AI-Driven Mental Health Support for Caregivers of Individuals With Alzheimer Disease: Systematic Literature Review and Development of a Conceptual Framework
Bibliographic record
Abstract
BACKGROUND: Caregivers supporting individuals with Alzheimer disease and related dementias (AD/ADRD) frequently encounter prolonged emotional strain, psychological distress, and social isolation, yet their needs are largely overlooked in current technological and clinical interventions. The special routines and obligations of caregivers of individuals with AD/ADRD are frequently not well-suited to the many artificial intelligence-driven (AI-driven) mental health solutions that are currently available. This reveals a critical need for sophisticated, customized solutions created especially to help the mental health of caregivers for patients with AD/ADRD. OBJECTIVE: To address the existing limitations of personalized mental health interventions, we aimed to identify existing literature on personalized mental health interventions using AI for specific purposes and to develop a new framework for the caregivers of individuals with AD/ADRD. METHODS: We followed an iterative approach to design the new framework. First, we did a systematic literature review of current literature to identify data analysis, AI methods, and personalized interventions. Second, we focused on the underlying gaps of this research, and by synthesizing our findings from the review, we proposed a conceptual framework. RESULTS: The systematic literature review identified 73 unique results, and from external sources, we found 3 unique potential papers. Of these, 28 papers were eligible for inclusion, on which we performed our analysis. Based on the findings, we developed a new conceptual framework with 3 special features that are specifically for caregivers of patients with AD/ADRD. The 3 unique features are a personalized daily routine scheduler, which will take both patients with AD/ADRD and caregiver's information to make it personalized, a daily reward system to keep patients motivated, and an educational repository to get the bite-sized knowledge for the lesson of handling patients in an efficient manner and taking care of one's own mental health. CONCLUSIONS: The proposed framework provides a chance for caregivers to receive mental health care, which will be personalized. The framework is developed with more updated methods than existing approaches, with a lack of personalization in this sector. This framework can be implemented with a goal of personalization and explainable approaches and can undergo further iterations to ensure it is appropriate for specific purposes.
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 | 0.049 | 0.124 |
| Meta-epidemiology (narrow) | 0.002 | 0.001 |
| Meta-epidemiology (broad) | 0.007 | 0.010 |
| Bibliometrics | 0.035 | 0.024 |
| Science and technology studies | 0.002 | 0.003 |
| Scholarly communication | 0.007 | 0.009 |
| Open science | 0.004 | 0.006 |
| Research integrity | 0.003 | 0.003 |
| Insufficient payload (model declined to judge) | 0.003 | 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 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".