Multi-modal virtual reminiscence therapy with an AI avatar for older adults with Alzheimer's and related dementias
Multi-modal Large Language Model-Empowered Talk Therapy for Older Adults With ADRD
This study will test whether a smart virtual reminiscence program with an interactive avatar can reduce behavioral and psychological symptoms in older adults with mild Alzheimer's or related dementias.
Quick facts
| Phase | Not applicable |
|---|---|
| Study type | Interventional |
| Enrollment | 60 (estimated) |
| Ages | 65 Years and up |
| Sex | All |
| Sponsor | Indiana University Academic / other |
| Locations | 1 site (Indianapolis, Indiana) |
| Trial ID | NCT07499570 on ClinicalTrials.gov |
What this trial studies
Patient–caregiver dyads are randomized to receive Smart Virtual Reminiscence (SVR) therapy delivered by a multi-modal avatar or an attention control of listening to music. SVR is a computer-accessible program that uses large language model–driven speech understanding, avatar nonverbal cues, and automatically assembled personal reminiscence materials (photos, music, videos) so a human facilitator is not required. Sessions can be completed at the study site or at home via a reliable internet connection with caregiver support as needed. The study measures changes in behavioral and psychological symptoms of dementia using caregiver- and self-report instruments.
Who should consider this trial
Good fit: Ideal candidates are community-dwelling adults aged 65 or older with mild cognitive impairment or mild Alzheimer's-related dementia, elevated BPSD (HABC score >14), reliable internet access, the ability to consent, and a willing care partner.
Not a fit: Patients in assisted living or nursing homes, those with moderate to severe dementia, or with life expectancy under six months are unlikely to benefit or be eligible for this intervention.
Why it matters
Potential benefit: If successful, SVR could provide a scalable, at-home non-drug therapy that lessens agitation, anxiety, and other behavioral symptoms and improves patient well-being.
How similar studies have performed: Reminiscence therapy and other nonpharmacological approaches have shown benefits for mood and behavioral symptoms, but fully automated LLM-driven avatar delivery is novel and has limited prior testing.
Eligibility criteria
Show full inclusion / exclusion criteria
For the patient: Inclusion criteria: * age ≥ 65 years * diagnosis of MCI (mild cognitive impairment) or mild ADRD * access to a reliable internet connection * community-dwelling * elevated behavioral and psychological symptoms of dementia (BPSD), indicated by a HABC (Healthy Aging Brain Care) monitor score above 14 on caregiver report or self report (indicating elevated levels of BPSD) * presence of one or more specific BPSD behaviors (e.g., agitation, anxiety, depression, apathy, or sleep disturbances) * ability to consent for themselves. Exclusion criteria: * lives in an assisted living facility or nursing home * has moderate to severe ADRD as measured by the Quick Dementia Rating System * has a life expectancy of less than 6 months. For the care partner: Inclusion criteria: * ≥ 21 years old * self-identified care partner (e.g., is knowledgeable about the patient's daytime and nighttime behaviors) of a community-dwelling patient diagnosed with MCI or mild ADRD who will also participate in the study Exclusion criteria: * has MCI or dementia * has a severe mental illness or substance abuse * has a life expectancy of less than 6 months.
Where this trial is running
Indianapolis, Indiana
- Sidney & Lois Eskenazi Hospital — Indianapolis, Indiana, United States (Recruiting)
Study contacts
- Principal investigator: Malaz Boustani, MD, MPH — Indiana University
- Study coordinator: Katrina Coppedge, BA
- Email: kcoppedg@iu.edu
- Phone: 317-278-1602
How to participate
- Review the eligibility criteria above with your treating physician.
- Visit the official trial page on ClinicalTrials.gov for the most current contact information and recruitment status.
- Contact the listed study coordinator or principal investigator to request pre-screening. Pre-screening is free and never obligates you to enroll.