Exploring the Potential of Virtual Reality and Artificial Intelligence as Tools to Design, Develop and Deliver Psychotherapeutic Intervention for Family Caregivers of Persons Living with Dementia
Bibliographic record
Abstract
Our presentation explores the potential of Virtual Reality (VR) and Artificial Intelligence (AI) as tools used in designing, developing and delivering psychotherapeutic interventions for family caregivers (CGs) of persons living with dementia (PwD). Family CGs experience significant emotional burden and strain from unresolved relational issues, which are compounded by the evolving nature of their caregiving roles. While traditional psychotherapeutic interventions have proven effective in reducing CGs distress while enhancing their coping strategies and resilience (Sadavoy et al., 2022), technology-based solutions may augment these efforts. VR, particularly through high-fidelity environments and scripted avatar dialogues, allows CGs to engage in simulated caregiving scenarios, and to practice communication skills and emotional regulation, and deepen their understanding of PwD's experiences, allowing CGs to build empathy. For example, VR-SIM Carers www.vrsimcarers.ca, a simulation-based experiential learning platform in VR, allows CGs to "walk through" challenging caregiving scenarios by selecting their responses, while receiving feedback from a virtual clinician and a virtual simulated-PwD. This safe, self-paced learning environment offers CGs a space to acknowledge and process their emotions, and to practice communication and coping strategies. AI-powered tools e.g. real-time AI responses may also be integrated into VR, to enhance accessibility, recommend personalized strategies tailored to CGs' situations. Despite aforementioned advances and benefits, the use of technology in psychotherapeutic interventions raises concerns, particularly regarding the emotional complexities of the CG-PwD relationship. Long-standing relational dynamics, including unresolved grief or resentment, can impact caregiving interactions. While AI shows promise in providing compassionate responses (Ovsyannikova et al, 2025), it may fall short of addressing the emotional nuanaces arising from these relationships. Particularly, its limited ability to interpret non-verbal cues and complex emotional nuances limits its effectiveness in deeply relational contexts. While technological innovations hold promise for enhancing the mental and emotional well-being of dementia caregivers, their design must be sensitive to the unique psychological and relational complexities inherent in caregiving. A collaborative, cross-sector approach that integrates the lived experiences of CGs is essential to ensure these tools are accessible, feasible, and culturally sensitive to the diverse populations they aim to support (Chiu & Saragosa, 2024).
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 | 0.005 | 0.008 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.001 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.001 | 0.002 |
| Scholarly communication | 0.003 | 0.002 |
| Open science | 0.001 | 0.002 |
| Research integrity | 0.001 | 0.001 |
| 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".