy, the model's ability to understand the question, intelligibility, trustworthiness, response safety, and perceived harm. Qualitative analysis of interviews revealed two key insights: (1) differences between baseline and experimental responses and (2) possible reasons for these differences. Twelve experts evaluated wordiness, detail, empathy, satisfaction, accuracy, relevance, and bias. Both models were considered somewhat verbose, but the experimental model's responses were viewed as more detailed, relevant, and actionable. Accuracy appeared similar across models, yet participants reported greater satisfaction with the experimental model's outputs. Conclusions: Results indicate that both conditions generated responses perceived as reasonable and intelligible. However, the experimental model offered more relevant, practical guidance on caregiving needs, providing specific information aligned with the 32 testing questions and actionable recommendations. This led to higher perceived satisfaction compared to the baseline model.
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 machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.079 | 0.100 |
| Meta-epidemiology (narrow) | 0.002 | 0.001 |
| Meta-epidemiology (broad) | 0.002 | 0.003 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.002 | 0.001 |
| Scholarly communication | 0.002 | 0.002 |
| Open science | 0.003 | 0.003 |
| Research integrity | 0.002 | 0.002 |
| Insufficient payload (model declined to judge) | 0.005 | 0.001 |
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 source (direct Gemma or distilled Codex), 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".