Three-agent chat app for lonely older adults in Hong Kong
Official title: A Mechanism Randomised Controlled Trial of a Three-Agent LLM-Augmented mHealth Intervention for Late-Life Loneliness in Older Adults
Run by The University of Hong Kong · NCT07822828 · Data updated 2026-11-12
This trial tests whether a Cantonese-language smartphone chat app with three conversational companions can help reduce loneliness in adults aged 60 and older in Hong Kong, by comparing a version powered by a large language model to a version using pre-written templates.
Quick facts
| Study type | Interventional |
|---|---|
| Ages | 60 Years and up |
| Sex | All |
| Enrollment | 72 (estimated) |
| Sponsor | The University of Hong Kong Academic / other |
| Locations | 1 site (Hong Kong, Hong Kong SAR) |
| Status | Recruiting |
| Started | October 21, 2026 |
| Main results expected | February 28, 2027 |
| Study ends | February 28, 2027 |
| Registry record updated | November 10, 2026 |
| Trial ID | NCT07822828 on ClinicalTrials.gov |
Is this trial a fit for you?
✓Likely a good fit
Ideal candidates are community-dwelling Cantonese-speaking adults aged 60+ in Hong Kong who feel at least moderately lonely and can use a smartphone.
✕Probably not a fit
Individuals with severe cognitive or sensory impairments, active suicidality, or those already receiving formal psychiatric treatment may not benefit or may be excluded.
A plain-English reading of the study's rules. Only the study team can confirm whether you qualify.
What this trial studies
In this randomized study, 72 Cantonese-speaking adults aged 60+ living in the community in Hong Kong with at least moderate loneliness will use a smartphone-based conversational app. Participants are randomized to receive either a hybrid arm with a language-model–generated assistant (plus memory, tone customization, reminiscence prompts, and model-created life-story chapters) or a built-in rule-based arm with the same interface and features minus the model-dependent capabilities. Both arms share the same visual design, three named companions, tools, and assessment prompts, isolating the effect of the language-model backend and related features. The study aims to determine whether the language-model–driven interactions provide added benefit over the template-based approach while controlling for interface richness and engagement. Outcomes focus on changes in loneliness and related well-being metrics collected through in-app assessments.
Why it matters
Potential benefit: If successful, participants may experience reduced loneliness and improved social connectedness through more engaging, personalized digital conversations.
How similar studies have gone: Previous studies of large language model–based conversational agents for loneliness are mostly early-stage; this trial adds a rigorous, architecturally matched comparator to isolate the model’s impact.
Who can join: the full rules
Show full inclusion / exclusion criteria
Inclusion Criteria: * Aged 60 years or above * Self-identified Cantonese as primary language of communication * Community-dwelling in Hong Kong (not in residential care) * De Jong Gierveld Emotional and Social Loneliness Scale total score of 2 or above at screening, indicating at least moderate loneliness * owns a smartphone on which the study app can be installed * Able to demonstrate understanding of the study using the teach-back method * Willing to provide written informed consent Exclusion Criteria: * Acute suicidality, defined as a PHQ-9 item 9 score above 1 with reported active intent * Currently receiving formal psychiatric treatment * Severe hearing or visual impairment precluding application use even with accommodation * Self-reported diagnosis of dementia or significant cognitive impairment * Unable to demonstrate understanding of the study using the teach-back method * Prior participation in the pilot runs of this trial * Another member of the same household has already registered for the study
Where it's running
-
The University of Hong Kong
Hong Kong, Hong Kong SAR, Hong Kong Recruiting
Study contacts
- Principal investigator: Junyu Zhao — The University of Hong Kong
- Study coordinator: Junyu Zhao
- Email: zhaojyxs@connect.hku.hk
- Phone: 852-60919592
Similar studies
Other studies for the same condition or treatment. Recruiting studies are listed first.
-
Social Connection Collective for older adults in subsidized housing
A resident-led program in subsidized housing in Baltimore will try to build friendships and peer support among residents aged 62 and older to see if it’s feasible and if it reduces loneliness.
-
Alive Project: Does group exercise improve social life and health in 75+ women living alone?
This study tests whether supervised group exercise at fitness clubs helps 75-year-old and older women who live alone feel less lonely and healthier compared to exercising alone or doing usual activities.
-
Mindful lifestyle social prescribing for older adults’ mood and connection
A group program about 8 weeks of mindfulness plus healthy lifestyle activities is tested to see if it helps reduce depressive symptoms and loneliness and improve quality of life in adults aged 55 and over.
-
CAPABLE Care + Connect for older adults experiencing social isolation
This project will see if combining the CAPABLE home-based support program with Johns Hopkins home-based primary care reduces loneliness and improves daily functioning for older, homebound adults.
-
CONNECT program: group telehealth to reduce loneliness and improve mental health in adults 55+
This project will test whether the group-based CONNECT telehealth program can reduce loneliness, social isolation, anxiety, and depression in adults 55 and older compared with routine community programming.
-
Need to Be Needed (N2BN): a program to boost feeling of being needed
This study will test whether weekly, personalized support to help adults with serious mental illness do acts of kindness and volunteer can reduce loneliness and social isolation.
How to take part
- Review the eligibility criteria above with your treating physician.
- Check the official listing on ClinicalTrials.gov for the latest contact details and recruitment status.
- Contact the study coordinator or principal investigator to ask for pre-screening. Pre-screening is free and never obligates you to enroll.