Designing a Multimodal and Culturally Relevant Alzheimer Disease and Related Dementia Generative Artificial Intelligence Tool for Black American Informal Caregivers: Cognitive Walk-Through Usability Study
Bibliographic record
Abstract
BACKGROUND: Many members of Black American communities, faced with the high prevalence of Alzheimer disease and related dementias (ADRD) within their demographic, find themselves taking on the role of informal caregivers. Despite being the primary individuals responsible for the care of individuals with ADRD, these caregivers often lack sufficient knowledge about ADRD-related health literacy and feel ill-prepared for their caregiving responsibilities. Generative AI has become a new promising technological innovation in the health care domain, particularly for improving health literacy; however, some generative AI developments might lead to increased bias and potential harm toward Black American communities. Therefore, rigorous development of generative AI tools to support the Black American community is needed. OBJECTIVE: The goal of this study is to test Lola, a multimodal mobile app, which, by relying on generative AI, facilitates access to ADRD-related health information by enabling speech and text as inputs and providing auditory, textual, and visual outputs. METHODS: To test our mobile app, we used the cognitive walk-through methodology, and we recruited 15 informal ADRD caregivers who were older than 50 years and part of the Black American community living within the region. We asked them to perform 3 tasks on the mobile app (ie, searching for an article on brain health, searching for local events, and finally, searching for opportunities to participate in scientific research in their area), then we recorded their opinions and impressions. The main aspects to be evaluated were the mobile app's usability, accessibility, cultural relevance, and adoption. RESULTS: Our findings highlight the users' need for a system that enables interaction with different modalities, the need for a system that can provide personalized and culturally and contextually relevant information, and the role of community and physical spaces in increasing the use of Lola. CONCLUSIONS: Our study shows that, when designing for Black American older adults, a multimodal interaction with the generative AI system can allow individuals to choose their own interaction way and style based upon their interaction preferences and external constraints. This flexibility of interaction modes can guarantee an inclusive and engaging generative AI experience.
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 | 0.001 | 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 | 0.001 | 0.002 |
| Scholarly communication | 0.000 | 0.001 |
| 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".